From 17c9e9afea69be0a514f33c20412b51ce304630c Mon Sep 17 00:00:00 2001
From: QianZhu <qian@lancedb.com>
Date: Tue, 7 Jan 2025 15:10:25 -0800
Subject: [PATCH] docs: add async examples to doc (#1941)

- added sync and async tabs for python examples
- moved python code to tests/docs

---------

Co-authored-by: Will Jones <willjones127@gmail.com>
---
 docs/mkdocs.yml                               |    8 +-
 docs/src/ann_indexes.md                       |   75 +-
 docs/src/fts.md                               |  115 +-
 docs/src/fts_tantivy.md                       |    2 +-
 docs/src/guides/scalar_index.md               |   79 +-
 docs/src/guides/storage.md                    |  299 +++--
 docs/src/guides/tables.md                     |  637 +++++-----
 docs/src/hybrid_search/hybrid_search.md       |   77 +-
 docs/src/notebooks/reproducibility.ipynb      |  546 ++++----
 .../src/notebooks/reproducibility_async.ipynb | 1096 +++++++++++++++++
 docs/src/python/pandas_and_pyarrow.md         |  105 +-
 docs/src/python/polars_arrow.md               |   55 +-
 docs/src/reranking/index.md                   |    6 +-
 docs/src/search.md                            |  153 ++-
 docs/src/sql.md                               |   40 +-
 docs/test/md_testing.py                       |    9 +-
 python/python/tests/docs/test_basic.py        |   26 +-
 python/python/tests/docs/test_guide_index.py  |  169 +++
 python/python/tests/docs/test_guide_tables.py |  576 +++++++++
 python/python/tests/docs/test_python.py       |  187 +++
 python/python/tests/docs/test_search.py       |  366 ++++++
 21 files changed, 3639 insertions(+), 987 deletions(-)
 create mode 100644 docs/src/notebooks/reproducibility_async.ipynb
 create mode 100644 python/python/tests/docs/test_guide_index.py
 create mode 100644 python/python/tests/docs/test_guide_tables.py
 create mode 100644 python/python/tests/docs/test_python.py
 create mode 100644 python/python/tests/docs/test_search.py

diff --git a/docs/mkdocs.yml b/docs/mkdocs.yml
index c41f2933..6df3c1d7 100644
--- a/docs/mkdocs.yml
+++ b/docs/mkdocs.yml
@@ -146,7 +146,9 @@ nav:
               - Building Custom Rerankers: reranking/custom_reranker.md
               - Example: notebooks/lancedb_reranking.ipynb
           - Filtering: sql.md
-          - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+          - Versioning & Reproducibility: 
+              - sync API: notebooks/reproducibility.ipynb
+              - async API: notebooks/reproducibility_async.ipynb
           - Configuring Storage: guides/storage.md
           - Migration Guide: migration.md
           - Tuning retrieval performance:
@@ -278,7 +280,9 @@ nav:
           - Building Custom Rerankers: reranking/custom_reranker.md
           - Example: notebooks/lancedb_reranking.ipynb
       - Filtering: sql.md
-      - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+      - Versioning & Reproducibility: 
+          - sync API: notebooks/reproducibility.ipynb
+          - async API: notebooks/reproducibility_async.ipynb
       - Configuring Storage: guides/storage.md
       - Migration Guide: migration.md
       - Tuning retrieval performance:
diff --git a/docs/src/ann_indexes.md b/docs/src/ann_indexes.md
index 8d293fa4..710ec8e3 100644
--- a/docs/src/ann_indexes.md
+++ b/docs/src/ann_indexes.md
@@ -18,25 +18,24 @@ See the [indexing](concepts/index_ivfpq.md) concepts guide for more information
 Lance supports `IVF_PQ` index type by default.
 
 === "Python"
+    === "Sync API"
 
-    Creating indexes is done via the [create_index](https://lancedb.github.io/lancedb/python/#lancedb.table.LanceTable.create_index) method.
+        Creating indexes is done via the [create_index](https://lancedb.github.io/lancedb/python/#lancedb.table.LanceTable.create_index) method.
 
-    ```python
-    import lancedb
-    import numpy as np
-    uri = "data/sample-lancedb"
-    db = lancedb.connect(uri)
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-numpy"
+        --8<-- "python/python/tests/docs/test_guide_index.py:create_ann_index"
+        ```
+    === "Async API"
+        Creating indexes is done via the [create_index](https://lancedb.github.io/lancedb/python/#lancedb.table.LanceTable.create_index) method.
 
-    # Create 10,000 sample vectors
-    data = [{"vector": row, "item": f"item {i}"}
-        for i, row in enumerate(np.random.random((10_000, 1536)).astype('float32'))]
-
-    # Add the vectors to a table
-    tbl = db.create_table("my_vectors", data=data)
-
-    # Create and train the index - you need to have enough data in the table for an effective training step
-    tbl.create_index(num_partitions=256, num_sub_vectors=96)
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-numpy"
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb-ivfpq"
+        --8<-- "python/python/tests/docs/test_guide_index.py:create_ann_index_async"
+        ```
 
 === "TypeScript"
 
@@ -127,7 +126,9 @@ You can specify the GPU device to train IVF partitions via
         accelerator="mps"
     )
     ```
-
+!!! note
+    GPU based indexing is not yet supported with our asynchronous client.
+    
 Troubleshooting:
 
 If you see `AssertionError: Torch not compiled with CUDA enabled`, you need to [install
@@ -152,14 +153,16 @@ There are a couple of parameters that can be used to fine-tune the search:
 
 
 === "Python"
+    === "Sync API"
 
-    ```python
-    tbl.search(np.random.random((1536))) \
-        .limit(2) \
-        .nprobes(20) \
-        .refine_factor(10) \
-        .to_pandas()
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_async"
+        ```
 
     ```text
                                               vector       item       _distance
@@ -196,10 +199,16 @@ The search will return the data requested in addition to the distance of each it
 You can further filter the elements returned by a search using a where clause.
 
 === "Python"
+    === "Sync API"
 
-    ```python
-    tbl.search(np.random.random((1536))).where("item != 'item 1141'").to_pandas()
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_with_filter"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_async_with_filter"
+        ```
 
 === "TypeScript"
 
@@ -221,10 +230,16 @@ You can select the columns returned by the query using a select clause.
 
 === "Python"
 
-    ```python
-    tbl.search(np.random.random((1536))).select(["vector"]).to_pandas()
-    ```
+    === "Sync API"
 
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_with_select"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_async_with_select"
+        ```
 
     ```text
                                                 vector _distance
diff --git a/docs/src/fts.md b/docs/src/fts.md
index c68c3714..cfc719d6 100644
--- a/docs/src/fts.md
+++ b/docs/src/fts.md
@@ -10,28 +10,20 @@ LanceDB provides support for full-text search via Lance, allowing you to incorpo
 Consider that we have a LanceDB table named `my_table`, whose string column `text` we want to index and query via keyword search, the FTS index must be created before you can search via keywords.
 
 === "Python"
+    === "Sync API"
 
-    ```python
-    import lancedb
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb-fts"
+        --8<-- "python/python/tests/docs/test_search.py:basic_fts"
+        ```
+    === "Async API"
 
-    uri = "data/sample-lancedb"
-    db = lancedb.connect(uri)
-
-    table = db.create_table(
-        "my_table",
-        data=[
-            {"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"},
-            {"vector": [5.9, 26.5], "text": "There are several kittens playing"},
-        ],
-    )
-
-    # passing `use_tantivy=False` to use lance FTS index
-    # `use_tantivy=True` by default
-    table.create_fts_index("text", use_tantivy=False)
-    table.search("puppy").limit(10).select(["text"]).to_list()
-    # [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]
-    # ...
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb-fts"
+        --8<-- "python/python/tests/docs/test_search.py:basic_fts_async"
+        ```
 
 === "TypeScript"
 
@@ -93,22 +85,32 @@ By default the text is tokenized by splitting on punctuation and whitespaces, an
 Stemming is useful for improving search results by reducing words to their root form, e.g. "running" to "run". LanceDB supports stemming for multiple languages, you can specify the tokenizer name to enable stemming by the pattern `tokenizer_name="{language_code}_stem"`, e.g. `en_stem` for English.
 
 For example, to enable stemming for English:
-```python
-table.create_fts_index("text", use_tantivy=True, tokenizer_name="en_stem")
-```
+=== "Sync API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_config_stem"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_config_stem_async"
+    ```
 
 the following [languages](https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html) are currently supported.
 
 The tokenizer is customizable, you can specify how the tokenizer splits the text, and how it filters out words, etc.
 
 For example, for language with accents, you can specify the tokenizer to use `ascii_folding` to remove accents, e.g. 'é' to 'e':
-```python
-table.create_fts_index("text",
-                        use_tantivy=False,
-                        language="French",
-                        stem=True,
-                        ascii_folding=True)
-```
+=== "Sync API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_config_folding"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_config_folding_async"
+    ```
 
 ## Filtering
 
@@ -119,9 +121,16 @@ This can be invoked via the familiar `where` syntax.
 With pre-filtering:
 === "Python"
 
-    ```python
-    table.search("puppy").limit(10).where("meta='foo'", prefilte=True).to_list()
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_prefiltering"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_prefiltering_async"
+        ```
 
 === "TypeScript"
 
@@ -151,9 +160,16 @@ With pre-filtering:
 With post-filtering:
 === "Python"
 
-    ```python
-    table.search("puppy").limit(10).where("meta='foo'", prefilte=False).to_list()
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_postfiltering"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_postfiltering_async"
+        ```
 
 === "TypeScript"
 
@@ -191,9 +207,16 @@ or a **terms** search query like `old man sea`. For more details on the terms
 query syntax, see Tantivy's [query parser rules](https://docs.rs/tantivy/latest/tantivy/query/struct.QueryParser.html).
 
 To search for a phrase, the index must be created with `with_position=True`:
-```python
-table.create_fts_index("text", use_tantivy=False, with_position=True)
-```
+=== "Sync API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_with_position"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_with_position_async"
+    ```
 This will allow you to search for phrases, but it will also significantly increase the index size and indexing time.
 
 
@@ -205,10 +228,16 @@ This can make the query more efficient, especially when the table is large and t
 
 === "Python"
 
-    ```python
-    table.add([{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"}])
-    table.optimize()
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_incremental_index"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_incremental_index_async"
+        ```
 
 === "TypeScript"
 
diff --git a/docs/src/fts_tantivy.md b/docs/src/fts_tantivy.md
index b41559dd..1c65db30 100644
--- a/docs/src/fts_tantivy.md
+++ b/docs/src/fts_tantivy.md
@@ -2,7 +2,7 @@
 
 LanceDB also provides support for full-text search via [Tantivy](https://github.com/quickwit-oss/tantivy), allowing you to incorporate keyword-based search (based on BM25) in your retrieval solutions.
 
-The tantivy-based FTS is only available in Python and does not support building indexes on object storage or incremental indexing. If you need these features, try native FTS [native FTS](fts.md).
+The tantivy-based FTS is only available in Python synchronous APIs and does not support building indexes on object storage or incremental indexing. If you need these features, try native FTS [native FTS](fts.md).
 
 ## Installation
 
diff --git a/docs/src/guides/scalar_index.md b/docs/src/guides/scalar_index.md
index 809f1c8f..97835394 100644
--- a/docs/src/guides/scalar_index.md
+++ b/docs/src/guides/scalar_index.md
@@ -32,19 +32,20 @@ over scalar columns.
 ### Create a scalar index
 === "Python"
 
-    ```python
-    import lancedb
-    books = [
-      {"book_id": 1, "publisher": "plenty of books", "tags": ["fantasy", "adventure"]},
-      {"book_id": 2, "publisher": "book town", "tags": ["non-fiction"]},
-      {"book_id": 3, "publisher": "oreilly", "tags": ["textbook"]}
-    ]
+    === "Sync API"
 
-    db = lancedb.connect("./db")
-    table = db.create_table("books", books)
-    table.create_scalar_index("book_id")  # BTree by default
-    table.create_scalar_index("publisher", index_type="BITMAP")
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb-btree-bitmap"
+        --8<-- "python/python/tests/docs/test_guide_index.py:basic_scalar_index"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb-btree-bitmap"
+        --8<-- "python/python/tests/docs/test_guide_index.py:basic_scalar_index_async"
+        ```
 
 === "Typescript"
 
@@ -62,12 +63,18 @@ The following scan will be faster if the column `book_id` has a scalar index:
 
 === "Python"
 
-    ```python
-    import lancedb
+    === "Sync API"
 
-    table = db.open_table("books")
-    my_df = table.search().where("book_id = 2").to_pandas()
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:search_with_scalar_index"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:search_with_scalar_index_async"
+        ```
 
 === "Typescript"
 
@@ -88,22 +95,18 @@ Scalar indices can also speed up scans containing a vector search or full text s
 
 === "Python"
 
-    ```python
-    import lancedb
+    === "Sync API"
 
-    data = [
-      {"book_id": 1, "vector": [1, 2]},
-      {"book_id": 2, "vector": [3, 4]},
-      {"book_id": 3, "vector": [5, 6]}
-    ]
-    table = db.create_table("book_with_embeddings", data)
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_with_scalar_index"
+        ```
+    === "Async API"
 
-    (
-        table.search([1, 2])
-        .where("book_id != 3", prefilter=True)
-        .to_pandas()
-    )
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_with_scalar_index_async"
+        ```
 
 === "Typescript"
 
@@ -122,10 +125,16 @@ Scalar indices can also speed up scans containing a vector search or full text s
 Updating the table data (adding, deleting, or modifying records) requires that you also update the scalar index. This can be done by calling `optimize`, which will trigger an update to the existing scalar index.
 === "Python"
 
-    ```python
-    table.add([{"vector": [7, 8], "book_id": 4}])
-    table.optimize()
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:update_scalar_index"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:update_scalar_index_async"
+        ```
 
 === "TypeScript"
 
diff --git a/docs/src/guides/storage.md b/docs/src/guides/storage.md
index 88cef2df..2f94dd34 100644
--- a/docs/src/guides/storage.md
+++ b/docs/src/guides/storage.md
@@ -12,26 +12,50 @@ LanceDB OSS supports object stores such as AWS S3 (and compatible stores), Azure
 === "Python"
 
     AWS S3:
+    === "Sync API"
 
-    ```python
-    import lancedb
-    db = lancedb.connect("s3://bucket/path")
-    ```
+        ```python
+        import lancedb
+        db = lancedb.connect("s3://bucket/path")
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async("s3://bucket/path")
+        ```
 
     Google Cloud Storage:
 
-    ```python
-    import lancedb
-    db = lancedb.connect("gs://bucket/path")
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect("gs://bucket/path")
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async("gs://bucket/path")
+        ```
 
     Azure Blob Storage:
 
     <!-- skip-test -->
-    ```python
-    import lancedb
-    db = lancedb.connect("az://bucket/path")
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect("az://bucket/path")
+        ```
+    <!-- skip-test -->
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async("az://bucket/path")
+        ```
     Note that for Azure, storage credentials must be configured. See [below](#azure-blob-storage) for more details.
 
 
@@ -94,13 +118,24 @@ If you only want this to apply to one particular connection, you can pass the `s
 
 === "Python"
 
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3://bucket/path",
-        storage_options={"timeout": "60s"}
-    )
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect(
+            "s3://bucket/path",
+            storage_options={"timeout": "60s"}
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
+            "s3://bucket/path",
+            storage_options={"timeout": "60s"}
+        )
+        ```
 
 === "TypeScript"
 
@@ -128,15 +163,29 @@ Getting even more specific, you can set the `timeout` for only a particular tabl
 === "Python"
 
     <!-- skip-test -->
-    ```python
-    import lancedb
-    db = await lancedb.connect_async("s3://bucket/path")
-    table = await db.create_table(
-        "table",
-        [{"a": 1, "b": 2}],
-        storage_options={"timeout": "60s"}
-    )
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect("s3://bucket/path")
+        table = db.create_table(
+            "table",
+            [{"a": 1, "b": 2}],
+            storage_options={"timeout": "60s"}
+        )
+        ```
+    <!-- skip-test -->
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async("s3://bucket/path")
+        async_table = await async_db.create_table(
+            "table",
+            [{"a": 1, "b": 2}],
+            storage_options={"timeout": "60s"}
+        )
+        ```
 
 === "TypeScript"
 
@@ -194,17 +243,32 @@ These can be set as environment variables or passed in the `storage_options` par
 
 === "Python"
 
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3://bucket/path",
-        storage_options={
-            "aws_access_key_id": "my-access-key",
-            "aws_secret_access_key": "my-secret-key",
-            "aws_session_token": "my-session-token",
-        }
-    )
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect(
+            "s3://bucket/path",
+            storage_options={
+                "aws_access_key_id": "my-access-key",
+                "aws_secret_access_key": "my-secret-key",
+                "aws_session_token": "my-session-token",
+            }
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
+            "s3://bucket/path",
+            storage_options={
+                "aws_access_key_id": "my-access-key",
+                "aws_secret_access_key": "my-secret-key",
+                "aws_session_token": "my-session-token",
+            }
+        )
+        ```
 
 === "TypeScript"
 
@@ -348,12 +412,22 @@ name of the table to use.
 
 === "Python"
 
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-    )
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect(
+            "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
+            "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
+        )    
+        ```
 
 === "JavaScript"
 
@@ -441,16 +515,30 @@ LanceDB can also connect to S3-compatible stores, such as MinIO. To do so, you m
 
 === "Python"
 
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3://bucket/path",
-        storage_options={
-            "region": "us-east-1",
-            "endpoint": "http://minio:9000",
-        }
-    )
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect(
+            "s3://bucket/path",
+            storage_options={
+                "region": "us-east-1",
+                "endpoint": "http://minio:9000",
+            }
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
+            "s3://bucket/path",
+            storage_options={
+                "region": "us-east-1",
+                "endpoint": "http://minio:9000",
+            }
+        )    
+        ```
 
 === "TypeScript"
 
@@ -502,16 +590,30 @@ To configure LanceDB to use an S3 Express endpoint, you must set the storage opt
 
 === "Python"
 
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3://my-bucket--use1-az4--x-s3/path",
-        storage_options={
-            "region": "us-east-1",
-            "s3_express": "true",
-        }
-    )
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect(
+            "s3://my-bucket--use1-az4--x-s3/path",
+            storage_options={
+                "region": "us-east-1",
+                "s3_express": "true",
+            }
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
+            "s3://my-bucket--use1-az4--x-s3/path",
+            storage_options={
+                "region": "us-east-1",
+                "s3_express": "true",
+            }
+        )    
+        ```
 
 === "TypeScript"
 
@@ -552,15 +654,29 @@ GCS credentials are configured by setting the `GOOGLE_SERVICE_ACCOUNT` environme
 === "Python"
 
     <!-- skip-test -->
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "gs://my-bucket/my-database",
-        storage_options={
-            "service_account": "path/to/service-account.json",
-        }
-    )
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = lancedb.connect(
+            "gs://my-bucket/my-database",
+            storage_options={
+                "service_account": "path/to/service-account.json",
+            }
+        )
+        ```
+    <!-- skip-test -->
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
+            "gs://my-bucket/my-database",
+            storage_options={
+                "service_account": "path/to/service-account.json",
+            }
+        )    
+        ```
 
 === "TypeScript"
 
@@ -612,16 +728,31 @@ Azure Blob Storage credentials can be configured by setting the `AZURE_STORAGE_A
 === "Python"
 
     <!-- skip-test -->
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "az://my-container/my-database",
-        storage_options={
-            account_name: "some-account",
-            account_key: "some-key",
-        }
-    )
-    ```
+    === "Sync API"
+
+        ```python
+        import lancedb
+        db = await lancedb.connect(
+            "az://my-container/my-database",
+            storage_options={
+                account_name: "some-account",
+                account_key: "some-key",
+            }
+        )
+        ```
+    <!-- skip-test -->
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
+            "az://my-container/my-database",
+            storage_options={
+                account_name: "some-account",
+                account_key: "some-key",
+            }
+        )   
+        ```
 
 === "TypeScript"
 
diff --git a/docs/src/guides/tables.md b/docs/src/guides/tables.md
index f4431771..a9fbc643 100644
--- a/docs/src/guides/tables.md
+++ b/docs/src/guides/tables.md
@@ -12,10 +12,18 @@ Initialize a LanceDB connection and create a table
 
 === "Python"
 
-    ```python
-    import lancedb
-    db = lancedb.connect("./.lancedb")
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:connect"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:connect_async"
+        ```
 
     LanceDB allows ingesting data from various sources - `dict`, `list[dict]`, `pd.DataFrame`, `pa.Table` or a `Iterator[pa.RecordBatch]`. Let's take a look at some of the these.
 
@@ -47,18 +55,16 @@ Initialize a LanceDB connection and create a table
 
 === "Python"
 
-    ```python
-    import lancedb
+    === "Sync API"
 
-    db = lancedb.connect("./.lancedb")
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table"
+        ```
+    === "Async API"
 
-    data = [{"vector": [1.1, 1.2], "lat": 45.5, "long": -122.7},
-            {"vector": [0.2, 1.8], "lat": 40.1, "long": -74.1}]
-
-    db.create_table("my_table", data)
-
-    db["my_table"].head()
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async"
+        ```
 
     !!! info "Note"
         If the table already exists, LanceDB will raise an error by default.
@@ -67,16 +73,30 @@ Initialize a LanceDB connection and create a table
         and the table exists, then it simply opens the existing table. The data you
         passed in will NOT be appended to the table in that case.
 
-    ```python
-    db.create_table("name", data, exist_ok=True)
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_exist_ok"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_exist_ok"
+        ```
 
     Sometimes you want to make sure that you start fresh. If you want to
     overwrite the table, you can pass in mode="overwrite" to the createTable function.
 
-    ```python
-    db.create_table("name", data, mode="overwrite")
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_overwrite"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_overwrite"
+        ```
 
 === "Typescript[^1]"
     You can create a LanceDB table in JavaScript using an array of records as follows.
@@ -146,34 +166,37 @@ Initialize a LanceDB connection and create a table
 
 ### From a Pandas DataFrame
 
-```python
-import pandas as pd
 
-data = pd.DataFrame({
-    "vector": [[1.1, 1.2, 1.3, 1.4], [0.2, 1.8, 0.4, 3.6]],
-    "lat": [45.5, 40.1],
-    "long": [-122.7, -74.1]
-})
+=== "Sync API"
 
-db.create_table("my_table", data)
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pandas"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_pandas"
+    ```
+=== "Async API"
 
-db["my_table"].head()
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pandas"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_pandas"
+    ```
 
 !!! info "Note"
     Data is converted to Arrow before being written to disk. For maximum control over how data is saved, either provide the PyArrow schema to convert to or else provide a PyArrow Table directly.
 
 The **`vector`** column needs to be a [Vector](../python/pydantic.md#vector-field) (defined as [pyarrow.FixedSizeList](https://arrow.apache.org/docs/python/generated/pyarrow.list_.html)) type.
 
-```python
-custom_schema = pa.schema([
-pa.field("vector", pa.list_(pa.float32(), 4)),
-pa.field("lat", pa.float32()),
-pa.field("long", pa.float32())
-])
+=== "Sync API"
 
-table = db.create_table("my_table", data, schema=custom_schema)
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_custom_schema"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_custom_schema"
+    ```
 
 ### From a Polars DataFrame
 
@@ -182,45 +205,38 @@ written in Rust. Just like in Pandas, the Polars integration is enabled by PyArr
 under the hood. A deeper integration between LanceDB Tables and Polars DataFrames
 is on the way.
 
-```python
-import polars as pl
+=== "Sync API"
 
-data = pl.DataFrame({
-    "vector": [[3.1, 4.1], [5.9, 26.5]],
-    "item": ["foo", "bar"],
-    "price": [10.0, 20.0]
-})
-table = db.create_table("pl_table", data=data)
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-polars"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_polars"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-polars"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_polars"
+    ```
 
 ### From an Arrow Table
 You can also create LanceDB tables directly from Arrow tables.
 LanceDB supports float16 data type!
 
 === "Python"
+    === "Sync API"
 
-    ```python
-    import pyarrows as pa
-    import numpy as np
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-numpy"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_arrow_table"
+        ```
+    === "Async API"
 
-    dim = 16
-    total = 2
-    schema = pa.schema(
-        [
-            pa.field("vector", pa.list_(pa.float16(), dim)),
-            pa.field("text", pa.string())
-        ]
-    )
-    data = pa.Table.from_arrays(
-        [
-            pa.array([np.random.randn(dim).astype(np.float16) for _ in range(total)],
-                    pa.list_(pa.float16(), dim)),
-            pa.array(["foo", "bar"])
-        ],
-        ["vector", "text"],
-    )
-    tbl = db.create_table("f16_tbl", data, schema=schema)
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-polars"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-numpy"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_arrow_table"
+        ```
 
 === "Typescript[^1]"
 
@@ -250,25 +266,22 @@ can be configured with the vector dimensions. It is also important to note that
 LanceDB only understands subclasses of `lancedb.pydantic.LanceModel`
 (which itself derives from `pydantic.BaseModel`).
 
-```python
-from lancedb.pydantic import Vector, LanceModel
+=== "Sync API"
 
-class Content(LanceModel):
-    movie_id: int
-    vector: Vector(128)
-    genres: str
-    title: str
-    imdb_id: int
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:class-Content"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_pydantic"
+    ```
+=== "Async API"
 
-    @property
-    def imdb_url(self) -> str:
-        return f"https://www.imdb.com/title/tt{self.imdb_id}"
-
-import pyarrow as pa
-db = lancedb.connect("~/.lancedb")
-table_name = "movielens_small"
-table = db.create_table(table_name, schema=Content)
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:class-Content"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_pydantic"
+    ```
 
 #### Nested schemas
 
@@ -277,22 +290,24 @@ For example, you may want to store the document string
 and the document source name as a nested Document object:
 
 ```python
-class Document(BaseModel):
-    content: str
-    source: str
+--8<-- "python/python/tests/docs/test_guide_tables.py:import-pydantic-basemodel"
+--8<-- "python/python/tests/docs/test_guide_tables.py:class-Document"
 ```
 
 This can be used as the type of a LanceDB table column:
 
-```python
-class NestedSchema(LanceModel):
-    id: str
-    vector: Vector(1536)
-    document: Document
+=== "Sync API"
 
-tbl = db.create_table("nested_table", schema=NestedSchema, mode="overwrite")
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:class-NestedSchema"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_nested_schema"
+    ```
+=== "Async API"
 
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:class-NestedSchema"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_nested_schema"
+    ```
 This creates a struct column called "document" that has two subfields
 called "content" and "source":
 
@@ -356,29 +371,20 @@ LanceDB additionally supports PyArrow's `RecordBatch` Iterators or other generat
 
 Here's an example using using `RecordBatch` iterator for creating tables.
 
-```python
-import pyarrow as pa
+=== "Sync API"
 
-def make_batches():
-    for i in range(5):
-        yield pa.RecordBatch.from_arrays(
-            [
-                pa.array([[3.1, 4.1, 5.1, 6.1], [5.9, 26.5, 4.7, 32.8]],
-                        pa.list_(pa.float32(), 4)),
-                pa.array(["foo", "bar"]),
-                pa.array([10.0, 20.0]),
-            ],
-            ["vector", "item", "price"],
-        )
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:make_batches"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_batch"
+    ```
+=== "Async API"
 
-schema = pa.schema([
-    pa.field("vector", pa.list_(pa.float32(), 4)),
-    pa.field("item", pa.utf8()),
-    pa.field("price", pa.float32()),
-])
-
-db.create_table("batched_tale", make_batches(), schema=schema)
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:make_batches"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_batch"
+    ```
 
 You can also use iterators of other types like Pandas DataFrame or Pylists directly in the above example.
 
@@ -387,15 +393,29 @@ You can also use iterators of other types like Pandas DataFrame or Pylists direc
 === "Python"
     If you forget the name of your table, you can always get a listing of all table names.
 
-    ```python
-    print(db.table_names())
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:list_tables"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:list_tables_async"
+        ```
 
     Then, you can open any existing tables.
 
-    ```python
-    tbl = db.open_table("my_table")
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:open_table"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:open_table_async"
+        ```
 
 === "Typescript[^1]"
 
@@ -418,35 +438,41 @@ You can create an empty table for scenarios where you want to add data to the ta
 
 
     An empty table can be initialized via a PyArrow schema.
+    === "Sync API"
 
-    ```python
-    import lancedb
-    import pyarrow as pa
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_empty_table"
+        ```
+    === "Async API"
 
-    schema = pa.schema(
-      [
-          pa.field("vector", pa.list_(pa.float32(), 2)),
-          pa.field("item", pa.string()),
-          pa.field("price", pa.float32()),
-      ])
-    tbl = db.create_table("empty_table_add", schema=schema)
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_empty_table_async"
+        ```
 
     Alternatively, you can also use Pydantic to specify the schema for the empty table. Note that we do not
     directly import `pydantic` but instead use `lancedb.pydantic` which is a subclass of `pydantic.BaseModel`
     that has been extended to support LanceDB specific types like `Vector`.
 
-    ```python
-    import lancedb
-    from lancedb.pydantic import LanceModel, vector
+    === "Sync API"
 
-    class Item(LanceModel):
-        vector: Vector(2)
-        item: str
-        price: float
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:class-Item"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_empty_table_pydantic"
+        ```
+    === "Async API"
 
-    tbl = db.create_table("empty_table_add", schema=Item.to_arrow_schema())
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:class-Item"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_empty_table_async_pydantic"
+        ```
 
     Once the empty table has been created, you can add data to it via the various methods listed in the [Adding to a table](#adding-to-a-table) section.
 
@@ -473,86 +499,96 @@ After a table has been created, you can always add more data to it using the `ad
 
     ### Add a Pandas DataFrame
 
-    ```python
-    df = pd.DataFrame({
-        "vector": [[1.3, 1.4], [9.5, 56.2]], "item": ["banana", "apple"], "price": [5.0, 7.0]
-    })
-    tbl.add(df)
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_pandas"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_pandas"
+        ```
 
     ### Add a Polars DataFrame
 
-    ```python
-    df = pl.DataFrame({
-        "vector": [[1.3, 1.4], [9.5, 56.2]], "item": ["banana", "apple"], "price": [5.0, 7.0]
-    })
-    tbl.add(df)
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_polars"
+        ```
+    === "Async API"
+    
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_polars"
+        ```
 
     ### Add an Iterator
 
     You can also add a large dataset batch in one go using Iterator of any supported data types.
 
-    ```python
-    def make_batches():
-        for i in range(5):
-            yield [
-                    {"vector": [3.1, 4.1], "item": "peach", "price": 6.0},
-                    {"vector": [5.9, 26.5], "item": "pear", "price": 5.0}
-                ]
-    tbl.add(make_batches())
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:make_batches_for_add"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_batch"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:make_batches_for_add"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_batch"
+        ```
 
     ### Add a PyArrow table
 
     If you have data coming in as a PyArrow table, you can add it directly to the LanceDB table.
 
-    ```python
-    pa_table = pa.Table.from_arrays(
-            [
-                pa.array([[9.1, 6.7], [9.9, 31.2]],
-                        pa.list_(pa.float32(), 2)),
-                pa.array(["mango", "orange"]),
-                pa.array([7.0, 4.0]),
-            ],
-            ["vector", "item", "price"],
-        )
+    === "Sync API"
 
-    tbl.add(pa_table)
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_pyarrow"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_pyarrow"
+        ```
 
     ### Add a Pydantic Model
 
     Assuming that a table has been created with the correct schema as shown [above](#creating-empty-table), you can add data items that are valid Pydantic models to the table.
 
-    ```python
-    pydantic_model_items = [
-        Item(vector=[8.1, 4.7], item="pineapple", price=10.0),
-        Item(vector=[6.9, 9.3], item="avocado", price=9.0)
-    ]
+    === "Sync API"
 
-    tbl.add(pydantic_model_items)
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_pydantic"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_pydantic"
+        ```
 
     ??? "Ingesting Pydantic models with LanceDB embedding API"
         When using LanceDB's embedding API, you can add Pydantic models directly to the table. LanceDB will automatically convert the `vector` field to a vector before adding it to the table. You need to specify the default value of `vector` field as None to allow LanceDB to automatically vectorize the data.
 
-        ```python
-        import lancedb
-        from lancedb.pydantic import LanceModel, Vector
-        from lancedb.embeddings import get_registry
+        === "Sync API"
 
-        db = lancedb.connect("~/tmp")
-        embed_fcn = get_registry().get("huggingface").create(name="BAAI/bge-small-en-v1.5")
+            ```python
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-embeddings"
+            --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_with_embedding"
+            ```
+        === "Async API"
 
-        class Schema(LanceModel):
-            text: str = embed_fcn.SourceField()
-            vector: Vector(embed_fcn.ndims()) = embed_fcn.VectorField(default=None)
-
-        tbl = db.create_table("my_table", schema=Schema, mode="overwrite")
-        models = [Schema(text="hello"), Schema(text="world")]
-        tbl.add(models)
-        ```
+            ```python
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-embeddings"
+            --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_with_embedding"
+            ```
 
 === "Typescript[^1]"
 
@@ -571,44 +607,41 @@ Use the `delete()` method on tables to delete rows from a table. To choose which
 
 === "Python"
 
-    ```python
-    tbl.delete('item = "fizz"')
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_row"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_row_async"
+        ```
 
     ### Deleting row with specific column value
 
-    ```python
-    import lancedb
+    === "Sync API"
 
-    data = [{"x": 1, "vector": [1, 2]},
-            {"x": 2, "vector": [3, 4]},
-            {"x": 3, "vector": [5, 6]}]
-    db = lancedb.connect("./.lancedb")
-    table = db.create_table("my_table", data)
-    table.to_pandas()
-    #   x      vector
-    # 0  1  [1.0, 2.0]
-    # 1  2  [3.0, 4.0]
-    # 2  3  [5.0, 6.0]
-
-    table.delete("x = 2")
-    table.to_pandas()
-    #   x      vector
-    # 0  1  [1.0, 2.0]
-    # 1  3  [5.0, 6.0]
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_specific_row"
+        ```
+    === "Async API"
 
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_specific_row_async"
+        ```
+    
     ### Delete from a list of values
+    === "Sync API"
 
-    ```python
-    to_remove = [1, 5]
-    to_remove = ", ".join(str(v) for v in to_remove)
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_list_values"
+        ```
+    === "Async API"
 
-    table.delete(f"x IN ({to_remove})")
-    table.to_pandas()
-    #   x      vector
-    # 0  3  [5.0, 6.0]
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_list_values_async"
+        ```
 
 === "Typescript[^1]"
 
@@ -659,27 +692,20 @@ This can be used to update zero to all rows depending on how many rows match the
 === "Python"
 
     API Reference: [lancedb.table.Table.update][]
+    === "Sync API"
 
-    ```python
-    import lancedb
-    import pandas as pd
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pandas"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:update_table"
+        ```
+    === "Async API"
 
-    # Create a lancedb connection
-    db = lancedb.connect("./.lancedb")
-
-    # Create a table from a pandas DataFrame
-    data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
-    table = db.create_table("my_table", data)
-
-    # Update the table where x = 2
-    table.update(where="x = 2", values={"vector": [10, 10]})
-
-    # Get the updated table as a pandas DataFrame
-    df = table.to_pandas()
-
-    # Print the DataFrame
-    print(df)
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pandas"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:update_table_async"
+        ```
 
     Output
     ```shell
@@ -734,13 +760,16 @@ This can be used to update zero to all rows depending on how many rows match the
   The `values` parameter is used to provide the new values for the columns as literal values. You can also use the `values_sql` / `valuesSql` parameter to provide SQL expressions for the new values. For example, you can use `values_sql="x + 1"` to increment the value of the `x` column by 1.
 
 === "Python"
+    === "Sync API"
 
-    ```python
-    # Update the table where x = 2
-    table.update(valuesSql={"x": "x + 1"})
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:update_table_sql"
+        ```
+    === "Async API"
 
-    print(table.to_pandas())
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:update_table_sql_async"
+        ```
 
     Output
     ```shell
@@ -771,11 +800,16 @@ This can be used to update zero to all rows depending on how many rows match the
 Use the `drop_table()` method on the database to remove a table.
 
 === "Python"
+    === "Sync API"
 
-      ```python
-      --8<-- "python/python/tests/docs/test_basic.py:drop_table"
-      --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
-      ```
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:drop_table"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
+        ```
 
       This permanently removes the table and is not recoverable, unlike deleting rows.
       By default, if the table does not exist an exception is raised. To suppress this,
@@ -809,9 +843,16 @@ data type for it.
 
 === "Python"
 
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:add_columns"
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:add_columns"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:add_columns_async"
+        ```
     **API Reference:** [lancedb.table.Table.add_columns][]
 
 === "Typescript"
@@ -848,10 +889,18 @@ rewriting the column, which can be a heavy operation.
 
 === "Python"
 
-    ```python
-    import pyarrow as pa
-    --8<-- "python/python/tests/docs/test_basic.py:alter_columns"
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+        --8<-- "python/python/tests/docs/test_basic.py:alter_columns"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+        --8<-- "python/python/tests/docs/test_basic.py:alter_columns_async"
+        ```
     **API Reference:** [lancedb.table.Table.alter_columns][]
 
 === "Typescript"
@@ -872,9 +921,16 @@ will remove the column from the schema.
 
 === "Python"
 
-    ```python
-     --8<-- "python/python/tests/docs/test_basic.py:drop_columns"
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:drop_columns"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:drop_columns_async"
+        ```
     **API Reference:** [lancedb.table.Table.drop_columns][]
 
 === "Typescript"
@@ -925,31 +981,46 @@ There are three possible settings for `read_consistency_interval`:
 
     To set strong consistency, use `timedelta(0)`:
 
-    ```python
-    from datetime import timedelta
-    db = lancedb.connect("./.lancedb",. read_consistency_interval=timedelta(0))
-    table = db.open_table("my_table")
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-datetime"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_strong_consistency"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-datetime"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_async_strong_consistency"
+        ```
 
     For eventual consistency, use a custom `timedelta`:
 
-    ```python
-    from datetime import timedelta
-    db = lancedb.connect("./.lancedb", read_consistency_interval=timedelta(seconds=5))
-    table = db.open_table("my_table")
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-datetime"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_eventual_consistency"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-datetime"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_async_eventual_consistency"
+        ```
 
     By default, a `Table` will never check for updates from other writers. To manually check for updates you can use `checkout_latest`:
 
-    ```python
-    db = lancedb.connect("./.lancedb")
-    table = db.open_table("my_table")
+    === "Sync API"
 
-    # (Other writes happen to my_table from another process)
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_checkout_latest"
+        ```
+    === "Async API"
 
-    # Check for updates
-    table.checkout_latest()
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_async_checkout_latest"
+        ```
 
 === "Typescript[^1]"
 
@@ -957,14 +1028,14 @@ There are three possible settings for `read_consistency_interval`:
 
     ```ts
     const db = await lancedb.connect({ uri: "./.lancedb", readConsistencyInterval: 0 });
-    const table = await db.openTable("my_table");
+    const tbl = await db.openTable("my_table");
     ```
 
     For eventual consistency, specify the update interval as seconds:
 
     ```ts
     const db = await lancedb.connect({ uri: "./.lancedb", readConsistencyInterval: 5 });
-    const table = await db.openTable("my_table");
+    const tbl = await db.openTable("my_table");
     ```
 
 <!-- Node doesn't yet support the version time travel: https://github.com/lancedb/lancedb/issues/1007
diff --git a/docs/src/hybrid_search/hybrid_search.md b/docs/src/hybrid_search/hybrid_search.md
index 823a9b8a..89f74fc4 100644
--- a/docs/src/hybrid_search/hybrid_search.md
+++ b/docs/src/hybrid_search/hybrid_search.md
@@ -5,57 +5,46 @@ LanceDB supports both semantic and keyword-based search (also termed full-text s
 ## Hybrid search in LanceDB
 You can perform hybrid search in LanceDB by combining the results of semantic and full-text search via a reranking algorithm of your choice. LanceDB provides multiple rerankers out of the box. However, you can always write a custom reranker if your use case need more sophisticated logic .
 
-```python
-import os
+=== "Sync API"
 
-import lancedb
-import openai
-from lancedb.embeddings import get_registry
-from lancedb.pydantic import LanceModel, Vector
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:import-os"
+    --8<-- "python/python/tests/docs/test_search.py:import-openai"
+    --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
+    --8<-- "python/python/tests/docs/test_search.py:import-embeddings"
+    --8<-- "python/python/tests/docs/test_search.py:import-pydantic"
+    --8<-- "python/python/tests/docs/test_search.py:import-lancedb-fts"
+    --8<-- "python/python/tests/docs/test_search.py:import-openai-embeddings"
+    --8<-- "python/python/tests/docs/test_search.py:class-Documents"
+    --8<-- "python/python/tests/docs/test_search.py:basic_hybrid_search"
+    ```
+=== "Async API"
 
-db = lancedb.connect("~/.lancedb")
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:import-os"
+    --8<-- "python/python/tests/docs/test_search.py:import-openai"
+    --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
+    --8<-- "python/python/tests/docs/test_search.py:import-embeddings"
+    --8<-- "python/python/tests/docs/test_search.py:import-pydantic"
+    --8<-- "python/python/tests/docs/test_search.py:import-lancedb-fts"
+    --8<-- "python/python/tests/docs/test_search.py:import-openai-embeddings"
+    --8<-- "python/python/tests/docs/test_search.py:class-Documents"
+    --8<-- "python/python/tests/docs/test_search.py:basic_hybrid_search_async"
+    ```
 
-# Ingest embedding function in LanceDB table
-# Configuring the environment variable OPENAI_API_KEY
-if "OPENAI_API_KEY" not in os.environ:
-# OR set the key here as a variable
-    openai.api_key = "sk-..."
-embeddings = get_registry().get("openai").create()
-
-class Documents(LanceModel):
-    vector: Vector(embeddings.ndims()) = embeddings.VectorField()
-    text: str = embeddings.SourceField()
-
-table = db.create_table("documents", schema=Documents)
-
-data = [
-    { "text": "rebel spaceships striking from a hidden base"},
-    { "text": "have won their first victory against the evil Galactic Empire"},
-    { "text": "during the battle rebel spies managed to steal secret plans"},
-    { "text": "to the Empire's ultimate weapon the Death Star"}
-]
-
-# ingest docs with auto-vectorization
-table.add(data)
-
-# Create a fts index before the hybrid search
-table.create_fts_index("text")
-# hybrid search with default reranker
-results = table.search("flower moon", query_type="hybrid").to_pandas()
-```
 !!! Note
     You can also pass the vector and text query manually. This is useful if you're not using the embedding API or if you're using a separate embedder service.
 ### Explicitly passing the vector and text query
-```python
-vector_query = [0.1, 0.2, 0.3, 0.4, 0.5]
-text_query = "flower moon"
-results = table.search(query_type="hybrid")
-                .vector(vector_query)
-                .text(text_query)
-                .limit(5)
-                .to_pandas()
+=== "Sync API"
 
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:hybrid_search_pass_vector_text"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:hybrid_search_pass_vector_text_async"
+    ```
 
 By default, LanceDB uses `RRFReranker()`, which uses reciprocal rank fusion score, to combine and rerank the results of semantic and full-text search. You can customize the hyperparameters as needed or write your own custom reranker. Here's how you can use any of the available rerankers:
 
diff --git a/docs/src/notebooks/reproducibility.ipynb b/docs/src/notebooks/reproducibility.ipynb
index ff65b20a..44bca99b 100644
--- a/docs/src/notebooks/reproducibility.ipynb
+++ b/docs/src/notebooks/reproducibility.ipynb
@@ -5,7 +5,7 @@
    "id": "c0de1e6a-61f7-4f99-a2fd-1461902ab36a",
    "metadata": {},
    "source": [
-    "# Versioning & Reproducibility\n",
+    "# Sync API\n",
     "\n",
     "Reproducibility is critical for AI. For code, it's easy to keep track of changes using Github or Gitlab.\n",
     "For data, it's not as easy. Most of the time, we're manually writing complicated data tracking code, wrestling with an external tool, and dealing with expensive duplicate snapshot copies with low granularity.\n",
@@ -34,61 +34,54 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0e74818f-109e-4b09-b5f8-dd1875c512e3",
+   "id": "14605311",
    "metadata": {},
    "source": [
-    "We'll start with a local LanceDB connection"
+    "Let's first prepare the data. We will be using a CSV file with a bunch of quotes from Rick and Morty"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "1f57d988-56b9-4384-8a7b-000d5f91034a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import lancedb\n",
-    "db = lancedb.connect(\"~/.lancedb\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9c4c443d-2f14-455d-b766-bacbaad43d20",
-   "metadata": {},
-   "source": [
-    "We've got a CSV file with a bunch of quotes from Rick and Morty"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "08556aeb-6bdc-451c-99f5-163374fdec55",
+   "id": "c02976c7",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "id,quote,author\n",
-      "1,\"Nobody exists on purpose. Nobody belongs anywhere.\",Morty\n",
-      "2,\"We're all going to die. Come watch TV.\",Morty\n",
-      "3,\"Losers look stuff up while the rest of us are carpin' all them diems.\",Summer\n",
-      "4,\"He's not a hot girl. He can't just bail on his life and set up shop in someone else's.\",Beth\n",
-      "5,\"When you are an a—hole, it doesn't matter how right you are. Nobody wants to give you the satisfaction.\",Morty\n",
-      "6,\"God's turning people into insect monsters, Beth. I'm the one beating them to death. Thank me.\",Jerry\n",
-      "7,\"Camping is just being homeless without the change.\",Summer\n",
-      "8,\"This seems like a good time for a drink and a cold, calculated speech with sinister overtones. A speech about politics, about order, brotherhood, power ... but speeches are for campaigning. Now is the time for action.\",Morty\n",
-      "9,\"Having a family doesn't mean that you stop being an individual. You know the best thing you can do for the people that depend on you? Be honest with them, even if it means setting them free.\",Mr. Meeseeks\n"
+      "--2024-12-17 11:54:43--  http://vectordb-recipes.s3.us-west-2.amazonaws.com/rick_and_morty_quotes.csv\n",
+      "Resolving vectordb-recipes.s3.us-west-2.amazonaws.com (vectordb-recipes.s3.us-west-2.amazonaws.com)... 52.92.138.34, 3.5.82.160, 52.218.236.161, ...\n",
+      "Connecting to vectordb-recipes.s3.us-west-2.amazonaws.com (vectordb-recipes.s3.us-west-2.amazonaws.com)|52.92.138.34|:80... connected.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 8236 (8.0K) [text/csv]\n",
+      "Saving to: ‘rick_and_morty_quotes.csv.1’\n",
+      "\n",
+      "rick_and_morty_quot 100%[===================>]   8.04K  --.-KB/s    in 0s      \n",
+      "\n",
+      "2024-12-17 11:54:43 (77.8 MB/s) - ‘rick_and_morty_quotes.csv.1’ saved [8236/8236]\n",
+      "\n",
+      "id,author,quote\n",
+      "1,Rick,\" Morty, you got to come on. You got to come with me.\"\n",
+      "2,Morty,\" Rick, what’s going on?\"\n",
+      "3,Rick,\" I got a surprise for you, Morty.\"\n",
+      "4,Morty,\" It’s the middle of the night. What are you talking about?\"\n",
+      "5,Rick,\" I got a surprise for you.\"\n",
+      "6,Morty,\" Ow! Ow! You’re tugging me too hard.\"\n",
+      "7,Rick,\" I got a surprise for you, Morty.\"\n",
+      "8,Rick,\" What do you think of this flying vehicle, Morty? I built it out of stuff I found in the garage.\"\n",
+      "9,Morty,\" Yeah, Rick, it’s great. Is this the surprise?\"\n"
      ]
     }
    ],
    "source": [
+    "!wget http://vectordb-recipes.s3.us-west-2.amazonaws.com/rick_and_morty_quotes.csv\n",
     "!head rick_and_morty_quotes.csv"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "a5fcdcda-b0fe-4ac4-90b4-6b42cf2ef34d",
+   "id": "533c5f58",
    "metadata": {},
    "source": [
     "Let's load this into a pandas dataframe.\n",
@@ -98,8 +91,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "def3ae59-77d9-43f0-ba6d-415a1503856b",
+   "execution_count": 2,
+   "id": "ee1443e3",
    "metadata": {},
    "outputs": [
     {
@@ -124,55 +117,55 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>id</th>\n",
-       "      <th>quote</th>\n",
        "      <th>author</th>\n",
+       "      <th>quote</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>1</td>\n",
-       "      <td>Nobody exists on purpose. Nobody belongs anywh...</td>\n",
-       "      <td>Morty</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, you got to come on. You got to come wi...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>2</td>\n",
-       "      <td>We're all going to die. Come watch TV.</td>\n",
        "      <td>Morty</td>\n",
+       "      <td>Rick, what’s going on?</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>3</td>\n",
-       "      <td>Losers look stuff up while the rest of us are ...</td>\n",
-       "      <td>Summer</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>4</td>\n",
-       "      <td>He's not a hot girl. He can't just bail on his...</td>\n",
-       "      <td>Beth</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>It’s the middle of the night. What are you ta...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>5</td>\n",
-       "      <td>When you are an a—hole, it doesn't matter how ...</td>\n",
-       "      <td>Morty</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you.</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "   id                                              quote  author\n",
-       "0   1  Nobody exists on purpose. Nobody belongs anywh...   Morty\n",
-       "1   2             We're all going to die. Come watch TV.   Morty\n",
-       "2   3  Losers look stuff up while the rest of us are ...  Summer\n",
-       "3   4  He's not a hot girl. He can't just bail on his...    Beth\n",
-       "4   5  When you are an a—hole, it doesn't matter how ...   Morty"
+       "   id author                                              quote\n",
+       "0   1   Rick   Morty, you got to come on. You got to come wi...\n",
+       "1   2  Morty                             Rick, what’s going on?\n",
+       "2   3   Rick                   I got a surprise for you, Morty.\n",
+       "3   4  Morty   It’s the middle of the night. What are you ta...\n",
+       "4   5   Rick                          I got a surprise for you."
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -183,6 +176,35 @@
     "df.head()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "0e74818f-109e-4b09-b5f8-dd1875c512e3",
+   "metadata": {},
+   "source": [
+    "We'll start with a local LanceDB connection"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "fa27ab30",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install lancedb -q"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1f57d988-56b9-4384-8a7b-000d5f91034a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lancedb\n",
+    "db = lancedb.connect(\"~/.lancedb\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "4ba9ffac-c779-49e3-91a7-f1c00f3fda41",
@@ -193,7 +215,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "bd981f6d-b921-4b1d-b63a-6c1d59f3a51d",
    "metadata": {},
    "outputs": [
@@ -219,55 +241,55 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>id</th>\n",
-       "      <th>quote</th>\n",
        "      <th>author</th>\n",
+       "      <th>quote</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>1</td>\n",
-       "      <td>Nobody exists on purpose. Nobody belongs anywh...</td>\n",
-       "      <td>Morty</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, you got to come on. You got to come wi...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>2</td>\n",
-       "      <td>We're all going to die. Come watch TV.</td>\n",
        "      <td>Morty</td>\n",
+       "      <td>Rick, what’s going on?</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>3</td>\n",
-       "      <td>Losers look stuff up while the rest of us are ...</td>\n",
-       "      <td>Summer</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>4</td>\n",
-       "      <td>He's not a hot girl. He can't just bail on his...</td>\n",
-       "      <td>Beth</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>It’s the middle of the night. What are you ta...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>5</td>\n",
-       "      <td>When you are an a—hole, it doesn't matter how ...</td>\n",
-       "      <td>Morty</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you.</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "   id                                              quote  author\n",
-       "0   1  Nobody exists on purpose. Nobody belongs anywh...   Morty\n",
-       "1   2             We're all going to die. Come watch TV.   Morty\n",
-       "2   3  Losers look stuff up while the rest of us are ...  Summer\n",
-       "3   4  He's not a hot girl. He can't just bail on his...    Beth\n",
-       "4   5  When you are an a—hole, it doesn't matter how ...   Morty"
+       "   id author                                              quote\n",
+       "0   1   Rick   Morty, you got to come on. You got to come wi...\n",
+       "1   2  Morty                             Rick, what’s going on?\n",
+       "2   3   Rick                   I got a surprise for you, Morty.\n",
+       "3   4  Morty   It’s the middle of the night. What are you ta...\n",
+       "4   5   Rick                          I got a surprise for you."
       ]
      },
-     "execution_count": 4,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -301,7 +323,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "9eac4708-a8c4-49aa-bc13-8e60c5bf34a0",
    "metadata": {},
    "outputs": [
@@ -327,40 +349,40 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>id</th>\n",
-       "      <th>quote</th>\n",
        "      <th>author</th>\n",
+       "      <th>quote</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>1</td>\n",
-       "      <td>Nobody exists on purpose. Nobody belongs anywh...</td>\n",
+       "      <td>2</td>\n",
        "      <td>Morty</td>\n",
+       "      <td>Rick, what’s going on?</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>2</td>\n",
-       "      <td>We're all going to die. Come watch TV.</td>\n",
+       "      <td>4</td>\n",
        "      <td>Morty</td>\n",
+       "      <td>It’s the middle of the night. What are you ta...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>3</td>\n",
-       "      <td>Losers look stuff up while the rest of us are ...</td>\n",
-       "      <td>Summer</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Ow! Ow! You’re tugging me too hard.</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>4</td>\n",
-       "      <td>He's not a hot girl. He can't just bail on his...</td>\n",
-       "      <td>Beth</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Yeah, Rick, it’s great. Is this the surprise?</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>5</td>\n",
-       "      <td>When you are an a—hole, it doesn't matter how ...</td>\n",
+       "      <td>11</td>\n",
        "      <td>Morty</td>\n",
+       "      <td>What?! A bomb?!</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
@@ -369,71 +391,71 @@
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>56</th>\n",
-       "      <td>57</td>\n",
-       "      <td>If I let you make me nervous, then we can't ge...</td>\n",
+       "      <th>94</th>\n",
+       "      <td>80</td>\n",
        "      <td>Richard Daniel Sanchez</td>\n",
+       "      <td>There you are, Morty. Listen to me. I got an ...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>57</th>\n",
-       "      <td>58</td>\n",
-       "      <td>Oh, boy, so you actually learned something tod...</td>\n",
+       "      <th>95</th>\n",
+       "      <td>82</td>\n",
        "      <td>Richard Daniel Sanchez</td>\n",
+       "      <td>It’s pretty obvious, Morty. I froze him. Now ...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>58</th>\n",
-       "      <td>59</td>\n",
-       "      <td>I can't abide bureaucracy. I don't like being ...</td>\n",
+       "      <th>96</th>\n",
+       "      <td>84</td>\n",
        "      <td>Richard Daniel Sanchez</td>\n",
+       "      <td>Do you have any concept of how much higher th...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>59</th>\n",
-       "      <td>60</td>\n",
-       "      <td>I think you have to think ahead and live in th...</td>\n",
+       "      <th>97</th>\n",
+       "      <td>86</td>\n",
        "      <td>Richard Daniel Sanchez</td>\n",
+       "      <td>I’ll do it later, Morty. He’ll be fine. Let’s...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>60</th>\n",
-       "      <td>61</td>\n",
-       "      <td>I know that new situations can be intimidating...</td>\n",
+       "      <th>98</th>\n",
+       "      <td>97</td>\n",
        "      <td>Richard Daniel Sanchez</td>\n",
+       "      <td>There she is. All right. Come on, Morty. Let’...</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>61 rows × 3 columns</p>\n",
+       "<p>99 rows × 3 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "    id                                              quote  \\\n",
-       "0    1  Nobody exists on purpose. Nobody belongs anywh...   \n",
-       "1    2             We're all going to die. Come watch TV.   \n",
-       "2    3  Losers look stuff up while the rest of us are ...   \n",
-       "3    4  He's not a hot girl. He can't just bail on his...   \n",
-       "4    5  When you are an a—hole, it doesn't matter how ...   \n",
-       "..  ..                                                ...   \n",
-       "56  57  If I let you make me nervous, then we can't ge...   \n",
-       "57  58  Oh, boy, so you actually learned something tod...   \n",
-       "58  59  I can't abide bureaucracy. I don't like being ...   \n",
-       "59  60  I think you have to think ahead and live in th...   \n",
-       "60  61  I know that new situations can be intimidating...   \n",
+       "    id                  author  \\\n",
+       "0    2                   Morty   \n",
+       "1    4                   Morty   \n",
+       "2    6                   Morty   \n",
+       "3    9                   Morty   \n",
+       "4   11                   Morty   \n",
+       "..  ..                     ...   \n",
+       "94  80  Richard Daniel Sanchez   \n",
+       "95  82  Richard Daniel Sanchez   \n",
+       "96  84  Richard Daniel Sanchez   \n",
+       "97  86  Richard Daniel Sanchez   \n",
+       "98  97  Richard Daniel Sanchez   \n",
        "\n",
-       "                    author  \n",
-       "0                    Morty  \n",
-       "1                    Morty  \n",
-       "2                   Summer  \n",
-       "3                     Beth  \n",
-       "4                    Morty  \n",
-       "..                     ...  \n",
-       "56  Richard Daniel Sanchez  \n",
-       "57  Richard Daniel Sanchez  \n",
-       "58  Richard Daniel Sanchez  \n",
-       "59  Richard Daniel Sanchez  \n",
-       "60  Richard Daniel Sanchez  \n",
+       "                                                quote  \n",
+       "0                              Rick, what’s going on?  \n",
+       "1    It’s the middle of the night. What are you ta...  \n",
+       "2                 Ow! Ow! You’re tugging me too hard.  \n",
+       "3       Yeah, Rick, it’s great. Is this the surprise?  \n",
+       "4                                     What?! A bomb?!  \n",
+       "..                                                ...  \n",
+       "94   There you are, Morty. Listen to me. I got an ...  \n",
+       "95   It’s pretty obvious, Morty. I froze him. Now ...  \n",
+       "96   Do you have any concept of how much higher th...  \n",
+       "97   I’ll do it later, Morty. He’ll be fine. Let’s...  \n",
+       "98   There she is. All right. Come on, Morty. Let’...  \n",
        "\n",
-       "[61 rows x 3 columns]"
+       "[99 rows x 3 columns]"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -470,19 +492,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "998f4eb5-31cd-49ae-9f7c-2ec4d6652ef6",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/ayush/Documents/lancedb/env/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from sentence_transformers import SentenceTransformer\n",
     "model = SentenceTransformer(\"all-MiniLM-L6-v2\", device=\"cpu\")\n",
@@ -503,7 +516,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "ccbea593-85cf-484c-989f-9836a31c7906",
    "metadata": {},
    "outputs": [],
@@ -515,7 +528,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "727c8230-7e41-436a-8666-60ee46e7041b",
    "metadata": {},
    "outputs": [
@@ -547,27 +560,27 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>[0.044295236, -0.0831885, -0.03597761, -0.0396...</td>\n",
+       "      <td>[-0.10369808, -0.038807657, -0.07471153, -0.05...</td>\n",
        "      <td>1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>[0.057405394, -0.09669633, 0.00515391, -0.0213...</td>\n",
+       "      <td>[-0.11813704, -0.0533092, 0.025554786, -0.0242...</td>\n",
        "      <td>2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>[0.057896998, -0.033441037, 0.01376669, -0.015...</td>\n",
+       "      <td>[-0.09807682, -0.035231438, -0.04206024, -0.06...</td>\n",
        "      <td>3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>[0.038649295, 0.01286428, -0.03261163, 0.01939...</td>\n",
+       "      <td>[0.032292824, 0.038136397, 0.013615396, 0.0335...</td>\n",
        "      <td>4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>[0.07633445, 0.03451182, -0.0037649637, 0.0203...</td>\n",
+       "      <td>[-0.050369408, -0.0043397923, 0.013419108, -0....</td>\n",
        "      <td>5</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
@@ -576,14 +589,14 @@
       ],
       "text/plain": [
        "                                              vector  id\n",
-       "0  [0.044295236, -0.0831885, -0.03597761, -0.0396...   1\n",
-       "1  [0.057405394, -0.09669633, 0.00515391, -0.0213...   2\n",
-       "2  [0.057896998, -0.033441037, 0.01376669, -0.015...   3\n",
-       "3  [0.038649295, 0.01286428, -0.03261163, 0.01939...   4\n",
-       "4  [0.07633445, 0.03451182, -0.0037649637, 0.0203...   5"
+       "0  [-0.10369808, -0.038807657, -0.07471153, -0.05...   1\n",
+       "1  [-0.11813704, -0.0533092, 0.025554786, -0.0242...   2\n",
+       "2  [-0.09807682, -0.035231438, -0.04206024, -0.06...   3\n",
+       "3  [0.032292824, 0.038136397, 0.013615396, 0.0335...   4\n",
+       "4  [-0.050369408, -0.0043397923, 0.013419108, -0....   5"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -604,7 +617,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "a4326a70-9863-47e8-8f3f-565e35d558cf",
    "metadata": {},
    "outputs": [
@@ -630,68 +643,68 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>id</th>\n",
-       "      <th>quote</th>\n",
        "      <th>author</th>\n",
+       "      <th>quote</th>\n",
        "      <th>vector</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>1</td>\n",
-       "      <td>Nobody exists on purpose. Nobody belongs anywh...</td>\n",
+       "      <td>2</td>\n",
        "      <td>Morty</td>\n",
-       "      <td>[0.044295236, -0.0831885, -0.03597761, -0.0396...</td>\n",
+       "      <td>Rick, what’s going on?</td>\n",
+       "      <td>[-0.11813704, -0.0533092, 0.025554786, -0.0242...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>2</td>\n",
-       "      <td>We're all going to die. Come watch TV.</td>\n",
+       "      <td>4</td>\n",
        "      <td>Morty</td>\n",
-       "      <td>[0.057405394, -0.09669633, 0.00515391, -0.0213...</td>\n",
+       "      <td>It’s the middle of the night. What are you ta...</td>\n",
+       "      <td>[0.032292824, 0.038136397, 0.013615396, 0.0335...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>3</td>\n",
-       "      <td>Losers look stuff up while the rest of us are ...</td>\n",
-       "      <td>Summer</td>\n",
-       "      <td>[0.057896998, -0.033441037, 0.01376669, -0.015...</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Ow! Ow! You’re tugging me too hard.</td>\n",
+       "      <td>[-0.035019904, -0.070963725, 0.003859435, -0.0...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>4</td>\n",
-       "      <td>He's not a hot girl. He can't just bail on his...</td>\n",
-       "      <td>Beth</td>\n",
-       "      <td>[0.038649295, 0.01286428, -0.03261163, 0.01939...</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Yeah, Rick, it’s great. Is this the surprise?</td>\n",
+       "      <td>[-0.12578955, -0.019364933, 0.01606114, -0.082...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>5</td>\n",
-       "      <td>When you are an a—hole, it doesn't matter how ...</td>\n",
+       "      <td>11</td>\n",
        "      <td>Morty</td>\n",
-       "      <td>[0.07633445, 0.03451182, -0.0037649637, 0.0203...</td>\n",
+       "      <td>What?! A bomb?!</td>\n",
+       "      <td>[0.0018287548, 0.07033146, -0.023754105, 0.047...</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "   id                                              quote  author  \\\n",
-       "0   1  Nobody exists on purpose. Nobody belongs anywh...   Morty   \n",
-       "1   2             We're all going to die. Come watch TV.   Morty   \n",
-       "2   3  Losers look stuff up while the rest of us are ...  Summer   \n",
-       "3   4  He's not a hot girl. He can't just bail on his...    Beth   \n",
-       "4   5  When you are an a—hole, it doesn't matter how ...   Morty   \n",
+       "   id author                                              quote  \\\n",
+       "0   2  Morty                             Rick, what’s going on?   \n",
+       "1   4  Morty   It’s the middle of the night. What are you ta...   \n",
+       "2   6  Morty                Ow! Ow! You’re tugging me too hard.   \n",
+       "3   9  Morty      Yeah, Rick, it’s great. Is this the surprise?   \n",
+       "4  11  Morty                                    What?! A bomb?!   \n",
        "\n",
        "                                              vector  \n",
-       "0  [0.044295236, -0.0831885, -0.03597761, -0.0396...  \n",
-       "1  [0.057405394, -0.09669633, 0.00515391, -0.0213...  \n",
-       "2  [0.057896998, -0.033441037, 0.01376669, -0.015...  \n",
-       "3  [0.038649295, 0.01286428, -0.03261163, 0.01939...  \n",
-       "4  [0.07633445, 0.03451182, -0.0037649637, 0.0203...  "
+       "0  [-0.11813704, -0.0533092, 0.025554786, -0.0242...  \n",
+       "1  [0.032292824, 0.038136397, 0.013615396, 0.0335...  \n",
+       "2  [-0.035019904, -0.070963725, 0.003859435, -0.0...  \n",
+       "3  [-0.12578955, -0.019364933, 0.01606114, -0.082...  \n",
+       "4  [0.0018287548, 0.07033146, -0.023754105, 0.047...  "
       ]
      },
-     "execution_count": 9,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -711,7 +724,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "ca9596a0-b4a0-4a5e-8d9e-967cd13b1eae",
    "metadata": {},
    "outputs": [
@@ -719,13 +732,13 @@
      "data": {
       "text/plain": [
        "id: int64\n",
-       "quote: string\n",
        "author: string\n",
+       "quote: string\n",
        "vector: fixed_size_list<item: float>[384]\n",
        "  child 0, item: float"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -757,15 +770,14 @@
    "metadata": {},
    "source": [
     "First, major operations are automatically versioned in LanceDB.\n",
-    "Version 1 is the table creation. This contains no rows but just records the schema and metadata.\n",
-    "Version 2 is the initial insertion of data.\n",
-    "Versions 3 and 4 represents the update (deletion + append)\n",
-    "Version 5 is adding the new column."
+    "Version 1 is the table creation, with the initial insertion of data.\n",
+    "Versions 2 and 3 represents the update (deletion + append)\n",
+    "Version 4 is adding the new column."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "a411902b-43d0-4889-8e34-bc5f3c409726",
    "metadata": {},
    "outputs": [
@@ -773,23 +785,20 @@
      "data": {
       "text/plain": [
        "[{'version': 1,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 33, 39, 40549),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 57, 21, 613932),\n",
        "  'metadata': {}},\n",
        " {'version': 2,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 33, 39, 63675),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 57, 21, 626525),\n",
        "  'metadata': {}},\n",
        " {'version': 3,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 33, 53, 979216),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 57, 27, 91378),\n",
        "  'metadata': {}},\n",
        " {'version': 4,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 33, 53, 988601),\n",
-       "  'metadata': {}},\n",
-       " {'version': 5,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 35, 44, 475220),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 58, 4, 513085),\n",
        "  'metadata': {}}]"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -803,12 +812,12 @@
    "id": "7bd5e954-ac0f-4973-81c6-ad6120412d40",
    "metadata": {},
    "source": [
-    "We can restore version 4, before we added the old vector column"
+    "We can restore version 3, before we added the old vector column"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "ad0682cc-7599-459c-bbd8-1cd1f296c845",
    "metadata": {},
    "outputs": [
@@ -834,61 +843,61 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>id</th>\n",
-       "      <th>quote</th>\n",
        "      <th>author</th>\n",
+       "      <th>quote</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>1</td>\n",
-       "      <td>Nobody exists on purpose. Nobody belongs anywh...</td>\n",
+       "      <td>2</td>\n",
        "      <td>Morty</td>\n",
+       "      <td>Rick, what’s going on?</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>2</td>\n",
-       "      <td>We're all going to die. Come watch TV.</td>\n",
+       "      <td>4</td>\n",
        "      <td>Morty</td>\n",
+       "      <td>It’s the middle of the night. What are you ta...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>3</td>\n",
-       "      <td>Losers look stuff up while the rest of us are ...</td>\n",
-       "      <td>Summer</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Ow! Ow! You’re tugging me too hard.</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>4</td>\n",
-       "      <td>He's not a hot girl. He can't just bail on his...</td>\n",
-       "      <td>Beth</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Yeah, Rick, it’s great. Is this the surprise?</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>5</td>\n",
-       "      <td>When you are an a—hole, it doesn't matter how ...</td>\n",
+       "      <td>11</td>\n",
        "      <td>Morty</td>\n",
+       "      <td>What?! A bomb?!</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "   id                                              quote  author\n",
-       "0   1  Nobody exists on purpose. Nobody belongs anywh...   Morty\n",
-       "1   2             We're all going to die. Come watch TV.   Morty\n",
-       "2   3  Losers look stuff up while the rest of us are ...  Summer\n",
-       "3   4  He's not a hot girl. He can't just bail on his...    Beth\n",
-       "4   5  When you are an a—hole, it doesn't matter how ...   Morty"
+       "   id author                                              quote\n",
+       "0   2  Morty                             Rick, what’s going on?\n",
+       "1   4  Morty   It’s the middle of the night. What are you ta...\n",
+       "2   6  Morty                Ow! Ow! You’re tugging me too hard.\n",
+       "3   9  Morty      Yeah, Rick, it’s great. Is this the surprise?\n",
+       "4  11  Morty                                    What?! A bomb?!"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "table.restore(4)\n",
+    "table.restore(3)\n",
     "table.head().to_pandas()"
    ]
   },
@@ -902,7 +911,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "d5bfb448-20b9-45e9-90ba-8a73abb86668",
    "metadata": {},
    "outputs": [
@@ -910,26 +919,23 @@
      "data": {
       "text/plain": [
        "[{'version': 1,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 33, 39, 40549),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 57, 21, 613932),\n",
        "  'metadata': {}},\n",
        " {'version': 2,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 33, 39, 63675),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 57, 21, 626525),\n",
        "  'metadata': {}},\n",
        " {'version': 3,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 33, 53, 979216),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 57, 27, 91378),\n",
        "  'metadata': {}},\n",
        " {'version': 4,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 33, 53, 988601),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 58, 4, 513085),\n",
        "  'metadata': {}},\n",
        " {'version': 5,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 35, 44, 475220),\n",
-       "  'metadata': {}},\n",
-       " {'version': 6,\n",
-       "  'timestamp': datetime.datetime(2023, 10, 20, 14, 36, 15, 658370),\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 11, 58, 27, 153807),\n",
        "  'metadata': {}}]"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -945,36 +951,15 @@
    "source": [
     "### Switching Models\n",
     "\n",
-    "Now we'll switch to the `all-mpnet-base-v2` model and add the vectors to the restored dataset again:"
+    "Now we'll switch to the `all-mpnet-base-v2` model and add the vectors to the restored dataset again. Note that this step can take a couple of minutes."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "id": "1fa2950d-3002-4903-b6c3-2760ce60d079",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Downloading (…)a8e1d/.gitattributes: 100%|██████████| 1.18k/1.18k [00:00<00:00, 6.02MB/s]\n",
-      "Downloading (…)_Pooling/config.json: 100%|██████████| 190/190 [00:00<00:00, 411kB/s]\n",
-      "Downloading (…)b20bca8e1d/README.md: 100%|██████████| 10.6k/10.6k [00:00<00:00, 14.2MB/s]\n",
-      "Downloading (…)0bca8e1d/config.json: 100%|██████████| 571/571 [00:00<00:00, 1.83MB/s]\n",
-      "Downloading (…)ce_transformers.json: 100%|██████████| 116/116 [00:00<00:00, 991kB/s]\n",
-      "Downloading (…)e1d/data_config.json: 100%|██████████| 39.3k/39.3k [00:00<00:00, 188kB/s]\n",
-      "Downloading pytorch_model.bin: 100%|██████████| 438M/438M [00:34<00:00, 12.6MB/s] \n",
-      "Downloading (…)nce_bert_config.json: 100%|██████████| 53.0/53.0 [00:00<00:00, 150kB/s]\n",
-      "Downloading (…)cial_tokens_map.json: 100%|██████████| 239/239 [00:00<00:00, 624kB/s]\n",
-      "Downloading (…)a8e1d/tokenizer.json: 100%|██████████| 466k/466k [00:00<00:00, 719kB/s]\n",
-      "Downloading (…)okenizer_config.json: 100%|██████████| 363/363 [00:00<00:00, 1.06MB/s]\n",
-      "Downloading (…)8e1d/train_script.py: 100%|██████████| 13.1k/13.1k [00:00<00:00, 21.8MB/s]\n",
-      "Downloading (…)b20bca8e1d/vocab.txt: 100%|██████████| 232k/232k [00:00<00:00, 606kB/s]\n",
-      "Downloading (…)bca8e1d/modules.json: 100%|██████████| 349/349 [00:00<00:00, 946kB/s]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "model = SentenceTransformer(\"all-mpnet-base-v2\", device=\"cpu\")\n",
     "vectors = model.encode(df.quote.values.tolist(),\n",
@@ -987,7 +972,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "id": "694c46e0-a1c3-4869-a1eb-562f14606ad4",
    "metadata": {},
    "outputs": [
@@ -995,13 +980,13 @@
      "data": {
       "text/plain": [
        "id: int64\n",
-       "quote: string\n",
        "author: string\n",
+       "quote: string\n",
        "vector: fixed_size_list<item: float>[768]\n",
        "  child 0, item: float"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1023,7 +1008,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "id": "9d11ddf1-b352-496c-91d7-99c70cbf304b",
    "metadata": {},
    "outputs": [],
@@ -1041,17 +1026,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 18,
    "id": "20bcce48-a5df-43c7-9ab9-7d59a83055e9",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "30"
+       "28"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1070,27 +1055,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 20,
    "id": "6e279635-75b0-400c-8b43-4aa069282ccd",
    "metadata": {},
    "outputs": [],
    "source": [
-    "table.restore(7)"
+    "table.restore(6)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 21,
    "id": "6a65b627-57a2-43b2-8acc-3805591845ad",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "61"
+       "99"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1111,17 +1096,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 22,
    "id": "f595c9b8-91ec-48c1-9790-c40e1bd24b60",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "9"
+       "8"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1137,15 +1122,14 @@
    "source": [
     "\n",
     "Versions:\n",
-    "- 1 - Create\n",
-    "- 2 - Append\n",
-    "- 3 - Update (deletion)\n",
-    "- 4 - Update (append)\n",
-    "- 5 - Merge (vector column)\n",
-    "- 6 - Restore (4)\n",
-    "- 7 - Merge (new vector column)\n",
-    "- 8 - Deletion\n",
-    "- 9 - Restore"
+    "- 1 - Create and append\n",
+    "- 2 - Update (deletion)\n",
+    "- 3 - Update (append)\n",
+    "- 4 - Merge (vector column)\n",
+    "- 5 - Restore (4)\n",
+    "- 6 - Merge (new vector column)\n",
+    "- 7 - Deletion\n",
+    "- 8 - Restore"
    ]
   },
   {
@@ -1167,7 +1151,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "doc-venv",
    "language": "python",
    "name": "python3"
   },
@@ -1181,7 +1165,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.11.10"
   }
  },
  "nbformat": 4,
diff --git a/docs/src/notebooks/reproducibility_async.ipynb b/docs/src/notebooks/reproducibility_async.ipynb
new file mode 100644
index 00000000..fef18d6a
--- /dev/null
+++ b/docs/src/notebooks/reproducibility_async.ipynb
@@ -0,0 +1,1096 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c0de1e6a-61f7-4f99-a2fd-1461902ab36a",
+   "metadata": {},
+   "source": [
+    "# Async API\n",
+    "\n",
+    "We demonstrate the following functionalities suppored by LanceDB using our asynchonous APIs:\n",
+    "- Automatic versioning\n",
+    "- Instant rollback\n",
+    "- Appends, updates, deletions\n",
+    "- Schema evolution"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d810f29",
+   "metadata": {},
+   "source": [
+    "Let's first prepare the data. We will be using a CSV file with a bunch of quotes from Rick and Morty"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "d00ed8e6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2024-12-17 15:58:31--  http://vectordb-recipes.s3.us-west-2.amazonaws.com/rick_and_morty_quotes.csv\n",
+      "Resolving vectordb-recipes.s3.us-west-2.amazonaws.com (vectordb-recipes.s3.us-west-2.amazonaws.com)... 3.5.84.162, 3.5.76.76, 52.92.228.138, ...\n",
+      "Connecting to vectordb-recipes.s3.us-west-2.amazonaws.com (vectordb-recipes.s3.us-west-2.amazonaws.com)|3.5.84.162|:80... connected.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 8236 (8.0K) [text/csv]\n",
+      "Saving to: ‘rick_and_morty_quotes.csv.3’\n",
+      "\n",
+      "rick_and_morty_quot 100%[===================>]   8.04K  --.-KB/s    in 0s      \n",
+      "\n",
+      "2024-12-17 15:58:31 (160 MB/s) - ‘rick_and_morty_quotes.csv.3’ saved [8236/8236]\n",
+      "\n",
+      "id,author,quote\n",
+      "1,Rick,\" Morty, you got to come on. You got to come with me.\"\n",
+      "2,Morty,\" Rick, what’s going on?\"\n",
+      "3,Rick,\" I got a surprise for you, Morty.\"\n",
+      "4,Morty,\" It’s the middle of the night. What are you talking about?\"\n",
+      "5,Rick,\" I got a surprise for you.\"\n",
+      "6,Morty,\" Ow! Ow! You’re tugging me too hard.\"\n",
+      "7,Rick,\" I got a surprise for you, Morty.\"\n",
+      "8,Rick,\" What do you think of this flying vehicle, Morty? I built it out of stuff I found in the garage.\"\n",
+      "9,Morty,\" Yeah, Rick, it’s great. Is this the surprise?\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "!wget http://vectordb-recipes.s3.us-west-2.amazonaws.com/rick_and_morty_quotes.csv\n",
+    "!head rick_and_morty_quotes.csv"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a5fcdcda-b0fe-4ac4-90b4-6b42cf2ef34d",
+   "metadata": {},
+   "source": [
+    "Let's load this into a pandas dataframe.\n",
+    "\n",
+    "It's got 3 columns, a quote id, the quote string, and the first name of the author of the quote:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "def3ae59-77d9-43f0-ba6d-415a1503856b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>author</th>\n",
+       "      <th>quote</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, you got to come on. You got to come wi...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Rick, what’s going on?</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>It’s the middle of the night. What are you ta...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you.</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id author                                              quote\n",
+       "0   1   Rick   Morty, you got to come on. You got to come wi...\n",
+       "1   2  Morty                             Rick, what’s going on?\n",
+       "2   3   Rick                   I got a surprise for you, Morty.\n",
+       "3   4  Morty   It’s the middle of the night. What are you ta...\n",
+       "4   5   Rick                          I got a surprise for you."
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "df = pd.read_csv(\"rick_and_morty_quotes.csv\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ba9ffac-c779-49e3-91a7-f1c00f3fda41",
+   "metadata": {},
+   "source": [
+    "Creating a LanceDB table from a pandas dataframe is straightforward using `create_table`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "392cf0ee",
+   "metadata": {},
+   "source": [
+    "We'll start with a local LanceDB connection"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "91a322dd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install lancedb -q"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "10715e72",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lancedb\n",
+    "async_db = await lancedb.connect_async(\"~/.lancedb\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "bd981f6d-b921-4b1d-b63a-6c1d59f3a51d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2024-12-17T23:58:46Z WARN  lance::dataset::write::insert] No existing dataset at ~/.lancedb/rick_and_morty.lance, it will be created\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>author</th>\n",
+       "      <th>quote</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, you got to come on. You got to come wi...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Rick, what’s going on?</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>It’s the middle of the night. What are you ta...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>6</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Ow! Ow! You’re tugging me too hard.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>7</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>8</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>What do you think of this flying vehicle, Mor...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>9</td>\n",
+       "      <td>Morty</td>\n",
+       "      <td>Yeah, Rick, it’s great. Is this the surprise?</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>10</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, I had to I had to I had to I had to ma...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id author                                              quote\n",
+       "0   1   Rick   Morty, you got to come on. You got to come wi...\n",
+       "1   2  Morty                             Rick, what’s going on?\n",
+       "2   3   Rick                   I got a surprise for you, Morty.\n",
+       "3   4  Morty   It’s the middle of the night. What are you ta...\n",
+       "4   5   Rick                          I got a surprise for you.\n",
+       "5   6  Morty                Ow! Ow! You’re tugging me too hard.\n",
+       "6   7   Rick                   I got a surprise for you, Morty.\n",
+       "7   8   Rick   What do you think of this flying vehicle, Mor...\n",
+       "8   9  Morty      Yeah, Rick, it’s great. Is this the surprise?\n",
+       "9  10   Rick   Morty, I had to I had to I had to I had to ma..."
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_db.drop_table(\"rick_and_morty\")\n",
+    "async_table = await async_db.create_table(\"rick_and_morty\", df, mode=\"overwrite\")\n",
+    "await async_table.to_pandas()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "38d055be-ae3e-4190-b1cf-abf14cdf8975",
+   "metadata": {},
+   "source": [
+    "## Updates"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "842550fb-da81-44ea-9e98-d5dbaa6916c7",
+   "metadata": {},
+   "source": [
+    "Now, since Rick is the smartest man in the multiverse, he deserves to have his quotes attributed to his full name: Richard Daniel Sanchez.\n",
+    "\n",
+    "This can be done via `LanceTable.update`. It needs two arguments:\n",
+    "\n",
+    "1. A `where` string filter (sql syntax) to determine the rows to update\n",
+    "2. A dict of `updates` where the keys are the column names to update and the values are the new values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "9eac4708-a8c4-49aa-bc13-8e60c5bf34a0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>author</th>\n",
+       "      <th>quote</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, you got to come on. You got to come wi...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>7</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>8</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>What do you think of this flying vehicle, Mor...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>10</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, I had to I had to I had to I had to ma...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>12</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>We’re gonna drop it down there just get a who...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>14</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Come on, Morty. Just take it easy, Morty. It’...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>16</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>When I drop the bomb you know, I want you to ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>18</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>And Jessica’s gonna be Eve,…</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id author                                              quote\n",
+       "0   1   Rick   Morty, you got to come on. You got to come wi...\n",
+       "1   3   Rick                   I got a surprise for you, Morty.\n",
+       "2   5   Rick                          I got a surprise for you.\n",
+       "3   7   Rick                   I got a surprise for you, Morty.\n",
+       "4   8   Rick   What do you think of this flying vehicle, Mor...\n",
+       "5  10   Rick   Morty, I had to I had to I had to I had to ma...\n",
+       "6  12   Rick   We’re gonna drop it down there just get a who...\n",
+       "7  14   Rick   Come on, Morty. Just take it easy, Morty. It’...\n",
+       "8  16   Rick   When I drop the bomb you know, I want you to ...\n",
+       "9  18   Rick                       And Jessica’s gonna be Eve,…"
+      ]
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.update(where=\"author='Morty'\", updates={\"author\": \"Richard Daniel Sanchez\"})\n",
+    "await async_table.to_pandas()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ac6499ce-af6d-4934-9051-be5f159ce623",
+   "metadata": {},
+   "source": [
+    "## Schema evolution"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "022f1334",
+   "metadata": {},
+   "source": [
+    "Let's add a `new_id` column to the table, where each value is the original `id` plus 1."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "a4326a70-9863-47e8-8f3f-565e35d558cf",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>author</th>\n",
+       "      <th>quote</th>\n",
+       "      <th>new_id</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, you got to come on. You got to come wi...</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you.</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>7</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "      <td>8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>8</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>What do you think of this flying vehicle, Mor...</td>\n",
+       "      <td>9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>10</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, I had to I had to I had to I had to ma...</td>\n",
+       "      <td>11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>12</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>We’re gonna drop it down there just get a who...</td>\n",
+       "      <td>13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>14</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Come on, Morty. Just take it easy, Morty. It’...</td>\n",
+       "      <td>15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>16</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>When I drop the bomb you know, I want you to ...</td>\n",
+       "      <td>17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>18</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>And Jessica’s gonna be Eve,…</td>\n",
+       "      <td>19</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id author                                              quote  new_id\n",
+       "0   1   Rick   Morty, you got to come on. You got to come wi...       2\n",
+       "1   3   Rick                   I got a surprise for you, Morty.       4\n",
+       "2   5   Rick                          I got a surprise for you.       6\n",
+       "3   7   Rick                   I got a surprise for you, Morty.       8\n",
+       "4   8   Rick   What do you think of this flying vehicle, Mor...       9\n",
+       "5  10   Rick   Morty, I had to I had to I had to I had to ma...      11\n",
+       "6  12   Rick   We’re gonna drop it down there just get a who...      13\n",
+       "7  14   Rick   Come on, Morty. Just take it easy, Morty. It’...      15\n",
+       "8  16   Rick   When I drop the bomb you know, I want you to ...      17\n",
+       "9  18   Rick                       And Jessica’s gonna be Eve,…      19"
+      ]
+     },
+     "execution_count": 55,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.add_columns({\"new_id\": \"id + 1\"})\n",
+    "await async_table.to_pandas()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f590fec8-0ed0-4148-b940-c81abe7b421c",
+   "metadata": {},
+   "source": [
+    "If we look at the schema, we see that a new int64 column was added"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "ca9596a0-b4a0-4a5e-8d9e-967cd13b1eae",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "id: int64\n",
+       "author: string\n",
+       "quote: string\n",
+       "new_id: int64"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.schema()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f046002c-872c-4c39-ab85-e03c3b45b477",
+   "metadata": {},
+   "source": [
+    "## Rollback\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dbfc298c-ada2-411b-925f-e53dc9d35f3c",
+   "metadata": {},
+   "source": [
+    "Suppose we used the table and found that the new column should be a different value. How do we use another new column without losing the change history?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dfb116e4-b3b2-4b7e-bbf8-d3e63ca2aa14",
+   "metadata": {},
+   "source": [
+    "First, major operations are automatically versioned in LanceDB.\n",
+    "Version 1 is the table creation, with the initial insertion of data.\n",
+    "Versions 2 and 3 represents the update (deletion + append)\n",
+    "Version 4 is adding the new column."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "a411902b-43d0-4889-8e34-bc5f3c409726",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'version': 1,\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 15, 58, 46, 983259),\n",
+       "  'metadata': {}},\n",
+       " {'version': 2,\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 15, 59, 0, 291948),\n",
+       "  'metadata': {}},\n",
+       " {'version': 3,\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 15, 59, 8, 381165),\n",
+       "  'metadata': {}}]"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.checkout_latest()\n",
+    "await async_table.list_versions()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7bd5e954-ac0f-4973-81c6-ad6120412d40",
+   "metadata": {},
+   "source": [
+    "We can restore version 3, before we added the `new_id` vector column"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "ad0682cc-7599-459c-bbd8-1cd1f296c845",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>author</th>\n",
+       "      <th>quote</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, you got to come on. You got to come wi...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>7</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>I got a surprise for you, Morty.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>8</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>What do you think of this flying vehicle, Mor...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>10</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Morty, I had to I had to I had to I had to ma...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>12</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>We’re gonna drop it down there just get a who...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>14</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>Come on, Morty. Just take it easy, Morty. It’...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>16</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>When I drop the bomb you know, I want you to ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>18</td>\n",
+       "      <td>Rick</td>\n",
+       "      <td>And Jessica’s gonna be Eve,…</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id author                                              quote\n",
+       "0   1   Rick   Morty, you got to come on. You got to come wi...\n",
+       "1   3   Rick                   I got a surprise for you, Morty.\n",
+       "2   5   Rick                          I got a surprise for you.\n",
+       "3   7   Rick                   I got a surprise for you, Morty.\n",
+       "4   8   Rick   What do you think of this flying vehicle, Mor...\n",
+       "5  10   Rick   Morty, I had to I had to I had to I had to ma...\n",
+       "6  12   Rick   We’re gonna drop it down there just get a who...\n",
+       "7  14   Rick   Come on, Morty. Just take it easy, Morty. It’...\n",
+       "8  16   Rick   When I drop the bomb you know, I want you to ...\n",
+       "9  18   Rick                       And Jessica’s gonna be Eve,…"
+      ]
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.checkout(2)\n",
+    "await async_table.restore()\n",
+    "await async_table.to_pandas()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b0a51146-40d0-4f16-9555-5ce68c2c9eee",
+   "metadata": {},
+   "source": [
+    "Notice that we now have one more, not less versions. When we restore an old version, we're not deleting the version history, we're just creating a new version where the schema and data is equivalent to the restored old version. In this way, we can keep track of all of the changes and always rollback to a previous state."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "d5bfb448-20b9-45e9-90ba-8a73abb86668",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'version': 1,\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 15, 58, 46, 983259),\n",
+       "  'metadata': {}},\n",
+       " {'version': 2,\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 15, 59, 0, 291948),\n",
+       "  'metadata': {}},\n",
+       " {'version': 3,\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 15, 59, 8, 381165),\n",
+       "  'metadata': {}},\n",
+       " {'version': 4,\n",
+       "  'timestamp': datetime.datetime(2024, 12, 17, 15, 59, 22, 800694),\n",
+       "  'metadata': {}}]"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.list_versions()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6713cb53-8cb9-4235-9c55-337c311f0af6",
+   "metadata": {},
+   "source": [
+    "### Add another new column\n",
+    "\n",
+    "Now we'll change the value of the `new_id` column and add it to the restored dataset again"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "id": "cdabeb56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "await async_table.add_columns({\"new_id\": \"id + 10\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "694c46e0-a1c3-4869-a1eb-562f14606ad4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "id: int64\n",
+       "author: string\n",
+       "quote: string\n",
+       "new_id: int64"
+      ]
+     },
+     "execution_count": 61,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.schema()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5e4085a5-a2e7-4520-acfc-eabaae2caa7d",
+   "metadata": {},
+   "source": [
+    "## Deletion\n",
+    "\n",
+    "What if the whole show was just Rick-isms? \n",
+    "Let's delete any quote not said by Rick"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "9d11ddf1-b352-496c-91d7-99c70cbf304b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "await async_table.delete(\"author != 'Richard Daniel Sanchez'\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "77d2f591-e492-423e-b995-2a18ae8cb831",
+   "metadata": {},
+   "source": [
+    "We can see that the number of rows has been reduced to 30"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "20bcce48-a5df-43c7-9ab9-7d59a83055e9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "34"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.count_rows()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef8457b2-1228-4a25-824e-477a07681b48",
+   "metadata": {},
+   "source": [
+    "Ok we had our fun, let's get back to the full quote set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "6e279635-75b0-400c-8b43-4aa069282ccd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "await async_table.checkout(5)\n",
+    "await async_table.restore()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "6a65b627-57a2-43b2-8acc-3805591845ad",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "99"
+      ]
+     },
+     "execution_count": 68,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.count_rows()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae1a6ee8-8868-49de-82ab-17a0f61f3a47",
+   "metadata": {},
+   "source": [
+    "## History\n",
+    "\n",
+    "We now have 9 versions in the data. We can review the operations that corresponds to each version below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "f595c9b8-91ec-48c1-9790-c40e1bd24b60",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "6"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await async_table.version()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "774f4eb0-03d4-4fda-a825-6217bf096619",
+   "metadata": {},
+   "source": [
+    "\n",
+    "Versions:\n",
+    "- 1 - Create\n",
+    "- 2 - Update\n",
+    "- 3 - Add a new column\n",
+    "- 4 - Restore (2)\n",
+    "- 5 - Add a new column\n",
+    "- 6 - Delete\n",
+    "- 7 - Restore"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fb0131e6-2b73-442a-b4c6-6976a9cf4c7e",
+   "metadata": {},
+   "source": [
+    "## Summary"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97a1cf79-b46b-40cd-ada0-54edef358627",
+   "metadata": {},
+   "source": [
+    "We never had to explicitly manage the versioning. And we never had to create expensive and slow snapshots. LanceDB automatically tracks the full history of operations I created and supports fast rollbacks. In production this is critical for debugging issues and minimizing downtime by rolling back to a previously successful state in seconds."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "doc-venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/docs/src/python/pandas_and_pyarrow.md b/docs/src/python/pandas_and_pyarrow.md
index ac86b68e..c597becf 100644
--- a/docs/src/python/pandas_and_pyarrow.md
+++ b/docs/src/python/pandas_and_pyarrow.md
@@ -8,54 +8,55 @@ and PyArrow. The sequence of steps in a typical workflow is shown below.
 
 First, we need to connect to a LanceDB database.
 
-```py
+=== "Sync API"
 
-import lancedb
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:import-lancedb"
+    --8<-- "python/python/tests/docs/test_python.py:connect_to_lancedb"
+    ```
+=== "Async API"
 
-db = lancedb.connect("data/sample-lancedb")
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:import-lancedb"
+    --8<-- "python/python/tests/docs/test_python.py:connect_to_lancedb_async"
+    ```
 
 We can load a Pandas `DataFrame` to LanceDB directly.
 
-```py
-import pandas as pd
+=== "Sync API"
 
-data = pd.DataFrame({
-    "vector": [[3.1, 4.1], [5.9, 26.5]],
-    "item": ["foo", "bar"],
-    "price": [10.0, 20.0]
-})
-table = db.create_table("pd_table", data=data)
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:import-pandas"
+    --8<-- "python/python/tests/docs/test_python.py:create_table_pandas"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:import-pandas"
+    --8<-- "python/python/tests/docs/test_python.py:create_table_pandas_async"
+    ```
 
 Similar to the [`pyarrow.write_dataset()`](https://arrow.apache.org/docs/python/generated/pyarrow.dataset.write_dataset.html) method, LanceDB's
 [`db.create_table()`](python.md/#lancedb.db.DBConnection.create_table) accepts data in a variety of forms.
 
 If you have a dataset that is larger than memory, you can create a table with `Iterator[pyarrow.RecordBatch]` to lazily load the data:
 
-```py
+=== "Sync API"
 
-from typing import Iterable
-import pyarrow as pa
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:import-iterable"
+    --8<-- "python/python/tests/docs/test_python.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_python.py:make_batches"
+    --8<-- "python/python/tests/docs/test_python.py:create_table_iterable"
+    ```
+=== "Async API"
 
-def make_batches() -> Iterable[pa.RecordBatch]:
-    for i in range(5):
-        yield pa.RecordBatch.from_arrays(
-            [
-                pa.array([[3.1, 4.1], [5.9, 26.5]]),
-                pa.array(["foo", "bar"]),
-                pa.array([10.0, 20.0]),
-            ],
-            ["vector", "item", "price"])
-
-schema=pa.schema([
-    pa.field("vector", pa.list_(pa.float32())),
-    pa.field("item", pa.utf8()),
-    pa.field("price", pa.float32()),
-])
-
-table = db.create_table("iterable_table", data=make_batches(), schema=schema)
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:import-iterable"
+    --8<-- "python/python/tests/docs/test_python.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_python.py:make_batches"
+    --8<-- "python/python/tests/docs/test_python.py:create_table_iterable_async"
+    ```
 
 You will find detailed instructions of creating a LanceDB dataset in
 [Getting Started](../basic.md#quick-start) and [API](python.md/#lancedb.db.DBConnection.create_table)
@@ -65,15 +66,16 @@ sections.
 
 We can now perform similarity search via the LanceDB Python API.
 
-```py
-# Open the table previously created.
-table = db.open_table("pd_table")
+=== "Sync API"
 
-query_vector = [100, 100]
-# Pandas DataFrame
-df = table.search(query_vector).limit(1).to_pandas()
-print(df)
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:vector_search"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:vector_search_async"
+    ```
 
 ```
     vector     item  price    _distance
@@ -83,16 +85,13 @@ print(df)
 If you have a simple filter, it's faster to provide a `where` clause to LanceDB's `search` method.
 For more complex filters or aggregations, you can always resort to using the underlying `DataFrame` methods after performing a search.
 
-```python
+=== "Sync API"
 
-# Apply the filter via LanceDB
-results = table.search([100, 100]).where("price < 15").to_pandas()
-assert len(results) == 1
-assert results["item"].iloc[0] == "foo"
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:vector_search_with_filter"
+    ```
+=== "Async API"
 
-# Apply the filter via Pandas
-df = results = table.search([100, 100]).to_pandas()
-results = df[df.price < 15]
-assert len(results) == 1
-assert results["item"].iloc[0] == "foo"
-```
+    ```python
+    --8<-- "python/python/tests/docs/test_python.py:vector_search_with_filter_async"
+    ```
diff --git a/docs/src/python/polars_arrow.md b/docs/src/python/polars_arrow.md
index 7bf5ad43..9d6d8c33 100644
--- a/docs/src/python/polars_arrow.md
+++ b/docs/src/python/polars_arrow.md
@@ -2,38 +2,29 @@
 
 LanceDB supports [Polars](https://github.com/pola-rs/polars), a blazingly fast DataFrame library for Python written in Rust. Just like in Pandas, the Polars integration is enabled by PyArrow under the hood. A deeper integration between Lance Tables and Polars DataFrames is in progress, but at the moment, you can read a Polars DataFrame into LanceDB and output the search results from a query to a Polars DataFrame.
 
+
 ## Create & Query LanceDB Table
 
 ### From Polars DataFrame
 
 First, we connect to a LanceDB database.
 
-```py
-import lancedb
 
-db = lancedb.connect("data/polars-lancedb")
+```py
+--8<-- "python/python/tests/docs/test_python.py:import-lancedb"
+--8<-- "python/python/tests/docs/test_python.py:connect_to_lancedb"
 ```
 
 We can load a Polars `DataFrame` to LanceDB directly.
 
 ```py
-import polars as pl
-
-data = pl.DataFrame({
-    "vector": [[3.1, 4.1], [5.9, 26.5]],
-    "item": ["foo", "bar"],
-    "price": [10.0, 20.0]
-})
-table = db.create_table("pl_table", data=data)
+--8<-- "python/python/tests/docs/test_python.py:import-polars"
+--8<-- "python/python/tests/docs/test_python.py:create_table_polars"
 ```
-
 We can now perform similarity search via the LanceDB Python API.
 
 ```py
-query = [3.0, 4.0]
-result = table.search(query).limit(1).to_polars()
-print(result)
-print(type(result))
+--8<-- "python/python/tests/docs/test_python.py:vector_search_polars"
 ```
 
 In addition to the selected columns, LanceDB also returns a vector
@@ -59,33 +50,16 @@ Note that the type of the result from a table search is a Polars DataFrame.
 Alternately, we can create an empty LanceDB Table using a Pydantic schema and populate it with a Polars DataFrame.
 
 ```py
-import polars as pl
-from lancedb.pydantic import Vector, LanceModel
-
-
-class Item(LanceModel):
-    vector: Vector(2)
-    item: str
-    price: float
-
-data = {
-    "vector": [[3.1, 4.1]],
-    "item": "foo",
-    "price": 10.0,
-}
-
-table = db.create_table("test_table", schema=Item)
-df = pl.DataFrame(data)
-# Add Polars DataFrame to table
-table.add(df)
+--8<-- "python/python/tests/docs/test_python.py:import-polars"
+--8<-- "python/python/tests/docs/test_python.py:import-lancedb-pydantic"
+--8<-- "python/python/tests/docs/test_python.py:class_Item"
+--8<-- "python/python/tests/docs/test_python.py:create_table_pydantic"
 ```
 
 The table can now be queried as usual.
 
 ```py
-result = table.search([3.0, 4.0]).limit(1).to_polars()
-print(result)
-print(type(result))
+--8<-- "python/python/tests/docs/test_python.py:vector_search_polars"
 ```
 
 ```
@@ -108,8 +82,7 @@ As you iterate on your application, you'll likely need to work with the whole ta
 LanceDB tables can also be converted directly into a polars LazyFrame for further processing.
 
 ```python
-ldf = table.to_polars()
-print(type(ldf))
+--8<-- "python/python/tests/docs/test_python.py:dump_table_lazyform"
 ```
 
 Unlike the search result from a query, we can see that the type of the result is a LazyFrame.
@@ -121,7 +94,7 @@ Unlike the search result from a query, we can see that the type of the result is
 We can now work with the LazyFrame as we would in Polars, and collect the first result.
 
 ```python
-print(ldf.first().collect())
+--8<-- "python/python/tests/docs/test_python.py:print_table_lazyform"
 ```
 
 ```
diff --git a/docs/src/reranking/index.md b/docs/src/reranking/index.md
index 1098737f..e4320366 100644
--- a/docs/src/reranking/index.md
+++ b/docs/src/reranking/index.md
@@ -36,14 +36,14 @@ tbl = db.create_table("test", data)
 reranker = CohereReranker(api_key="your_api_key")
 
 # Run vector search with a reranker
-result = tbl.query("hello").rerank(reranker).to_list() 
+result = tbl.search("hello").rerank(reranker).to_list() 
 
 # Run FTS search with a reranker
-result = tbl.query("hello", query_type="fts").rerank(reranker).to_list()
+result = tbl.search("hello", query_type="fts").rerank(reranker).to_list()
 
 # Run hybrid search with a reranker
 tbl.create_fts_index("text")
-result = tbl.query("hello", query_type="hybrid").rerank(reranker).to_list()
+result = tbl.search("hello", query_type="hybrid").rerank(reranker).to_list()
 ```
 
 ### Multi-vector reranking
diff --git a/docs/src/search.md b/docs/src/search.md
index 3420abab..39d9db19 100644
--- a/docs/src/search.md
+++ b/docs/src/search.md
@@ -44,18 +44,16 @@ db.create_table("my_vectors", data=data)
 
 === "Python"
 
-    ```python
-    import lancedb
-    import numpy as np
+    === "Sync API"
 
-    db = lancedb.connect("data/sample-lancedb")
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:exhaustive_search"
+        ```
+    === "Async API"
 
-    tbl = db.open_table("my_vectors")
-
-    df = tbl.search(np.random.random((1536))) \
-        .limit(10) \
-        .to_list()
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:exhaustive_search_async"
+        ```
 
 === "TypeScript"
 
@@ -81,12 +79,16 @@ By default, `l2` will be used as metric type. You can specify the metric type as
 
 === "Python"
 
-    ```python
-    df = tbl.search(np.random.random((1536))) \
-        .metric("cosine") \
-        .limit(10) \
-        .to_list()
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:exhaustive_search_cosine"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:exhaustive_search_async_cosine"
+        ```
 
 === "TypeScript"
 
@@ -142,40 +144,28 @@ LanceDB returns vector search results via different formats commonly used in pyt
 Let's create a LanceDB table with a nested schema:
 
 === "Python"
+    === "Sync API"
 
-    ```python
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:import-datetime"
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb-pydantic"
+        --8<-- "python/python/tests/docs/test_search.py:import-numpy"
+        --8<-- "python/python/tests/docs/test_search.py:import-pydantic-base-model"
+        --8<-- "python/python/tests/docs/test_search.py:class-definition"
+        --8<-- "python/python/tests/docs/test_search.py:create_table_with_nested_schema"
+        ```
+    === "Async API"
 
-    from datetime import datetime
-    import lancedb
-    from lancedb.pydantic import LanceModel, Vector
-    import numpy as np
-    from pydantic import BaseModel
-    uri = "data/sample-lancedb-nested"
-
-    class Metadata(BaseModel):
-        source: str
-        timestamp: datetime
-
-    class Document(BaseModel):
-        content: str
-        meta: Metadata
-
-    class LanceSchema(LanceModel):
-        id: str
-        vector: Vector(1536)
-        payload: Document
-
-    # Let's add 100 sample rows to our dataset
-    data = [LanceSchema(
-        id=f"id{i}",
-        vector=np.random.randn(1536),
-        payload=Document(
-            content=f"document{i}", meta=Metadata(source=f"source{i % 10}", timestamp=datetime.now())
-        ),
-    ) for i in range(100)]
-
-    tbl = db.create_table("documents", data=data)
-    ```
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:import-datetime"
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb-pydantic"
+        --8<-- "python/python/tests/docs/test_search.py:import-numpy"
+        --8<-- "python/python/tests/docs/test_search.py:import-pydantic-base-model"
+        --8<-- "python/python/tests/docs/test_search.py:class-definition"
+        --8<-- "python/python/tests/docs/test_search.py:create_table_async_with_nested_schema"
+        ```
 
     ### As a PyArrow table
 
@@ -184,17 +174,31 @@ Let's create a LanceDB table with a nested schema:
     the addition of an `_distance` column for vector search or a `score`
     column for full text search.
 
-    ```python
-    tbl.search(np.random.randn(1536)).to_arrow()
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_as_pyarrow"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_async_as_pyarrow"
+        ```
 
     ### As a Pandas DataFrame
 
     You can also get the results as a pandas dataframe.
 
-    ```python
-    tbl.search(np.random.randn(1536)).to_pandas()
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_as_pandas"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_async_as_pandas"
+        ```
 
     While other formats like Arrow/Pydantic/Python dicts have a natural
     way to handle nested schemas, pandas can only store nested data as a
@@ -202,33 +206,50 @@ Let's create a LanceDB table with a nested schema:
     So for convenience, you can also tell LanceDB to flatten a nested schema
     when creating the pandas dataframe.
 
-    ```python
-    tbl.search(np.random.randn(1536)).to_pandas(flatten=True)
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_as_pandas_flatten_true"
+        ```
 
     If your table has a deeply nested struct, you can control how many levels
     of nesting to flatten by passing in a positive integer.
 
-    ```python
-    tbl.search(np.random.randn(1536)).to_pandas(flatten=1)
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_as_pandas_flatten_1"
+        ```
+    !!! note
+        `flatten` is not yet supported with our asynchronous client.
 
     ### As a list of Python dicts
 
     You can of course return results as a list of python dicts.
 
-    ```python
-    tbl.search(np.random.randn(1536)).to_list()
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_as_list"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_async_as_list"
+        ```
 
     ### As a list of Pydantic models
 
     We can add data using Pydantic models, and we can certainly
     retrieve results as Pydantic models
 
-    ```python
-    tbl.search(np.random.randn(1536)).to_pydantic(LanceSchema)
-    ```
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:search_result_as_pydantic"
+        ```
+    !!! note
+        `to_pydantic()` is not yet supported with our asynchronous client.
 
     Note that in this case the extra `_distance` field is discarded since
     it's not part of the LanceSchema.
diff --git a/docs/src/sql.md b/docs/src/sql.md
index e2c084c5..5d3bdb09 100644
--- a/docs/src/sql.md
+++ b/docs/src/sql.md
@@ -15,13 +15,18 @@ Similarly, a highly selective post-filter can lead to false positives. Increasin
 ```python
 import lancedb
 import numpy as np
+
 uri = "data/sample-lancedb"
-db = lancedb.connect(uri)
-
 data = [{"vector": row, "item": f"item {i}", "id": i}
-     for i, row in enumerate(np.random.random((10_000, 2)).astype('int'))]
+    for i, row in enumerate(np.random.random((10_000, 2)).astype('int'))]
 
+# Synchronous client
+db = lancedb.connect(uri)
 tbl = db.create_table("my_vectors", data=data)
+
+# Asynchronous client
+async_db = await lancedb.connect_async(uri)
+async_tbl = await async_db.create_table("my_vectors_async", data=data)
 ```
 -->
 <!-- Setup Code
@@ -39,13 +44,11 @@ const tbl = await db.createTable('myVectors', data)
 
 === "Python"
 
-    ```py
-    result = (
-        tbl.search([0.5, 0.2])
-        .where("id = 10", prefilter=True)
-        .limit(1)
-        .to_arrow()
-    )
+    ```python
+    # Synchronous client
+    result = tbl.search([0.5, 0.2]).where("id = 10", prefilter=True).limit(1).to_arrow()
+    # Asynchronous client
+    result = await async_tbl.query().where("id = 10").nearest_to([0.5, 0.2]).limit(1).to_arrow()
     ```
 
 === "TypeScript"
@@ -88,9 +91,17 @@ For example, the following filter string is acceptable:
 === "Python"
 
     ```python
-    tbl.search([100, 102]) \
-       .where("(item IN ('item 0', 'item 2')) AND (id > 10)") \
-       .to_arrow()
+    # Synchronous client
+    tbl.search([100, 102]).where(
+        "(item IN ('item 0', 'item 2')) AND (id > 10)"
+    ).to_arrow()
+    # Asynchronous client
+    await (
+        async_tbl.query()
+        .where("(item IN ('item 0', 'item 2')) AND (id > 10)")
+        .nearest_to([100, 102])
+        .to_arrow()
+    )
     ```
 
 === "TypeScript"
@@ -168,7 +179,10 @@ You can also filter your data without search:
 === "Python"
 
     ```python
+    # Synchronous client
     tbl.search().where("id = 10").limit(10).to_arrow()
+    # Asynchronous client
+    await async_tbl.query().where("id = 10").limit(10).to_arrow()
     ```
 
 === "TypeScript"
diff --git a/docs/test/md_testing.py b/docs/test/md_testing.py
index 08008177..97051131 100755
--- a/docs/test/md_testing.py
+++ b/docs/test/md_testing.py
@@ -12,6 +12,8 @@ excluded_globs = [
     "../src/integrations/*.md",
     "../src/guides/tables.md",
     "../src/python/duckdb.md",
+    "../src/python/pandas_and_pyarrow.md",
+    "../src/python/polars_arrow.md",
     "../src/embeddings/*.md",
     "../src/concepts/*.md",
     "../src/ann_indexes.md",
@@ -23,9 +25,10 @@ excluded_globs = [
     "../src/embeddings/available_embedding_models/text_embedding_functions/*.md",
     "../src/embeddings/available_embedding_models/multimodal_embedding_functions/*.md",
     "../src/rag/*.md",
-    "../src/rag/advanced_techniques/*.md"
-
-
+    "../src/rag/advanced_techniques/*.md",
+    "../src/guides/scalar_index.md",
+    "../src/guides/storage.md",
+    "../src/search.md"
 ]
 
 python_prefix = "py"
diff --git a/python/python/tests/docs/test_basic.py b/python/python/tests/docs/test_basic.py
index 3f1280a2..62b9055d 100644
--- a/python/python/tests/docs/test_basic.py
+++ b/python/python/tests/docs/test_basic.py
@@ -125,7 +125,7 @@ async def test_quickstart_async():
 
     # --8<-- [start:create_table_async]
     # Asynchronous client
-    async_tbl = await async_db.create_table("my_table2", data=data)
+    async_tbl = await async_db.create_table("my_table_async", data=data)
     # --8<-- [end:create_table_async]
 
     df = pd.DataFrame(
@@ -137,17 +137,17 @@ async def test_quickstart_async():
 
     # --8<-- [start:create_table_async_pandas]
     # Asynchronous client
-    async_tbl = await async_db.create_table("table_from_df2", df)
+    async_tbl = await async_db.create_table("table_from_df_async", df)
     # --8<-- [end:create_table_async_pandas]
 
     schema = pa.schema([pa.field("vector", pa.list_(pa.float32(), list_size=2))])
     # --8<-- [start:create_empty_table_async]
     # Asynchronous client
-    async_tbl = await async_db.create_table("empty_table2", schema=schema)
+    async_tbl = await async_db.create_table("empty_table_async", schema=schema)
     # --8<-- [end:create_empty_table_async]
     # --8<-- [start:open_table_async]
     # Asynchronous client
-    async_tbl = await async_db.open_table("my_table2")
+    async_tbl = await async_db.open_table("my_table_async")
     # --8<-- [end:open_table_async]
     # --8<-- [start:table_names_async]
     # Asynchronous client
@@ -161,6 +161,22 @@ async def test_quickstart_async():
     data = [{"vector": [x, x], "item": "filler", "price": x * x} for x in range(1000)]
     await async_tbl.add(data)
     # --8<-- [start:vector_search_async]
+    # --8<-- [start:add_columns_async]
+    await async_tbl.add_columns({"double_price": "cast((price * 2) as float)"})
+    # --8<-- [end:add_columns_async]
+    # --8<-- [start:alter_columns_async]
+    await async_tbl.alter_columns(
+        {
+            "path": "double_price",
+            "rename": "dbl_price",
+            "data_type": pa.float64(),
+            "nullable": True,
+        }
+    )
+    # --8<-- [end:alter_columns_async]
+    # --8<-- [start:drop_columns_async]
+    await async_tbl.drop_columns(["dbl_price"])
+    # --8<-- [end:drop_columns_async]
     # Asynchronous client
     await async_tbl.vector_search([100, 100]).limit(2).to_pandas()
     # --8<-- [end:vector_search_async]
@@ -174,5 +190,5 @@ async def test_quickstart_async():
     # --8<-- [end:delete_rows_async]
     # --8<-- [start:drop_table_async]
     # Asynchronous client
-    await async_db.drop_table("my_table2")
+    await async_db.drop_table("my_table_async")
     # --8<-- [end:drop_table_async]
diff --git a/python/python/tests/docs/test_guide_index.py b/python/python/tests/docs/test_guide_index.py
new file mode 100644
index 00000000..5e99edaf
--- /dev/null
+++ b/python/python/tests/docs/test_guide_index.py
@@ -0,0 +1,169 @@
+# --8<-- [start:import-lancedb]
+import lancedb
+
+# --8<-- [end:import-lancedb]
+# --8<-- [start:import-lancedb-ivfpq]
+from lancedb.index import IvfPq
+
+# --8<-- [end:import-lancedb-ivfpq]
+# --8<-- [start:import-lancedb-btree-bitmap]
+from lancedb.index import BTree, Bitmap
+
+# --8<-- [end:import-lancedb-btree-bitmap]
+# --8<-- [start:import-numpy]
+import numpy as np
+
+# --8<-- [end:import-numpy]
+import pytest
+
+
+def test_ann_index():
+    # --8<-- [start:create_ann_index]
+    uri = "data/sample-lancedb"
+
+    # Create 5,000 sample vectors
+    data = [
+        {"vector": row, "item": f"item {i}"}
+        for i, row in enumerate(np.random.random((5_000, 32)).astype("float32"))
+    ]
+
+    db = lancedb.connect(uri)
+    # Add the vectors to a table
+    tbl = db.create_table("my_vectors", data=data)
+    # Create and train the index - you need to have enough data in the table
+    # for an effective training step
+    tbl.create_index(num_partitions=2, num_sub_vectors=4)
+    # --8<-- [end:create_ann_index]
+    # --8<-- [start:vector_search]
+    tbl.search(np.random.random((32))).limit(2).nprobes(20).refine_factor(
+        10
+    ).to_pandas()
+    # --8<-- [end:vector_search]
+    # --8<-- [start:vector_search_with_filter]
+    tbl.search(np.random.random((32))).where("item != 'item 1141'").to_pandas()
+    # --8<-- [end:vector_search_with_filter]
+    # --8<-- [start:vector_search_with_select]
+    tbl.search(np.random.random((32))).select(["vector"]).to_pandas()
+    # --8<-- [end:vector_search_with_select]
+
+
+@pytest.mark.asyncio
+async def test_ann_index_async():
+    # --8<-- [start:create_ann_index_async]
+    uri = "data/sample-lancedb"
+
+    # Create 5,000 sample vectors
+    data = [
+        {"vector": row, "item": f"item {i}"}
+        for i, row in enumerate(np.random.random((5_000, 32)).astype("float32"))
+    ]
+
+    async_db = await lancedb.connect_async(uri)
+    # Add the vectors to a table
+    async_tbl = await async_db.create_table("my_vectors_async", data=data)
+    # Create and train the index - you need to have enough data in the table
+    # for an effective training step
+    await async_tbl.create_index(
+        "vector", config=IvfPq(num_partitions=2, num_sub_vectors=4)
+    )
+    # --8<-- [end:create_ann_index_async]
+    # --8<-- [start:vector_search_async]
+    await (
+        async_tbl.query()
+        .nearest_to(np.random.random((32)))
+        .limit(2)
+        .nprobes(20)
+        .refine_factor(10)
+        .to_pandas()
+    )
+    # --8<-- [end:vector_search_async]
+    # --8<-- [start:vector_search_async_with_filter]
+    await (
+        async_tbl.query()
+        .nearest_to(np.random.random((32)))
+        .where("item != 'item 1141'")
+        .to_pandas()
+    )
+    # --8<-- [end:vector_search_async_with_filter]
+    # --8<-- [start:vector_search_async_with_select]
+    await (
+        async_tbl.query()
+        .nearest_to(np.random.random((32)))
+        .select(["vector"])
+        .to_pandas()
+    )
+    # --8<-- [end:vector_search_async_with_select]
+
+
+def test_scalar_index():
+    # --8<-- [start:basic_scalar_index]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+    books = [
+        {
+            "book_id": 1,
+            "publisher": "plenty of books",
+            "tags": ["fantasy", "adventure"],
+        },
+        {"book_id": 2, "publisher": "book town", "tags": ["non-fiction"]},
+        {"book_id": 3, "publisher": "oreilly", "tags": ["textbook"]},
+    ]
+    table = db.create_table("books", books)
+    table.create_scalar_index("book_id")  # BTree by default
+    table.create_scalar_index("publisher", index_type="BITMAP")
+    # --8<-- [end:basic_scalar_index]
+    # --8<-- [start:search_with_scalar_index]
+    table = db.open_table("books")
+    table.search().where("book_id = 2").to_pandas()
+    # --8<-- [end:search_with_scalar_index]
+    # --8<-- [start:vector_search_with_scalar_index]
+    data = [
+        {"book_id": 1, "vector": [1, 2]},
+        {"book_id": 2, "vector": [3, 4]},
+        {"book_id": 3, "vector": [5, 6]},
+    ]
+
+    table = db.create_table("book_with_embeddings", data)
+    (table.search([1, 2]).where("book_id != 3", prefilter=True).to_pandas())
+    # --8<-- [end:vector_search_with_scalar_index]
+    # --8<-- [start:update_scalar_index]
+    table.add([{"vector": [7, 8], "book_id": 4}])
+    table.optimize()
+    # --8<-- [end:update_scalar_index]
+
+
+@pytest.mark.asyncio
+async def test_scalar_index_async():
+    # --8<-- [start:basic_scalar_index_async]
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri)
+    books = [
+        {
+            "book_id": 1,
+            "publisher": "plenty of books",
+            "tags": ["fantasy", "adventure"],
+        },
+        {"book_id": 2, "publisher": "book town", "tags": ["non-fiction"]},
+        {"book_id": 3, "publisher": "oreilly", "tags": ["textbook"]},
+    ]
+    async_tbl = await async_db.create_table("books_async", books)
+    await async_tbl.create_index("book_id", config=BTree())  # BTree by default
+    await async_tbl.create_index("publisher", config=Bitmap())
+    # --8<-- [end:basic_scalar_index_async]
+    # --8<-- [start:search_with_scalar_index_async]
+    async_tbl = await async_db.open_table("books_async")
+    await async_tbl.query().where("book_id = 2").to_pandas()
+    # --8<-- [end:search_with_scalar_index_async]
+    # --8<-- [start:vector_search_with_scalar_index_async]
+    data = [
+        {"book_id": 1, "vector": [1, 2]},
+        {"book_id": 2, "vector": [3, 4]},
+        {"book_id": 3, "vector": [5, 6]},
+    ]
+    async_tbl = await async_db.create_table("book_with_embeddings_async", data)
+    (await async_tbl.query().where("book_id != 3").nearest_to([1, 2]).to_pandas())
+    # --8<-- [end:vector_search_with_scalar_index_async]
+    # --8<-- [start:update_scalar_index_async]
+    await async_tbl.add([{"vector": [7, 8], "book_id": 4}])
+    await async_tbl.optimize()
+    # --8<-- [end:update_scalar_index_async]
diff --git a/python/python/tests/docs/test_guide_tables.py b/python/python/tests/docs/test_guide_tables.py
new file mode 100644
index 00000000..fd23c1fb
--- /dev/null
+++ b/python/python/tests/docs/test_guide_tables.py
@@ -0,0 +1,576 @@
+# --8<-- [start:import-lancedb]
+import lancedb
+
+# --8<-- [end:import-lancedb]
+# --8<-- [start:import-pandas]
+import pandas as pd
+
+# --8<-- [end:import-pandas]
+# --8<-- [start:import-pyarrow]
+import pyarrow as pa
+
+# --8<-- [end:import-pyarrow]
+# --8<-- [start:import-polars]
+import polars as pl
+
+# --8<-- [end:import-polars]
+# --8<-- [start:import-numpy]
+import numpy as np
+
+# --8<-- [end:import-numpy]
+# --8<-- [start:import-lancedb-pydantic]
+from lancedb.pydantic import Vector, LanceModel
+
+# --8<-- [end:import-lancedb-pydantic]
+# --8<-- [start:import-datetime]
+from datetime import timedelta
+
+# --8<-- [end:import-datetime]
+# --8<-- [start:import-embeddings]
+from lancedb.embeddings import get_registry
+
+# --8<-- [end:import-embeddings]
+# --8<-- [start:import-pydantic-basemodel]
+from pydantic import BaseModel
+
+# --8<-- [end:import-pydantic-basemodel]
+import pytest
+
+
+# --8<-- [start:class-Content]
+class Content(LanceModel):
+    movie_id: int
+    vector: Vector(128)
+    genres: str
+    title: str
+    imdb_id: int
+
+    @property
+    def imdb_url(self) -> str:
+        return f"https://www.imdb.com/title/tt{self.imdb_id}"
+
+
+# --8<-- [end:class-Content]
+# --8<-- [start:class-Document]
+class Document(BaseModel):
+    content: str
+    source: str
+
+
+# --8<-- [end:class-Document]
+# --8<-- [start:class-NestedSchema]
+class NestedSchema(LanceModel):
+    id: str
+    vector: Vector(1536)
+    document: Document
+
+
+# --8<-- [end:class-NestedSchema]
+# --8<-- [start:class-Item]
+class Item(LanceModel):
+    vector: Vector(2)
+    item: str
+    price: float
+
+
+# --8<-- [end:class-Item]
+
+
+# --8<-- [start:make_batches]
+def make_batches():
+    for i in range(5):
+        yield pa.RecordBatch.from_arrays(
+            [
+                pa.array(
+                    [[3.1, 4.1, 5.1, 6.1], [5.9, 26.5, 4.7, 32.8]],
+                    pa.list_(pa.float32(), 4),
+                ),
+                pa.array(["foo", "bar"]),
+                pa.array([10.0, 20.0]),
+            ],
+            ["vector", "item", "price"],
+        )
+
+
+# --8<-- [end:make_batches]
+
+
+# --8<-- [start:make_batches_for_add]
+def make_batches_for_add():
+    for i in range(5):
+        yield [
+            {"vector": [3.1, 4.1], "item": "peach", "price": 6.0},
+            {"vector": [5.9, 26.5], "item": "pear", "price": 5.0},
+        ]
+
+
+# --8<-- [end:make_batches_for_add]
+
+
+def test_table():
+    # --8<-- [start:connect]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+    # --8<-- [end:connect]
+    # --8<-- [start:create_table]
+    data = [
+        {"vector": [1.1, 1.2], "lat": 45.5, "long": -122.7},
+        {"vector": [0.2, 1.8], "lat": 40.1, "long": -74.1},
+    ]
+    db.create_table("test_table", data)
+    db["test_table"].head()
+    # --8<-- [end:create_table]
+    # --8<-- [start:create_table_exist_ok]
+    db.create_table("test_table", data, exist_ok=True)
+    # --8<-- [end:create_table_exist_ok]
+    # --8<-- [start:create_table_overwrite]
+    db.create_table("test_table", data, mode="overwrite")
+    # --8<-- [end:create_table_overwrite]
+    # --8<-- [start:create_table_from_pandas]
+    data = pd.DataFrame(
+        {
+            "vector": [[1.1, 1.2, 1.3, 1.4], [0.2, 1.8, 0.4, 3.6]],
+            "lat": [45.5, 40.1],
+            "long": [-122.7, -74.1],
+        }
+    )
+    db.create_table("my_table_pandas", data)
+    db["my_table_pandas"].head()
+    # --8<-- [end:create_table_from_pandas]
+    # --8<-- [start:create_table_custom_schema]
+    custom_schema = pa.schema(
+        [
+            pa.field("vector", pa.list_(pa.float32(), 4)),
+            pa.field("lat", pa.float32()),
+            pa.field("long", pa.float32()),
+        ]
+    )
+
+    tbl = db.create_table("my_table_custom_schema", data, schema=custom_schema)
+    # --8<-- [end:create_table_custom_schema]
+    # --8<-- [start:create_table_from_polars]
+    data = pl.DataFrame(
+        {
+            "vector": [[3.1, 4.1], [5.9, 26.5]],
+            "item": ["foo", "bar"],
+            "price": [10.0, 20.0],
+        }
+    )
+    tbl = db.create_table("my_table_pl", data)
+    # --8<-- [end:create_table_from_polars]
+    # --8<-- [start:create_table_from_arrow_table]
+    dim = 16
+    total = 2
+    schema = pa.schema(
+        [pa.field("vector", pa.list_(pa.float16(), dim)), pa.field("text", pa.string())]
+    )
+    data = pa.Table.from_arrays(
+        [
+            pa.array(
+                [np.random.randn(dim).astype(np.float16) for _ in range(total)],
+                pa.list_(pa.float16(), dim),
+            ),
+            pa.array(["foo", "bar"]),
+        ],
+        ["vector", "text"],
+    )
+    tbl = db.create_table("f16_tbl", data, schema=schema)
+    # --8<-- [end:create_table_from_arrow_table]
+    # --8<-- [start:create_table_from_pydantic]
+    tbl = db.create_table("movielens_small", schema=Content)
+    # --8<-- [end:create_table_from_pydantic]
+    # --8<-- [start:create_table_nested_schema]
+    tbl = db.create_table("nested_table", schema=NestedSchema)
+    # --8<-- [end:create_table_nested_schema]
+    # --8<-- [start:create_table_from_batch]
+    schema = pa.schema(
+        [
+            pa.field("vector", pa.list_(pa.float32(), 4)),
+            pa.field("item", pa.utf8()),
+            pa.field("price", pa.float32()),
+        ]
+    )
+    db.create_table("batched_tale", make_batches(), schema=schema)
+    # --8<-- [end:create_table_from_batch]
+    # --8<-- [start:list_tables]
+    print(db.table_names())
+    # --8<-- [end:list_tables]
+    # --8<-- [start:open_table]
+    tbl = db.open_table("test_table")
+    # --8<-- [end:open_table]
+    # --8<-- [start:create_empty_table]
+    schema = pa.schema(
+        [
+            pa.field("vector", pa.list_(pa.float32(), 2)),
+            pa.field("item", pa.string()),
+            pa.field("price", pa.float32()),
+        ]
+    )
+    tbl = db.create_table("test_empty_table", schema=schema)
+    # --8<-- [end:create_empty_table]
+    # --8<-- [start:create_empty_table_pydantic]
+    tbl = db.create_table("test_empty_table_new", schema=Item.to_arrow_schema())
+    # --8<-- [end:create_empty_table_pydantic]
+    # --8<-- [start:add_table_from_pandas]
+    df = pd.DataFrame(
+        {
+            "vector": [[1.3, 1.4], [9.5, 56.2]],
+            "item": ["banana", "apple"],
+            "price": [5.0, 7.0],
+        }
+    )
+
+    tbl.add(df)
+    # --8<-- [end:add_table_from_pandas]
+    # --8<-- [start:add_table_from_polars]
+    df = pl.DataFrame(
+        {
+            "vector": [[1.3, 1.4], [9.5, 56.2]],
+            "item": ["banana", "apple"],
+            "price": [5.0, 7.0],
+        }
+    )
+
+    tbl.add(df)
+    # --8<-- [end:add_table_from_polars]
+    # --8<-- [start:add_table_from_batch]
+    tbl.add(make_batches_for_add())
+    # --8<-- [end:add_table_from_batch]
+    # --8<-- [start:add_table_from_pyarrow]
+    pa_table = pa.Table.from_arrays(
+        [
+            pa.array([[9.1, 6.7], [9.9, 31.2]], pa.list_(pa.float32(), 2)),
+            pa.array(["mango", "orange"]),
+            pa.array([7.0, 4.0]),
+        ],
+        ["vector", "item", "price"],
+    )
+    tbl.add(pa_table)
+    # --8<-- [end:add_table_from_pyarrow]
+    # --8<-- [start:add_table_from_pydantic]
+    pydantic_model_items = [
+        Item(vector=[8.1, 4.7], item="pineapple", price=10.0),
+        Item(vector=[6.9, 9.3], item="avocado", price=9.0),
+    ]
+    tbl.add(pydantic_model_items)
+    # --8<-- [end:add_table_from_pydantic]
+    # --8<-- [start:delete_row]
+    tbl.delete('item = "fizz"')
+    # --8<-- [end:delete_row]
+    # --8<-- [start:delete_specific_row]
+    data = [
+        {"x": 1, "vector": [1, 2]},
+        {"x": 2, "vector": [3, 4]},
+        {"x": 3, "vector": [5, 6]},
+    ]
+    # Synchronous client
+    tbl = db.create_table("delete_row", data)
+    tbl.to_pandas()
+    #   x      vector
+    # 0  1  [1.0, 2.0]
+    # 1  2  [3.0, 4.0]
+    # 2  3  [5.0, 6.0]
+
+    tbl.delete("x = 2")
+    tbl.to_pandas()
+    #   x      vector
+    # 0  1  [1.0, 2.0]
+    # 1  3  [5.0, 6.0]
+    # --8<-- [end:delete_specific_row]
+    # --8<-- [start:delete_list_values]
+    to_remove = [1, 5]
+    to_remove = ", ".join(str(v) for v in to_remove)
+
+    tbl.delete(f"x IN ({to_remove})")
+    tbl.to_pandas()
+    #   x      vector
+    # 0  3  [5.0, 6.0]
+    # --8<-- [end:delete_list_values]
+    # --8<-- [start:update_table]
+    # Create a table from a pandas DataFrame
+    data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
+
+    tbl = db.create_table("test_table", data, mode="overwrite")
+    # Update the table where x = 2
+    tbl.update(where="x = 2", values={"vector": [10, 10]})
+    # Get the updated table as a pandas DataFrame
+    df = tbl.to_pandas()
+    print(df)
+    # --8<-- [end:update_table]
+    # --8<-- [start:update_table_sql]
+    # Update the table where x = 2
+    tbl.update(values_sql={"x": "x + 1"})
+    print(tbl.to_pandas())
+    # --8<-- [end:update_table_sql]
+    # --8<-- [start:table_strong_consistency]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri, read_consistency_interval=timedelta(0))
+    tbl = db.open_table("test_table")
+    # --8<-- [end:table_strong_consistency]
+    # --8<-- [start:table_eventual_consistency]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri, read_consistency_interval=timedelta(seconds=5))
+    tbl = db.open_table("test_table")
+    # --8<-- [end:table_eventual_consistency]
+    # --8<-- [start:table_checkout_latest]
+    tbl = db.open_table("test_table")
+
+    # (Other writes happen to my_table from another process)
+
+    # Check for updates
+    tbl.checkout_latest()
+    # --8<-- [end:table_checkout_latest]
+
+
+@pytest.mark.skip
+def test_table_with_embedding():
+    db = lancedb.connect("data/sample-lancedb")
+    # --8<-- [start:create_table_with_embedding]
+    embed_fcn = get_registry().get("huggingface").create(name="BAAI/bge-small-en-v1.5")
+
+    class Schema(LanceModel):
+        text: str = embed_fcn.SourceField()
+        vector: Vector(embed_fcn.ndims()) = embed_fcn.VectorField(default=None)
+
+    tbl = db.create_table("my_table_with_embedding", schema=Schema, mode="overwrite")
+    models = [Schema(text="hello"), Schema(text="world")]
+    tbl.add(models)
+    # --8<-- [end:create_table_with_embedding]
+
+
+@pytest.mark.skip
+async def test_table_with_embedding_async():
+    async_db = await lancedb.connect_async("data/sample-lancedb")
+    # --8<-- [start:create_table_async_with_embedding]
+    embed_fcn = get_registry().get("huggingface").create(name="BAAI/bge-small-en-v1.5")
+
+    class Schema(LanceModel):
+        text: str = embed_fcn.SourceField()
+        vector: Vector(embed_fcn.ndims()) = embed_fcn.VectorField(default=None)
+
+    async_tbl = await async_db.create_table(
+        "my_table_async_with_embedding", schema=Schema, mode="overwrite"
+    )
+    models = [Schema(text="hello"), Schema(text="world")]
+    await async_tbl.add(models)
+    # --8<-- [end:create_table_async_with_embedding]
+
+
+@pytest.mark.asyncio
+async def test_table_async():
+    # --8<-- [start:connect_async]
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri)
+    # --8<-- [end:connect_async]
+    # --8<-- [start:create_table_async]
+    data = [
+        {"vector": [1.1, 1.2], "lat": 45.5, "long": -122.7},
+        {"vector": [0.2, 1.8], "lat": 40.1, "long": -74.1},
+    ]
+    async_tbl = await async_db.create_table("test_table_async", data)
+    await async_tbl.head()
+    # --8<-- [end:create_table_async]
+    # --8<-- [start:create_table_async_exist_ok]
+    await async_db.create_table("test_table_async", data, exist_ok=True)
+    # --8<-- [end:create_table_async_exist_ok]
+    # --8<-- [start:create_table_async_overwrite]
+    await async_db.create_table("test_table_async", data, mode="overwrite")
+    # --8<-- [end:create_table_async_overwrite]
+    # --8<-- [start:create_table_async_from_pandas]
+    data = pd.DataFrame(
+        {
+            "vector": [[1.1, 1.2, 1.3, 1.4], [0.2, 1.8, 0.4, 3.6]],
+            "lat": [45.5, 40.1],
+            "long": [-122.7, -74.1],
+        }
+    )
+    async_tbl = await async_db.create_table("my_table_async_pd", data)
+    await async_tbl.head()
+    # --8<-- [end:create_table_async_from_pandas]
+    # --8<-- [start:create_table_async_custom_schema]
+    custom_schema = pa.schema(
+        [
+            pa.field("vector", pa.list_(pa.float32(), 4)),
+            pa.field("lat", pa.float32()),
+            pa.field("long", pa.float32()),
+        ]
+    )
+    async_tbl = await async_db.create_table(
+        "my_table_async_custom_schema", data, schema=custom_schema
+    )
+    # --8<-- [end:create_table_async_custom_schema]
+    # --8<-- [start:create_table_async_from_polars]
+    data = pl.DataFrame(
+        {
+            "vector": [[3.1, 4.1], [5.9, 26.5]],
+            "item": ["foo", "bar"],
+            "price": [10.0, 20.0],
+        }
+    )
+    async_tbl = await async_db.create_table("my_table_async_pl", data)
+    # --8<-- [end:create_table_async_from_polars]
+    # --8<-- [start:create_table_async_from_arrow_table]
+    dim = 16
+    total = 2
+    schema = pa.schema(
+        [pa.field("vector", pa.list_(pa.float16(), dim)), pa.field("text", pa.string())]
+    )
+    data = pa.Table.from_arrays(
+        [
+            pa.array(
+                [np.random.randn(dim).astype(np.float16) for _ in range(total)],
+                pa.list_(pa.float16(), dim),
+            ),
+            pa.array(["foo", "bar"]),
+        ],
+        ["vector", "text"],
+    )
+    async_tbl = await async_db.create_table("f16_tbl_async", data, schema=schema)
+    # --8<-- [end:create_table_async_from_arrow_table]
+    # --8<-- [start:create_table_async_from_pydantic]
+    async_tbl = await async_db.create_table("movielens_small_async", schema=Content)
+    # --8<-- [end:create_table_async_from_pydantic]
+    # --8<-- [start:create_table_async_nested_schema]
+    async_tbl = await async_db.create_table("nested_table_async", schema=NestedSchema)
+    # --8<-- [end:create_table_async_nested_schema]
+    # --8<-- [start:create_table_async_from_batch]
+    schema = pa.schema(
+        [
+            pa.field("vector", pa.list_(pa.float32(), 4)),
+            pa.field("item", pa.utf8()),
+            pa.field("price", pa.float32()),
+        ]
+    )
+    await async_db.create_table("batched_table", make_batches(), schema=schema)
+    # --8<-- [end:create_table_async_from_batch]
+    # --8<-- [start:list_tables_async]
+    print(await async_db.table_names())
+    # --8<-- [end:list_tables_async]
+    # --8<-- [start:open_table_async]
+    async_tbl = await async_db.open_table("test_table_async")
+    # --8<-- [end:open_table_async]
+    # --8<-- [start:create_empty_table_async]
+    schema = pa.schema(
+        [
+            pa.field("vector", pa.list_(pa.float32(), 2)),
+            pa.field("item", pa.string()),
+            pa.field("price", pa.float32()),
+        ]
+    )
+    async_tbl = await async_db.create_table("test_empty_table_async", schema=schema)
+    # --8<-- [end:create_empty_table_async]
+    # --8<-- [start:create_empty_table_async_pydantic]
+    async_tbl = await async_db.create_table(
+        "test_empty_table_async_new", schema=Item.to_arrow_schema()
+    )
+    # --8<-- [end:create_empty_table_async_pydantic]
+    # --8<-- [start:add_table_async_from_pandas]
+    df = pd.DataFrame(
+        {
+            "vector": [[1.3, 1.4], [9.5, 56.2]],
+            "item": ["banana", "apple"],
+            "price": [5.0, 7.0],
+        }
+    )
+    await async_tbl.add(df)
+    # --8<-- [end:add_table_async_from_pandas]
+    # --8<-- [start:add_table_async_from_polars]
+    df = pl.DataFrame(
+        {
+            "vector": [[1.3, 1.4], [9.5, 56.2]],
+            "item": ["banana", "apple"],
+            "price": [5.0, 7.0],
+        }
+    )
+    await async_tbl.add(df)
+    # --8<-- [end:add_table_async_from_polars]
+    # --8<-- [start:add_table_async_from_batch]
+    await async_tbl.add(make_batches_for_add())
+    # --8<-- [end:add_table_async_from_batch]
+    # --8<-- [start:add_table_async_from_pyarrow]
+    pa_table = pa.Table.from_arrays(
+        [
+            pa.array([[9.1, 6.7], [9.9, 31.2]], pa.list_(pa.float32(), 2)),
+            pa.array(["mango", "orange"]),
+            pa.array([7.0, 4.0]),
+        ],
+        ["vector", "item", "price"],
+    )
+    await async_tbl.add(pa_table)
+    # --8<-- [end:add_table_async_from_pyarrow]
+    # --8<-- [start:add_table_async_from_pydantic]
+    pydantic_model_items = [
+        Item(vector=[8.1, 4.7], item="pineapple", price=10.0),
+        Item(vector=[6.9, 9.3], item="avocado", price=9.0),
+    ]
+    await async_tbl.add(pydantic_model_items)
+    # --8<-- [end:add_table_async_from_pydantic]
+    # --8<-- [start:delete_row_async]
+    await async_tbl.delete('item = "fizz"')
+    # --8<-- [end:delete_row_async]
+    # --8<-- [start:delete_specific_row_async]
+    data = [
+        {"x": 1, "vector": [1, 2]},
+        {"x": 2, "vector": [3, 4]},
+        {"x": 3, "vector": [5, 6]},
+    ]
+    async_db = await lancedb.connect_async(uri)
+    async_tbl = await async_db.create_table("delete_row_async", data)
+    await async_tbl.to_pandas()
+    #   x      vector
+    # 0  1  [1.0, 2.0]
+    # 1  2  [3.0, 4.0]
+    # 2  3  [5.0, 6.0]
+
+    await async_tbl.delete("x = 2")
+    await async_tbl.to_pandas()
+    #   x      vector
+    # 0  1  [1.0, 2.0]
+    # 1  3  [5.0, 6.0]
+    # --8<-- [end:delete_specific_row_async]
+    # --8<-- [start:delete_list_values_async]
+    to_remove = [1, 5]
+    to_remove = ", ".join(str(v) for v in to_remove)
+
+    await async_tbl.delete(f"x IN ({to_remove})")
+    await async_tbl.to_pandas()
+    #   x      vector
+    # 0  3  [5.0, 6.0]
+    # --8<-- [end:delete_list_values_async]
+    # --8<-- [start:update_table_async]
+    # Create a table from a pandas DataFrame
+    data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
+
+    async_tbl = await async_db.create_table("update_table_async", data)
+    # Update the table where x = 2
+    await async_tbl.update({"vector": [10, 10]}, where="x = 2")
+    # Get the updated table as a pandas DataFrame
+    df = await async_tbl.to_pandas()
+    # Print the DataFrame
+    print(df)
+    # --8<-- [end:update_table_async]
+    # --8<-- [start:update_table_sql_async]
+    # Update the table where x = 2
+    await async_tbl.update(updates_sql={"x": "x + 1"})
+    print(await async_tbl.to_pandas())
+    # --8<-- [end:update_table_sql_async]
+    # --8<-- [start:table_async_strong_consistency]
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri, read_consistency_interval=timedelta(0))
+    async_tbl = await async_db.open_table("test_table_async")
+    # --8<-- [end:table_async_strong_consistency]
+    # --8<-- [start:table_async_ventual_consistency]
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(
+        uri, read_consistency_interval=timedelta(seconds=5)
+    )
+    async_tbl = await async_db.open_table("test_table_async")
+    # --8<-- [end:table_async_eventual_consistency]
+    # --8<-- [start:table_async_checkout_latest]
+    async_tbl = await async_db.open_table("test_table_async")
+
+    # (Other writes happen to test_table_async from another process)
+
+    # Check for updates
+    await async_tbl.checkout_latest()
+    # --8<-- [end:table_async_checkout_latest]
diff --git a/python/python/tests/docs/test_python.py b/python/python/tests/docs/test_python.py
new file mode 100644
index 00000000..44c028db
--- /dev/null
+++ b/python/python/tests/docs/test_python.py
@@ -0,0 +1,187 @@
+# --8<-- [start:import-lancedb]
+import lancedb
+
+# --8<-- [end:import-lancedb]
+# --8<-- [start:import-pandas]
+import pandas as pd
+
+# --8<-- [end:import-pandas]
+# --8<-- [start:import-iterable]
+from typing import Iterable
+
+# --8<-- [end:import-iterable]
+# --8<-- [start:import-pyarrow]
+import pyarrow as pa
+
+# --8<-- [end:import-pyarrow]
+# --8<-- [start:import-polars]
+import polars as pl
+
+# --8<-- [end:import-polars]
+# --8<-- [start:import-lancedb-pydantic]
+from lancedb.pydantic import Vector, LanceModel
+
+# --8<-- [end:import-lancedb-pydantic]
+import pytest
+
+
+# --8<-- [start:make_batches]
+def make_batches() -> Iterable[pa.RecordBatch]:
+    for i in range(5):
+        yield pa.RecordBatch.from_arrays(
+            [
+                pa.array([[3.1, 4.1], [5.9, 26.5]]),
+                pa.array(["foo", "bar"]),
+                pa.array([10.0, 20.0]),
+            ],
+            ["vector", "item", "price"],
+        )
+
+
+# --8<-- [end:make_batches]
+
+
+def test_pandas_and_pyarrow():
+    # --8<-- [start:connect_to_lancedb]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+    # --8<-- [end:connect_to_lancedb]
+    # --8<-- [start:create_table_pandas]
+    data = pd.DataFrame(
+        {
+            "vector": [[3.1, 4.1], [5.9, 26.5]],
+            "item": ["foo", "bar"],
+            "price": [10.0, 20.0],
+        }
+    )
+    table = db.create_table("pd_table", data=data)
+    # --8<-- [end:create_table_pandas]
+    # --8<-- [start:create_table_iterable]
+    schema = pa.schema(
+        [
+            pa.field("vector", pa.list_(pa.float32())),
+            pa.field("item", pa.utf8()),
+            pa.field("price", pa.float32()),
+        ]
+    )
+    table = db.create_table("iterable_table", data=make_batches(), schema=schema)
+    # --8<-- [end:create_table_iterable]
+    # --8<-- [start:vector_search]
+    # Open the table previously created.
+    table = db.open_table("pd_table")
+
+    query_vector = [100, 100]
+    # Pandas DataFrame
+    df = table.search(query_vector).limit(1).to_pandas()
+    print(df)
+    # --8<-- [end:vector_search]
+    # --8<-- [start:vector_search_with_filter]
+    # Apply the filter via LanceDB
+    results = table.search([100, 100]).where("price < 15").to_pandas()
+    assert len(results) == 1
+    assert results["item"].iloc[0] == "foo"
+
+    # Apply the filter via Pandas
+    df = results = table.search([100, 100]).to_pandas()
+    results = df[df.price < 15]
+    assert len(results) == 1
+    assert results["item"].iloc[0] == "foo"
+    # --8<-- [end:vector_search_with_filter]
+
+
+@pytest.mark.asyncio
+async def test_pandas_and_pyarrow_async():
+    # --8<-- [start:connect_to_lancedb_async]
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri)
+    # --8<-- [end:connect_to_lancedb_async]
+    # --8<-- [start:create_table_pandas_async]
+    data = pd.DataFrame(
+        {
+            "vector": [[3.1, 4.1], [5.9, 26.5]],
+            "item": ["foo", "bar"],
+            "price": [10.0, 20.0],
+        }
+    )
+    await async_db.create_table("pd_table_async", data=data)
+    # --8<-- [end:create_table_pandas_async]
+    # --8<-- [start:create_table_iterable_async]
+    schema = pa.schema(
+        [
+            pa.field("vector", pa.list_(pa.float32())),
+            pa.field("item", pa.utf8()),
+            pa.field("price", pa.float32()),
+        ]
+    )
+    await async_db.create_table(
+        "iterable_table_async", data=make_batches(), schema=schema
+    )
+    # --8<-- [end:create_table_iterable_async]
+    # --8<-- [start:vector_search_async]
+    # Open the table previously created.
+    async_tbl = await async_db.open_table("pd_table_async")
+
+    query_vector = [100, 100]
+    # Pandas DataFrame
+    df = await async_tbl.query().nearest_to(query_vector).limit(1).to_pandas()
+    print(df)
+    # --8<-- [end:vector_search_async]
+    # --8<-- [start:vector_search_with_filter_async]
+    # Apply the filter via LanceDB
+    results = (
+        await async_tbl.query().nearest_to([100, 100]).where("price < 15").to_pandas()
+    )
+    assert len(results) == 1
+    assert results["item"].iloc[0] == "foo"
+
+    # Apply the filter via Pandas
+    df = results = await async_tbl.query().nearest_to([100, 100]).to_pandas()
+    results = df[df.price < 15]
+    assert len(results) == 1
+    assert results["item"].iloc[0] == "foo"
+    # --8<-- [end:vector_search_with_filter_async]
+
+
+# --8<-- [start:class_Item]
+class Item(LanceModel):
+    vector: Vector(2)
+    item: str
+    price: float
+
+
+# --8<-- [end:class_Item]
+
+
+def test_polars():
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+
+    # --8<-- [start:create_table_polars]
+    data = pl.DataFrame(
+        {
+            "vector": [[3.1, 4.1], [5.9, 26.5]],
+            "item": ["foo", "bar"],
+            "price": [10.0, 20.0],
+        }
+    )
+    table = db.create_table("pl_table", data=data)
+    # --8<-- [end:create_table_polars]
+    # --8<-- [start:vector_search_polars]
+    query = [3.0, 4.0]
+    result = table.search(query).limit(1).to_polars()
+    print(result)
+    print(type(result))
+    # --8<-- [end:vector_search_polars]
+    # --8<-- [start:create_table_pydantic]
+    table = db.create_table("pydantic_table", schema=Item)
+    df = pl.DataFrame(data)
+    # Add Polars DataFrame to table
+    table.add(df)
+    # --8<-- [end:create_table_pydantic]
+    # --8<-- [start:dump_table_lazyform]
+    ldf = table.to_polars()
+    print(type(ldf))
+    # --8<-- [end:dump_table_lazyform]
+    # --8<-- [start:print_table_lazyform]
+    print(ldf.first().collect())
+    # --8<-- [end:print_table_lazyform]
diff --git a/python/python/tests/docs/test_search.py b/python/python/tests/docs/test_search.py
new file mode 100644
index 00000000..df1103ca
--- /dev/null
+++ b/python/python/tests/docs/test_search.py
@@ -0,0 +1,366 @@
+# --8<-- [start:import-lancedb]
+import lancedb
+
+# --8<-- [end:import-lancedb]
+# --8<-- [start:import-numpy]
+import numpy as np
+
+# --8<-- [end:import-numpy]
+# --8<-- [start:import-datetime]
+from datetime import datetime
+
+# --8<-- [end:import-datetime]
+# --8<-- [start:import-lancedb-pydantic]
+from lancedb.pydantic import Vector, LanceModel
+
+# --8<-- [end:import-lancedb-pydantic]
+# --8<-- [start:import-pydantic-base-model]
+from pydantic import BaseModel
+
+# --8<-- [end:import-pydantic-base-model]
+# --8<-- [start:import-lancedb-fts]
+from lancedb.index import FTS
+
+# --8<-- [end:import-lancedb-fts]
+# --8<-- [start:import-os]
+import os
+
+# --8<-- [end:import-os]
+# --8<-- [start:import-embeddings]
+from lancedb.embeddings import get_registry
+
+# --8<-- [end:import-embeddings]
+import pytest
+
+
+# --8<-- [start:class-definition]
+class Metadata(BaseModel):
+    source: str
+    timestamp: datetime
+
+
+class Document(BaseModel):
+    content: str
+    meta: Metadata
+
+
+class LanceSchema(LanceModel):
+    id: str
+    vector: Vector(1536)
+    payload: Document
+
+
+# --8<-- [end:class-definition]
+
+
+def test_vector_search():
+    # --8<-- [start:exhaustive_search]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+    data = [
+        {"vector": row, "item": f"item {i}"}
+        for i, row in enumerate(np.random.random((10_000, 1536)).astype("float32"))
+    ]
+    tbl = db.create_table("vector_search", data=data)
+    tbl.search(np.random.random((1536))).limit(10).to_list()
+    # --8<-- [end:exhaustive_search]
+    # --8<-- [start:exhaustive_search_cosine]
+    tbl.search(np.random.random((1536))).metric("cosine").limit(10).to_list()
+    # --8<-- [end:exhaustive_search_cosine]
+    # --8<-- [start:create_table_with_nested_schema]
+    # Let's add 100 sample rows to our dataset
+    data = [
+        LanceSchema(
+            id=f"id{i}",
+            vector=np.random.randn(1536),
+            payload=Document(
+                content=f"document{i}",
+                meta=Metadata(source=f"source{i % 10}", timestamp=datetime.now()),
+            ),
+        )
+        for i in range(100)
+    ]
+
+    # Synchronous client
+    tbl = db.create_table("documents", data=data)
+    # --8<-- [end:create_table_with_nested_schema]
+    # --8<-- [start:search_result_as_pyarrow]
+    tbl.search(np.random.randn(1536)).to_arrow()
+    # --8<-- [end:search_result_as_pyarrow]
+    # --8<-- [start:search_result_as_pandas]
+    tbl.search(np.random.randn(1536)).to_pandas()
+    # --8<-- [end:search_result_as_pandas]
+    # --8<-- [start:search_result_as_pandas_flatten_true]
+    tbl.search(np.random.randn(1536)).to_pandas(flatten=True)
+    # --8<-- [end:search_result_as_pandas_flatten_true]
+    # --8<-- [start:search_result_as_pandas_flatten_1]
+    tbl.search(np.random.randn(1536)).to_pandas(flatten=1)
+    # --8<-- [end:search_result_as_pandas_flatten_1]
+    # --8<-- [start:search_result_as_list]
+    tbl.search(np.random.randn(1536)).to_list()
+    # --8<-- [end:search_result_as_list]
+    # --8<-- [start:search_result_as_pydantic]
+    tbl.search(np.random.randn(1536)).to_pydantic(LanceSchema)
+    # --8<-- [end:search_result_as_pydantic]
+
+
+@pytest.mark.asyncio
+async def test_vector_search_async():
+    # --8<-- [start:exhaustive_search_async]
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri)
+    data = [
+        {"vector": row, "item": f"item {i}"}
+        for i, row in enumerate(np.random.random((10_000, 1536)).astype("float32"))
+    ]
+    async_tbl = await async_db.create_table("vector_search_async", data=data)
+    (await async_tbl.query().nearest_to(np.random.random((1536))).limit(10).to_list())
+    # --8<-- [end:exhaustive_search_async]
+    # --8<-- [start:exhaustive_search_async_cosine]
+    (
+        await async_tbl.query()
+        .nearest_to(np.random.random((1536)))
+        .distance_type("cosine")
+        .limit(10)
+        .to_list()
+    )
+    # --8<-- [end:exhaustive_search_async_cosine]
+    # --8<-- [start:create_table_async_with_nested_schema]
+    # Let's add 100 sample rows to our dataset
+    data = [
+        LanceSchema(
+            id=f"id{i}",
+            vector=np.random.randn(1536),
+            payload=Document(
+                content=f"document{i}",
+                meta=Metadata(source=f"source{i % 10}", timestamp=datetime.now()),
+            ),
+        )
+        for i in range(100)
+    ]
+
+    async_tbl = await async_db.create_table("documents_async", data=data)
+    # --8<-- [end:create_table_async_with_nested_schema]
+    # --8<-- [start:search_result_async_as_pyarrow]
+    await async_tbl.query().nearest_to(np.random.randn(1536)).to_arrow()
+    # --8<-- [end:search_result_async_as_pyarrow]
+    # --8<-- [start:search_result_async_as_pandas]
+    await async_tbl.query().nearest_to(np.random.randn(1536)).to_pandas()
+    # --8<-- [end:search_result_async_as_pandas]
+    # --8<-- [start:search_result_async_as_list]
+    await async_tbl.query().nearest_to(np.random.randn(1536)).to_list()
+    # --8<-- [end:search_result_async_as_list]
+
+
+def test_fts_native():
+    # --8<-- [start:basic_fts]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+
+    table = db.create_table(
+        "my_table_fts",
+        data=[
+            {"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"},
+            {"vector": [5.9, 26.5], "text": "There are several kittens playing"},
+        ],
+    )
+
+    # passing `use_tantivy=False` to use lance FTS index
+    # `use_tantivy=True` by default
+    table.create_fts_index("text", use_tantivy=False)
+    table.search("puppy").limit(10).select(["text"]).to_list()
+    # [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]
+    # ...
+    # --8<-- [end:basic_fts]
+    # --8<-- [start:fts_config_stem]
+    table.create_fts_index("text", tokenizer_name="en_stem", replace=True)
+    # --8<-- [end:fts_config_stem]
+    # --8<-- [start:fts_config_folding]
+    table.create_fts_index(
+        "text",
+        use_tantivy=False,
+        language="French",
+        stem=True,
+        ascii_folding=True,
+        replace=True,
+    )
+    # --8<-- [end:fts_config_folding]
+    # --8<-- [start:fts_prefiltering]
+    table.search("puppy").limit(10).where("text='foo'", prefilter=True).to_list()
+    # --8<-- [end:fts_prefiltering]
+    # --8<-- [start:fts_postfiltering]
+    table.search("puppy").limit(10).where("text='foo'", prefilter=False).to_list()
+    # --8<-- [end:fts_postfiltering]
+    # --8<-- [start:fts_with_position]
+    table.create_fts_index("text", use_tantivy=False, with_position=True, replace=True)
+    # --8<-- [end:fts_with_position]
+    # --8<-- [start:fts_incremental_index]
+    table.add([{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"}])
+    table.optimize()
+    # --8<-- [end:fts_incremental_index]
+
+
+@pytest.mark.asyncio
+async def test_fts_native_async():
+    # --8<-- [start:basic_fts_async]
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri)
+
+    async_tbl = await async_db.create_table(
+        "my_table_fts_async",
+        data=[
+            {"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"},
+            {"vector": [5.9, 26.5], "text": "There are several kittens playing"},
+        ],
+    )
+
+    # async API uses our native FTS algorithm
+    await async_tbl.create_index("text", config=FTS())
+    await (
+        async_tbl.query().nearest_to_text("puppy").select(["text"]).limit(10).to_list()
+    )
+    # [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]
+    # ...
+    # --8<-- [end:basic_fts_async]
+    # --8<-- [start:fts_config_stem_async]
+    await async_tbl.create_index(
+        "text", config=FTS(language="English", stem=True, remove_stop_words=True)
+    )  # --8<-- [end:fts_config_stem_async]
+    # --8<-- [start:fts_config_folding_async]
+    await async_tbl.create_index(
+        "text", config=FTS(language="French", stem=True, ascii_folding=True)
+    )
+    # --8<-- [end:fts_config_folding_async]
+    # --8<-- [start:fts_prefiltering_async]
+    await (
+        async_tbl.query()
+        .nearest_to_text("puppy")
+        .limit(10)
+        .where("text='foo'")
+        .to_list()
+    )
+    # --8<-- [end:fts_prefiltering_async]
+    # --8<-- [start:fts_postfiltering_async]
+    await (
+        async_tbl.query()
+        .nearest_to_text("puppy")
+        .limit(10)
+        .where("text='foo'")
+        .postfilter()
+        .to_list()
+    )
+    # --8<-- [end:fts_postfiltering_async]
+    # --8<-- [start:fts_with_position_async]
+    await async_tbl.create_index("text", config=FTS(with_position=True))
+    # --8<-- [end:fts_with_position_async]
+    # --8<-- [start:fts_incremental_index_async]
+    await async_tbl.add([{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"}])
+    await async_tbl.optimize()
+    # --8<-- [end:fts_incremental_index_async]
+
+
+@pytest.mark.skip()
+def test_hybrid_search():
+    # --8<-- [start:import-openai]
+    import openai
+
+    # --8<-- [end:import-openai]
+    # --8<-- [start:openai-embeddings]
+    # Ingest embedding function in LanceDB table
+    # Configuring the environment variable OPENAI_API_KEY
+    if "OPENAI_API_KEY" not in os.environ:
+        # OR set the key here as a variable
+        openai.api_key = "sk-..."
+    embeddings = get_registry().get("openai").create()
+
+    # --8<-- [end:openai-embeddings]
+    # --8<-- [start:class-Documents]
+    class Documents(LanceModel):
+        vector: Vector(embeddings.ndims()) = embeddings.VectorField()
+        text: str = embeddings.SourceField()
+
+    # --8<-- [end:class-Documents]
+    # --8<-- [start:basic_hybrid_search]
+    data = [
+        {"text": "rebel spaceships striking from a hidden base"},
+        {"text": "have won their first victory against the evil Galactic Empire"},
+        {"text": "during the battle rebel spies managed to steal secret plans"},
+        {"text": "to the Empire's ultimate weapon the Death Star"},
+    ]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+    table = db.create_table("documents", schema=Documents)
+    # ingest docs with auto-vectorization
+    table.add(data)
+    # Create a fts index before the hybrid search
+    table.create_fts_index("text")
+    # hybrid search with default re-ranker
+    table.search("flower moon", query_type="hybrid").to_pandas()
+    # --8<-- [end:basic_hybrid_search]
+    # --8<-- [start:hybrid_search_pass_vector_text]
+    vector_query = [0.1, 0.2, 0.3, 0.4, 0.5]
+    text_query = "flower moon"
+    (
+        table.search(query_type="hybrid")
+        .vector(vector_query)
+        .text(text_query)
+        .limit(5)
+        .to_pandas()
+    )
+    # --8<-- [end:hybrid_search_pass_vector_text]
+
+
+@pytest.mark.skip
+async def test_hybrid_search_async():
+    import openai
+
+    # --8<-- [start:openai-embeddings]
+    # Ingest embedding function in LanceDB table
+    # Configuring the environment variable OPENAI_API_KEY
+    if "OPENAI_API_KEY" not in os.environ:
+        # OR set the key here as a variable
+        openai.api_key = "sk-..."
+    embeddings = get_registry().get("openai").create()
+
+    # --8<-- [end:openai-embeddings]
+    # --8<-- [start:class-Documents]
+    class Documents(LanceModel):
+        vector: Vector(embeddings.ndims()) = embeddings.VectorField()
+        text: str = embeddings.SourceField()
+
+    # --8<-- [end:class-Documents]
+    # --8<-- [start:basic_hybrid_search_async]
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri)
+    data = [
+        {"text": "rebel spaceships striking from a hidden base"},
+        {"text": "have won their first victory against the evil Galactic Empire"},
+        {"text": "during the battle rebel spies managed to steal secret plans"},
+        {"text": "to the Empire's ultimate weapon the Death Star"},
+    ]
+    async_tbl = await async_db.create_table("documents_async", schema=Documents)
+    # ingest docs with auto-vectorization
+    await async_tbl.add(data)
+    # Create a fts index before the hybrid search
+    await async_tbl.create_index("text", config=FTS())
+    text_query = "flower moon"
+    vector_query = embeddings.compute_query_embeddings(text_query)[0]
+    # hybrid search with default re-ranker
+    await (
+        async_tbl.query()
+        .nearest_to(vector_query)
+        .nearest_to_text(text_query)
+        .to_pandas()
+    )
+    # --8<-- [end:basic_hybrid_search_async]
+    # --8<-- [start:hybrid_search_pass_vector_text_async]
+    vector_query = [0.1, 0.2, 0.3, 0.4, 0.5]
+    text_query = "flower moon"
+    await (
+        async_tbl.query()
+        .nearest_to(vector_query)
+        .nearest_to_text(text_query)
+        .limit(5)
+        .to_pandas()
+    )
+    # --8<-- [end:hybrid_search_pass_vector_text_async]