update

Solves -  https://github.com/lancedb/lancedb/issues/968

.github/workflows/docs_test.yml

@@ -18,7 +18,7 @@ on:
 env:
   # Disable full debug symbol generation to speed up CI build and keep memory down
   # "1" means line tables only, which is useful for panic tracebacks.
-  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=native -C target-feature=+f16c,+avx2,+fma"
+  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=haswell -C target-feature=+f16c,+avx2,+fma"
   RUST_BACKTRACE: "1"
 
 jobs:
@@ -28,6 +28,8 @@ jobs:
     steps:
     - name: Checkout
       uses: actions/checkout@v4
+    - name: Print CPU capabilities
+      run: cat /proc/cpuinfo
     - name: Install dependecies needed for ubuntu
       run: |
         sudo apt install -y protobuf-compiler libssl-dev
@@ -39,7 +41,7 @@ jobs:
         cache: "pip"
         cache-dependency-path: "docs/test/requirements.txt"
     - name: Rust cache
-      uses: swatinem/rust-cache@v2        
+      uses: swatinem/rust-cache@v2
     - name: Build Python
       working-directory: docs/test
       run:
@@ -64,6 +66,8 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
+    - name: Print CPU capabilities
+      run: cat /proc/cpuinfo
     - name: Set up Node
       uses: actions/setup-node@v4
       with:

.github/workflows/node.yml

@@ -20,7 +20,8 @@ env:
   # "1" means line tables only, which is useful for panic tracebacks.
   #
   # Use native CPU to accelerate tests if possible, especially for f16
-  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=native -C target-feature=+f16c,+avx2,+fma"
+  # target-cpu=haswell fixes failing ci build
+  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=haswell -C target-feature=+f16c,+avx2,+fma"
   RUST_BACKTRACE: "1"
 
 jobs:

docs/mkdocs.yml

@@ -38,178 +38,196 @@ theme:
   custom_dir: overrides
 
 plugins:
-- search
-- autorefs
-- mkdocstrings:
-    handlers:
-      python:
-        paths: [../python]
-        options:
-          docstring_style: numpy
-          heading_level: 4
-          show_source: true
-          show_symbol_type_in_heading: true
-          show_signature_annotations: true
-          members_order: source
-        import:
-          # for cross references
-          - https://arrow.apache.org/docs/objects.inv
-          - https://pandas.pydata.org/docs/objects.inv
-- mkdocs-jupyter
-- ultralytics:
-    verbose: True
-    enabled: True
-    default_image: "assets/lancedb_and_lance.png" # Default image for all pages
-    add_image: True # Automatically add meta image
-    add_keywords: True # Add page keywords in the header tag
-    add_share_buttons: True # Add social share buttons
-    add_authors: False # Display page authors
-    add_desc: False
-    add_dates: False
+  - search
+  - autorefs
+  - mkdocstrings:
+      handlers:
+        python:
+          paths: [../python]
+          options:
+            docstring_style: numpy
+            heading_level: 3
+            show_source: true
+            show_symbol_type_in_heading: true
+            show_signature_annotations: true
+            show_root_heading: true
+            members_order: source
+          import:
+            # for cross references
+            - https://arrow.apache.org/docs/objects.inv
+            - https://pandas.pydata.org/docs/objects.inv
+  - mkdocs-jupyter
+  - ultralytics:
+      verbose: True
+      enabled: True
+      default_image: "assets/lancedb_and_lance.png" # Default image for all pages
+      add_image: True # Automatically add meta image
+      add_keywords: True # Add page keywords in the header tag
+      add_share_buttons: True # Add social share buttons
+      add_authors: False # Display page authors
+      add_desc: False
+      add_dates: False
 
 markdown_extensions:
-- admonition
-- footnotes
-- pymdownx.details
-- pymdownx.highlight:
-    anchor_linenums: true
-    line_spans: __span
-    pygments_lang_class: true
-- pymdownx.inlinehilite
-- pymdownx.snippets:
-    base_path: ..
-    dedent_subsections: true
-- pymdownx.superfences
-- pymdownx.tabbed:
-    alternate_style: true
-- md_in_html
-- attr_list
-
+  - admonition
+  - footnotes
+  - pymdownx.details
+  - pymdownx.highlight:
+      anchor_linenums: true
+      line_spans: __span
+      pygments_lang_class: true
+  - pymdownx.inlinehilite
+  - pymdownx.snippets:
+      base_path: ..
+      dedent_subsections: true
+  - pymdownx.superfences
+  - pymdownx.tabbed:
+      alternate_style: true
+  - md_in_html
+  - attr_list
+  
 nav:
-- Home:
-  - LanceDB: index.md
-  - 🏃🏼‍♂️ Quick start: basic.md
-  - 📚 Concepts:
-    - Vector search: concepts/vector_search.md
-    - Indexing: concepts/index_ivfpq.md
-    - Storage: concepts/storage.md
-    - Data management: concepts/data_management.md
-  - 🔨 Guides:
-    - Working with tables: guides/tables.md
-    - Building an ANN index: ann_indexes.md
-    - Vector Search: search.md
-    - Full-text search: fts.md
-    - Hybrid search:
-      - Overview: hybrid_search/hybrid_search.md
-      - Comparing Rerankers: hybrid_search/eval.md
-      - Airbnb financial data example: notebooks/hybrid_search.ipynb
-    - Filtering: sql.md
-    - Versioning & Reproducibility: notebooks/reproducibility.ipynb
-    - Configuring Storage: guides/storage.md
-  - 🧬 Managing embeddings:
-    - Overview: embeddings/index.md
-    - Embedding functions: embeddings/embedding_functions.md
-    - Available models: embeddings/default_embedding_functions.md
-    - User-defined embedding functions: embeddings/custom_embedding_function.md
-    - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
-    - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
-  - 🔌 Integrations:
-    - Tools and data formats: integrations/index.md
-    - Pandas and PyArrow: python/pandas_and_pyarrow.md
-    - Polars: python/polars_arrow.md
-    - DuckDB: python/duckdb.md
-    - LangChain 🔗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
-    - LangChain JS/TS 🔗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
-    - LlamaIndex 🦙: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
-    - Pydantic: python/pydantic.md
-    - Voxel51: integrations/voxel51.md
-    - PromptTools: integrations/prompttools.md
-  - 🎯 Examples:
-    - Overview: examples/index.md
-    - 🐍 Python:
-      - Overview: examples/examples_python.md
+  - Home:
+      - LanceDB: index.md
+      - 🏃🏼‍♂️ Quick start: basic.md
+      - 📚 Concepts:
+          - Vector search: concepts/vector_search.md
+          - Indexing: concepts/index_ivfpq.md
+          - Storage: concepts/storage.md
+          - Data management: concepts/data_management.md
+      - 🔨 Guides:
+          - Working with tables: guides/tables.md
+          - Building an ANN index: ann_indexes.md
+          - Vector Search: search.md
+          - Full-text search: fts.md
+          - Hybrid search:
+              - Overview: hybrid_search/hybrid_search.md
+              - Comparing Rerankers: hybrid_search/eval.md
+              - Airbnb financial data example: notebooks/hybrid_search.ipynb
+          - Reranking:
+              - Quickstart: reranking/index.md
+              - Cohere Reranker: reranking/cohere.md
+              - Linear Combination Reranker: reranking/linear_combination.md
+              - Cross Encoder Reranker: reranking/cross_encoder.md
+              - ColBERT Reranker: reranking/colbert.md
+              - OpenAI Reranker: reranking/openai.md
+              - Building Custom Rerankers: reranking/custom_reranker.md
+          - Filtering: sql.md
+          - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+          - Configuring Storage: guides/storage.md
+          - Sync -> Async Migration Guide: migration.md
+      - 🧬 Managing embeddings:
+          - Overview: embeddings/index.md
+          - Embedding functions: embeddings/embedding_functions.md
+          - Available models: embeddings/default_embedding_functions.md
+          - User-defined embedding functions: embeddings/custom_embedding_function.md
+          - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
+          - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
+      - 🔌 Integrations:
+          - Tools and data formats: integrations/index.md
+          - Pandas and PyArrow: python/pandas_and_pyarrow.md
+          - Polars: python/polars_arrow.md
+          - DuckDB: python/duckdb.md
+          - LangChain 🔗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
+          - LangChain JS/TS 🔗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
+          - LlamaIndex 🦙: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
+          - Pydantic: python/pydantic.md
+          - Voxel51: integrations/voxel51.md
+          - PromptTools: integrations/prompttools.md
+      - 🎯 Examples:
+          - Overview: examples/index.md
+          - 🐍 Python:
+              - Overview: examples/examples_python.md
+              - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
+              - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
+              - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
+              - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
+              - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
+              - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
+          - 👾 JavaScript:
+              - Overview: examples/examples_js.md
+              - Serverless Website Chatbot: examples/serverless_website_chatbot.md
+              - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
+              - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
+          - 🦀 Rust:
+              - Overview: examples/examples_rust.md
+      - 🔧 CLI & Config: cli_config.md
+      - 💭 FAQs: faq.md
+      - ⚙️ API reference:
+          - 🐍 Python: python/python.md
+          - 👾 JavaScript: javascript/modules.md
+          - 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
+      - ☁️ LanceDB Cloud:
+          - Overview: cloud/index.md
+          - API reference:
+              - 🐍 Python: python/saas-python.md
+              - 👾 JavaScript: javascript/saas-modules.md
+
+  - Quick start: basic.md
+  - Concepts:
+      - Vector search: concepts/vector_search.md
+      - Indexing: concepts/index_ivfpq.md
+      - Storage: concepts/storage.md
+      - Data management: concepts/data_management.md
+  - Guides:
+      - Working with tables: guides/tables.md
+      - Building an ANN index: ann_indexes.md
+      - Vector Search: search.md
+      - Full-text search: fts.md
+      - Hybrid search:
+          - Overview: hybrid_search/hybrid_search.md
+          - Comparing Rerankers: hybrid_search/eval.md
+          - Airbnb financial data example: notebooks/hybrid_search.ipynb
+      - Reranking:
+          - Quickstart: reranking/index.md
+          - Cohere Reranker: reranking/cohere.md
+          - Linear Combination Reranker: reranking/linear_combination.md
+          - Cross Encoder Reranker: reranking/cross_encoder.md
+          - ColBERT Reranker: reranking/colbert.md
+          - OpenAI Reranker: reranking/openai.md
+          - Building Custom Rerankers: reranking/custom_reranker.md
+      - Filtering: sql.md
+      - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+      - Configuring Storage: guides/storage.md
+      - Sync -> Async Migration Guide: migration.md
+  - Managing Embeddings:
+      - Overview: embeddings/index.md
+      - Embedding functions: embeddings/embedding_functions.md
+      - Available models: embeddings/default_embedding_functions.md
+      - User-defined embedding functions: embeddings/custom_embedding_function.md
+      - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
+      - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
+  - Integrations:
+      - Overview: integrations/index.md
+      - Pandas and PyArrow: python/pandas_and_pyarrow.md
+      - Polars: python/polars_arrow.md
+      - DuckDB: python/duckdb.md
+      - LangChain 🦜️🔗↗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
+      - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
+      - LlamaIndex 🦙↗: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
+      - Pydantic: python/pydantic.md
+      - Voxel51: integrations/voxel51.md
+      - PromptTools: integrations/prompttools.md
+  - Examples:
+      - examples/index.md
       - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
       - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
       - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
-      - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
       - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
       - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
-    - 👾 JavaScript:
-      - Overview: examples/examples_js.md
-      - Serverless Website Chatbot: examples/serverless_website_chatbot.md
-      - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
+      - YouTube Transcript Search (JS): examples/youtube_transcript_bot_with_nodejs.md
+      - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
       - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
-    - 🦀 Rust:
-      - Overview: examples/examples_rust.md
-  - 🔧 CLI & Config: cli_config.md
-  - 💭 FAQs: faq.md
-  - ⚙️ API reference:
-    - 🐍 Python: python/python.md
-    - 👾 JavaScript: javascript/modules.md
-    - 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
-  - ☁️ LanceDB Cloud:
-    - Overview: cloud/index.md
-    - API reference:
-      - 🐍 Python: python/saas-python.md
-      - 👾 JavaScript: javascript/saas-modules.md
-
-
-- Quick start: basic.md
-- Concepts:
-    - Vector search: concepts/vector_search.md
-    - Indexing: concepts/index_ivfpq.md
-    - Storage: concepts/storage.md
-    - Data management: concepts/data_management.md
-- Guides:
-    - Working with tables: guides/tables.md
-    - Building an ANN index: ann_indexes.md
-    - Vector Search: search.md
-    - Full-text search: fts.md
-    - Hybrid search:
-      - Overview: hybrid_search/hybrid_search.md
-      - Comparing Rerankers: hybrid_search/eval.md
-      - Airbnb financial data example: notebooks/hybrid_search.ipynb
-    - Filtering: sql.md
-    - Versioning & Reproducibility: notebooks/reproducibility.ipynb
-    - Configuring Storage: guides/storage.md
-- Managing Embeddings:
-  - Overview: embeddings/index.md
-  - Embedding functions: embeddings/embedding_functions.md
-  - Available models: embeddings/default_embedding_functions.md
-  - User-defined embedding functions: embeddings/custom_embedding_function.md
-  - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
-  - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
-- Integrations:
-  - Overview: integrations/index.md
-  - Pandas and PyArrow: python/pandas_and_pyarrow.md
-  - Polars: python/polars_arrow.md
-  - DuckDB : python/duckdb.md
-  - LangChain 🦜️🔗↗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
-  - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
-  - LlamaIndex 🦙↗: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
-  - Pydantic: python/pydantic.md
-  - Voxel51: integrations/voxel51.md
-  - PromptTools: integrations/prompttools.md
-- Examples:
-  - examples/index.md
-  - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
-  - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
-  - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
-  - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
-  - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
-  - YouTube Transcript Search (JS): examples/youtube_transcript_bot_with_nodejs.md
-  - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
-  - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
-- API reference:
-  - Overview: api_reference.md
-  - Python: python/python.md
-  - Javascript: javascript/modules.md
-  - Rust: https://docs.rs/lancedb/latest/lancedb/index.html
-- LanceDB Cloud:
-    - Overview: cloud/index.md
-    - API reference:
-      - 🐍 Python: python/saas-python.md
-      - 👾 JavaScript: javascript/saas-modules.md
+  - API reference:
+      - Overview: api_reference.md
+      - Python: python/python.md
+      - Javascript: javascript/modules.md
+      - Rust: https://docs.rs/lancedb/latest/lancedb/index.html
+  - LanceDB Cloud:
+      - Overview: cloud/index.md
+      - API reference:
+          - 🐍 Python: python/saas-python.md
+          - 👾 JavaScript: javascript/saas-modules.md
 
 extra_css:
   - styles/global.css
@@ -221,4 +239,4 @@ extra_javascript:
 extra:
   analytics:
     provider: google
-    property: G-B7NFM40W74
+    property: G-B7NFM40W74

docs/src/basic.md

@@ -48,11 +48,20 @@
 
 === "Python"
 
-      ```python
-      import lancedb
-      uri = "data/sample-lancedb"
-      db = lancedb.connect(uri)
-      ```
+    ```python
+    --8<-- "python/python/tests/docs/test_basic.py:imports"
+    --8<-- "python/python/tests/docs/test_basic.py:connect"
+
+    --8<-- "python/python/tests/docs/test_basic.py:connect_async"
+    ```
+
+    !!! note "Asynchronous Python API"
+
+        The asynchronous Python API is new and has some slight differences compared
+        to the synchronous API.  Feel free to start using the asynchronous version.
+        Once all features have migrated we will start to move the synchronous API to
+        use the same syntax as the asynchronous API.  To help with this migration we
+        have created a [migration guide](migration.md) detailing the differences.
 
 === "Typescript"
 
@@ -82,15 +91,14 @@ If you need a reminder of the uri, you can call `db.uri()`.
 ### Create a table from initial data
 
 If you have data to insert into the table at creation time, you can simultaneously create a
-table and insert the data into it.  The schema of the data will be used as the schema of the
+table and insert the data into it. The schema of the data will be used as the schema of the
 table.
 
 === "Python"
 
     ```python
-    tbl = db.create_table("my_table",
-                    data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-                          {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
+    --8<-- "python/python/tests/docs/test_basic.py:create_table"
+    --8<-- "python/python/tests/docs/test_basic.py:create_table_async"
     ```
 
     If the table already exists, LanceDB will raise an error by default.
@@ -100,10 +108,8 @@ table.
     You can also pass in a pandas DataFrame directly:
 
     ```python
-    import pandas as pd
-    df = pd.DataFrame([{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-                       {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
-    tbl = db.create_table("table_from_df", data=df)
+    --8<-- "python/python/tests/docs/test_basic.py:create_table_pandas"
+    --8<-- "python/python/tests/docs/test_basic.py:create_table_async_pandas"
     ```
 
 === "Typescript"
@@ -138,15 +144,14 @@ table.
 
 Sometimes you may not have the data to insert into the table at creation time.
 In this case, you can create an empty table and specify the schema, so that you can add
-data to the table at a later time (as long as it conforms to the schema).  This is
+data to the table at a later time (as long as it conforms to the schema). This is
 similar to a `CREATE TABLE` statement in SQL.
 
 === "Python"
 
       ```python
-      import pyarrow as pa
-      schema = pa.schema([pa.field("vector", pa.list_(pa.float32(), list_size=2))])
-      tbl = db.create_table("empty_table", schema=schema)
+      --8<-- "python/python/tests/docs/test_basic.py:create_empty_table"
+      --8<-- "python/python/tests/docs/test_basic.py:create_empty_table_async"
       ```
 
 === "Typescript"
@@ -168,7 +173,8 @@ Once created, you can open a table as follows:
 === "Python"
 
     ```python
-    tbl = db.open_table("my_table")
+    --8<-- "python/python/tests/docs/test_basic.py:open_table"
+    --8<-- "python/python/tests/docs/test_basic.py:open_table_async"
     ```
 
 === "Typescript"
@@ -188,7 +194,8 @@ If you forget the name of your table, you can always get a listing of all table
 === "Python"
 
     ```python
-    print(db.table_names())
+    --8<-- "python/python/tests/docs/test_basic.py:table_names"
+    --8<-- "python/python/tests/docs/test_basic.py:table_names_async"
     ```
 
 === "Javascript"
@@ -210,15 +217,8 @@ After a table has been created, you can always add more data to it as follows:
 === "Python"
 
     ```python
-
-    # Option 1: Add a list of dicts to a table
-    data = [{"vector": [1.3, 1.4], "item": "fizz", "price": 100.0},
-            {"vector": [9.5, 56.2], "item": "buzz", "price": 200.0}]
-    tbl.add(data)
-
-    # Option 2: Add a pandas DataFrame to a table
-    df = pd.DataFrame(data)
-    tbl.add(data)
+    --8<-- "python/python/tests/docs/test_basic.py:add_data"
+    --8<-- "python/python/tests/docs/test_basic.py:add_data_async"
     ```
 
 === "Typescript"
@@ -240,7 +240,8 @@ Once you've embedded the query, you can find its nearest neighbors as follows:
 === "Python"
 
     ```python
-    tbl.search([100, 100]).limit(2).to_pandas()
+    --8<-- "python/python/tests/docs/test_basic.py:vector_search"
+    --8<-- "python/python/tests/docs/test_basic.py:vector_search_async"
     ```
 
     This returns a pandas DataFrame with the results.
@@ -274,7 +275,8 @@ LanceDB allows you to create an ANN index on a table as follows:
 === "Python"
 
     ```py
-    tbl.create_index()
+    --8<-- "python/python/tests/docs/test_basic.py:create_index"
+    --8<-- "python/python/tests/docs/test_basic.py:create_index_async"
     ```
 
 === "Typescript"
@@ -286,15 +288,15 @@ LanceDB allows you to create an ANN index on a table as follows:
 === "Rust"
 
     ```rust
-     --8<-- "rust/lancedb/examples/simple.rs:create_index"
+    --8<-- "rust/lancedb/examples/simple.rs:create_index"
     ```
 
 !!! note "Why do I need to create an index manually?"
-    LanceDB does not automatically create the ANN index for two reasons. The first is that it's optimized
-    for really fast retrievals via a disk-based index, and the second is that data and query workloads can
-    be very diverse, so there's no one-size-fits-all index configuration. LanceDB provides many parameters
-    to fine-tune index size, query latency and accuracy. See the section on
-    [ANN indexes](ann_indexes.md) for more details.
+LanceDB does not automatically create the ANN index for two reasons. The first is that it's optimized
+for really fast retrievals via a disk-based index, and the second is that data and query workloads can
+be very diverse, so there's no one-size-fits-all index configuration. LanceDB provides many parameters
+to fine-tune index size, query latency and accuracy. See the section on
+[ANN indexes](ann_indexes.md) for more details.
 
 ## Delete rows from a table
 
@@ -305,7 +307,8 @@ This can delete any number of rows that match the filter.
 === "Python"
 
     ```python
-    tbl.delete('item = "fizz"')
+    --8<-- "python/python/tests/docs/test_basic.py:delete_rows"
+    --8<-- "python/python/tests/docs/test_basic.py:delete_rows_async"
     ```
 
 === "Typescript"
@@ -322,7 +325,7 @@ This can delete any number of rows that match the filter.
 
 The deletion predicate is a SQL expression that supports the same expressions
 as the `where()` clause (`only_if()` in Rust) on a search. They can be as
-simple or complex as needed.  To see what expressions are supported, see the
+simple or complex as needed. To see what expressions are supported, see the
 [SQL filters](sql.md) section.
 
 === "Python"
@@ -344,7 +347,8 @@ Use the `drop_table()` method on the database to remove a table.
 === "Python"
 
       ```python
-      db.drop_table("my_table")
+      --8<-- "python/python/tests/docs/test_basic.py:drop_table"
+      --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
       ```
 
       This permanently removes the table and is not recoverable, unlike deleting rows.

docs/src/embeddings/default_embedding_functions.md

@@ -19,27 +19,163 @@ Allows you to set parameters when registering a `sentence-transformers` object.
 | `normalize` | `bool` | `True` | Whether to normalize the input text before feeding it to the model |
 
 
-```python
-db = lancedb.connect("/tmp/db")
-registry = EmbeddingFunctionRegistry.get_instance()
-func = registry.get("sentence-transformers").create(device="cpu")
+??? "Check out available sentence-transformer models here!"
+    ```markdown
+    - sentence-transformers/all-MiniLM-L12-v2
+    - sentence-transformers/paraphrase-mpnet-base-v2
+    - sentence-transformers/gtr-t5-base
+    - sentence-transformers/LaBSE
+    - sentence-transformers/all-MiniLM-L6-v2
+    - sentence-transformers/bert-base-nli-max-tokens
+    - sentence-transformers/bert-base-nli-mean-tokens
+    - sentence-transformers/bert-base-nli-stsb-mean-tokens
+    - sentence-transformers/bert-base-wikipedia-sections-mean-tokens
+    - sentence-transformers/bert-large-nli-cls-token
+    - sentence-transformers/bert-large-nli-max-tokens
+    - sentence-transformers/bert-large-nli-mean-tokens
+    - sentence-transformers/bert-large-nli-stsb-mean-tokens
+    - sentence-transformers/distilbert-base-nli-max-tokens
+    - sentence-transformers/distilbert-base-nli-mean-tokens
+    - sentence-transformers/distilbert-base-nli-stsb-mean-tokens
+    - sentence-transformers/distilroberta-base-msmarco-v1
+    - sentence-transformers/distilroberta-base-msmarco-v2
+    - sentence-transformers/nli-bert-base-cls-pooling
+    - sentence-transformers/nli-bert-base-max-pooling
+    - sentence-transformers/nli-bert-base
+    - sentence-transformers/nli-bert-large-cls-pooling
+    - sentence-transformers/nli-bert-large-max-pooling
+    - sentence-transformers/nli-bert-large
+    - sentence-transformers/nli-distilbert-base-max-pooling
+    - sentence-transformers/nli-distilbert-base
+    - sentence-transformers/nli-roberta-base
+    - sentence-transformers/nli-roberta-large
+    - sentence-transformers/roberta-base-nli-mean-tokens
+    - sentence-transformers/roberta-base-nli-stsb-mean-tokens
+    - sentence-transformers/roberta-large-nli-mean-tokens
+    - sentence-transformers/roberta-large-nli-stsb-mean-tokens
+    - sentence-transformers/stsb-bert-base
+    - sentence-transformers/stsb-bert-large
+    - sentence-transformers/stsb-distilbert-base
+    - sentence-transformers/stsb-roberta-base
+    - sentence-transformers/stsb-roberta-large
+    - sentence-transformers/xlm-r-100langs-bert-base-nli-mean-tokens
+    - sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens
+    - sentence-transformers/xlm-r-base-en-ko-nli-ststb
+    - sentence-transformers/xlm-r-bert-base-nli-mean-tokens
+    - sentence-transformers/xlm-r-bert-base-nli-stsb-mean-tokens
+    - sentence-transformers/xlm-r-large-en-ko-nli-ststb
+    - sentence-transformers/bert-base-nli-cls-token
+    - sentence-transformers/all-distilroberta-v1
+    - sentence-transformers/multi-qa-MiniLM-L6-dot-v1
+    - sentence-transformers/multi-qa-distilbert-cos-v1
+    - sentence-transformers/multi-qa-distilbert-dot-v1
+    - sentence-transformers/multi-qa-mpnet-base-cos-v1
+    - sentence-transformers/multi-qa-mpnet-base-dot-v1
+    - sentence-transformers/nli-distilroberta-base-v2
+    - sentence-transformers/all-MiniLM-L6-v1
+    - sentence-transformers/all-mpnet-base-v1
+    - sentence-transformers/all-mpnet-base-v2
+    - sentence-transformers/all-roberta-large-v1
+    - sentence-transformers/allenai-specter
+    - sentence-transformers/average_word_embeddings_glove.6B.300d
+    - sentence-transformers/average_word_embeddings_glove.840B.300d
+    - sentence-transformers/average_word_embeddings_komninos
+    - sentence-transformers/average_word_embeddings_levy_dependency
+    - sentence-transformers/clip-ViT-B-32-multilingual-v1
+    - sentence-transformers/clip-ViT-B-32
+    - sentence-transformers/distilbert-base-nli-stsb-quora-ranking
+    - sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking
+    - sentence-transformers/distilroberta-base-paraphrase-v1
+    - sentence-transformers/distiluse-base-multilingual-cased-v1
+    - sentence-transformers/distiluse-base-multilingual-cased-v2
+    - sentence-transformers/distiluse-base-multilingual-cased
+    - sentence-transformers/facebook-dpr-ctx_encoder-multiset-base
+    - sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base
+    - sentence-transformers/facebook-dpr-question_encoder-multiset-base
+    - sentence-transformers/facebook-dpr-question_encoder-single-nq-base
+    - sentence-transformers/gtr-t5-large
+    - sentence-transformers/gtr-t5-xl
+    - sentence-transformers/gtr-t5-xxl
+    - sentence-transformers/msmarco-MiniLM-L-12-v3
+    - sentence-transformers/msmarco-MiniLM-L-6-v3
+    - sentence-transformers/msmarco-MiniLM-L12-cos-v5
+    - sentence-transformers/msmarco-MiniLM-L6-cos-v5
+    - sentence-transformers/msmarco-bert-base-dot-v5
+    - sentence-transformers/msmarco-bert-co-condensor
+    - sentence-transformers/msmarco-distilbert-base-dot-prod-v3
+    - sentence-transformers/msmarco-distilbert-base-tas-b
+    - sentence-transformers/msmarco-distilbert-base-v2
+    - sentence-transformers/msmarco-distilbert-base-v3
+    - sentence-transformers/msmarco-distilbert-base-v4
+    - sentence-transformers/msmarco-distilbert-cos-v5
+    - sentence-transformers/msmarco-distilbert-dot-v5
+    - sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-lng-aligned
+    - sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-trained-scratch
+    - sentence-transformers/msmarco-distilroberta-base-v2
+    - sentence-transformers/msmarco-roberta-base-ance-firstp
+    - sentence-transformers/msmarco-roberta-base-v2
+    - sentence-transformers/msmarco-roberta-base-v3
+    - sentence-transformers/multi-qa-MiniLM-L6-cos-v1
+    - sentence-transformers/nli-mpnet-base-v2
+    - sentence-transformers/nli-roberta-base-v2
+    - sentence-transformers/nq-distilbert-base-v1
+    - sentence-transformers/paraphrase-MiniLM-L12-v2
+    - sentence-transformers/paraphrase-MiniLM-L3-v2
+    - sentence-transformers/paraphrase-MiniLM-L6-v2
+    - sentence-transformers/paraphrase-TinyBERT-L6-v2
+    - sentence-transformers/paraphrase-albert-base-v2
+    - sentence-transformers/paraphrase-albert-small-v2
+    - sentence-transformers/paraphrase-distilroberta-base-v1
+    - sentence-transformers/paraphrase-distilroberta-base-v2
+    - sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+    - sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+    - sentence-transformers/paraphrase-xlm-r-multilingual-v1
+    - sentence-transformers/quora-distilbert-base
+    - sentence-transformers/quora-distilbert-multilingual
+    - sentence-transformers/sentence-t5-base
+    - sentence-transformers/sentence-t5-large
+    - sentence-transformers/sentence-t5-xxl
+    - sentence-transformers/sentence-t5-xl
+    - sentence-transformers/stsb-distilroberta-base-v2
+    - sentence-transformers/stsb-mpnet-base-v2
+    - sentence-transformers/stsb-roberta-base-v2
+    - sentence-transformers/stsb-xlm-r-multilingual
+    - sentence-transformers/xlm-r-distilroberta-base-paraphrase-v1
+    - sentence-transformers/clip-ViT-L-14
+    - sentence-transformers/clip-ViT-B-16
+    - sentence-transformers/use-cmlm-multilingual
+    - sentence-transformers/all-MiniLM-L12-v1
+    ```
 
-class Words(LanceModel):
-    text: str = func.SourceField()
-    vector: Vector(func.ndims()) = func.VectorField()
+!!! info
+    You can also load many other model architectures from the library. For example models from sources such as BAAI, nomic, salesforce research, etc.
+    See this HF hub page for all [supported models](https://huggingface.co/models?library=sentence-transformers).
 
-table = db.create_table("words", schema=Words)
-table.add(
-    [
-        {"text": "hello world"}
-        {"text": "goodbye world"}
-    ]
-)
+!!! note "BAAI Embeddings example"
+    Here is an example that uses BAAI embedding model from the HuggingFace Hub [supported models](https://huggingface.co/models?library=sentence-transformers)
+    ```python
+    db = lancedb.connect("/tmp/db")
+    registry = EmbeddingFunctionRegistry.get_instance()
+    model = registry.get("sentence-transformers").create(name="BAAI/bge-small-en-v1.5", device="cpu")
+
+    class Words(LanceModel):
+        text: str = model.SourceField()
+        vector: Vector(model.ndims()) = model.VectorField()
+
+    table = db.create_table("words", schema=Words)
+    table.add(
+        [
+            {"text": "hello world"}
+            {"text": "goodbye world"}
+        ]
+    )
+
+    query = "greetings"
+    actual = table.search(query).limit(1).to_pydantic(Words)[0]
+    print(actual.text)
+    ```
+Visit sentence-transformers [HuggingFace HUB](https://huggingface.co/sentence-transformers) page for more information on the available models.
 
-query = "greetings"
-actual = table.search(query).limit(1).to_pydantic(Words)[0]
-print(actual.text)
-```
 
 ### OpenAI embeddings
 LanceDB registers the OpenAI embeddings function in the registry by default, as `openai`. Below are the parameters that you can customize when creating the instances:

docs/src/hybrid_search/hybrid_search.md

@@ -5,6 +5,9 @@ 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 .
 
+!!! note
+    You need to create a full-text search index before performing a hybrid search. You can create a full-text search index using the `create_fts_index()` method of the table object.
+
 ```python
 import os
 
@@ -55,188 +58,7 @@ By default, LanceDB uses `LinearCombinationReranker(weight=0.7)` to combine and
 
 
 ## Available Rerankers
-LanceDB provides a number of re-rankers out of the box. You can use any of these re-rankers by passing them to the `rerank()` method. Here's a list of available re-rankers:
+LanceDB provides a number of re-rankers out of the box. You can use any of these re-rankers by passing them to the `rerank()` method. Visit the [rerankers](../reranking/) page for more information on each re-ranker.
 
-### Linear Combination Reranker
-This is the default re-ranker used by LanceDB. It combines the results of semantic and full-text search using a linear combination of the scores. The weights for the linear combination can be specified. It defaults to 0.7, i.e, 70% weight for semantic search and 30% weight for full-text search.
-
-
-```python
-from lancedb.rerankers import LinearCombinationReranker
-
-reranker = LinearCombinationReranker(weight=0.3) # Use 0.3 as the weight for vector search
-
-results = table.search("rebel", query_type="hybrid").rerank(reranker=reranker).to_pandas()
-```
-
-### Arguments
-----------------
-* `weight`: `float`, default `0.7`:
-    The weight to use for the semantic search score. The weight for the full-text search score is `1 - weights`.
-* `fill`: `float`, default `1.0`:
-        The score to give to results that are only in one of the two result sets.This is treated as penalty, so a higher value means a lower score.
-        TODO: We should just hardcode this-- its pretty confusing as we invert scores to calculate final score
-* `return_score` : str, default `"relevance"`
-        options are "relevance" or "all"
-        The type of score to return. If "relevance", will return only the `_relevance_score. If "all", will return all scores from the vector and FTS search along with the relevance score.
-
-### Cohere Reranker
-This re-ranker uses the [Cohere](https://cohere.ai/) API to combine the results of semantic and full-text search. You can use this re-ranker by passing `CohereReranker()` to the `rerank()` method. Note that you'll need to set the `COHERE_API_KEY` environment variable to use this re-ranker.
-
-```python
-from lancedb.rerankers import CohereReranker
-
-reranker = CohereReranker()
-
-results = table.search("vampire weekend", query_type="hybrid").rerank(reranker=reranker).to_pandas()
-```
-
-### Arguments
-----------------
-* `model_name` : str, default `"rerank-english-v2.0"`
-        The name of the cross encoder model to use. Available cohere models are:
-        - rerank-english-v2.0
-        - rerank-multilingual-v2.0
-* `column` : str, default `"text"`
-        The name of the column to use as input to the cross encoder model.
-* `top_n` : str, default `None`
-        The number of results to return. If None, will return all results.
-
-!!! Note
-    Only returns `_relevance_score`. Does not support `return_score = "all"`.
-
-### Cross Encoder Reranker
-This reranker uses the [Sentence Transformers](https://www.sbert.net/) library to combine the results of semantic and full-text search. You can use it by passing `CrossEncoderReranker()` to the `rerank()` method.
-
-```python
-from lancedb.rerankers import CrossEncoderReranker
-
-reranker = CrossEncoderReranker()
-
-results = table.search("harmony hall", query_type="hybrid").rerank(reranker=reranker).to_pandas()
-```
-
-
-### Arguments
-----------------
-* `model` : str, default `"cross-encoder/ms-marco-TinyBERT-L-6"`
-        The name of the cross encoder model to use. Available cross encoder models can be found [here](https://www.sbert.net/docs/pretrained_cross-encoders.html)
-* `column` : str, default `"text"`
-        The name of the column to use as input to the cross encoder model.
-* `device` : str, default `None`
-        The device to use for the cross encoder model. If None, will use "cuda" if available, otherwise "cpu".
-
-!!! Note
-    Only returns `_relevance_score`. Does not support `return_score = "all"`.
-
-
-### ColBERT Reranker
-This reranker uses the ColBERT model to combine the results of semantic and full-text search. You can use it by passing `ColbertrReranker()` to the `rerank()` method. 
-
-ColBERT reranker model calculates relevance of given docs against the query and don't take existing fts and vector search scores into account, so it currently only supports `return_score="relevance"`. By default, it looks for `text` column to rerank the results. But you can specify the column name to use as input to the cross encoder model as described below.
-
-```python
-from lancedb.rerankers import ColbertReranker
-
-reranker = ColbertReranker()
-
-results = table.search("harmony hall", query_type="hybrid").rerank(reranker=reranker).to_pandas()
-```
-
-### Arguments
-----------------
-* `model_name` : `str`, default `"colbert-ir/colbertv2.0"`
-        The name of the cross encoder model to use.
-* `column` : `str`, default `"text"`
-        The name of the column to use as input to the cross encoder model.
-* `return_score` : `str`, default `"relevance"`
-        options are `"relevance"` or `"all"`. Only `"relevance"` is supported for now.
-
-!!! Note
-    Only returns `_relevance_score`. Does not support `return_score = "all"`.
-
-### OpenAI Reranker
-This reranker uses the OpenAI API to combine the results of semantic and full-text search. You can use it by passing `OpenaiReranker()` to the `rerank()` method.
-
-!!! Note
-    This prompts chat model to rerank results which is not a dedicated reranker model. This should be treated as experimental.
-
-!!! Tip
-    - You might run out of token limit so set the search `limits` based on your token limit.
-    - It is recommended to use gpt-4-turbo-preview, the default model, older models might lead to undesired behaviour
-
-```python
-from lancedb.rerankers import OpenaiReranker
-
-reranker = OpenaiReranker()
-
-results = table.search("harmony hall", query_type="hybrid").rerank(reranker=reranker).to_pandas()
-```
-
-### Arguments
-----------------
-* `model_name` : `str`, default `"gpt-4-turbo-preview"`
-    The name of the cross encoder model to use.
-* `column` : `str`, default `"text"`
-    The name of the column to use as input to the cross encoder model.
-* `return_score` : `str`, default `"relevance"`
-    options are "relevance" or "all". Only "relevance" is supported for now.
-* `api_key` : `str`, default `None`
-    The API key to use. If None, will use the OPENAI_API_KEY environment variable.
-
-
-## Building Custom Rerankers
-You can build your own custom reranker by subclassing the `Reranker` class and implementing the `rerank_hybrid()` method. Here's an example of a custom reranker that combines the results of semantic and full-text search using a linear combination of the scores.
-
-The `Reranker` base interface comes with a `merge_results()` method that can be used to combine the results of semantic and full-text search. This is a vanilla merging algorithm that simply concatenates the results and removes the duplicates without taking the scores into consideration. It only keeps the first copy of the row encountered. This works well in cases that don't require the scores of semantic and full-text search to combine the results. If you want to use the scores or want to support `return_score="all"`, you'll need to implement your own merging algorithm.
-
-```python
-
-from lancedb.rerankers import Reranker
-import pyarrow as pa
-
-class MyReranker(Reranker):
-    def __init__(self, param1, param2, ..., return_score="relevance"):
-        super().__init__(return_score)
-        self.param1 = param1
-        self.param2 = param2
-    
-    def rerank_hybrid(self, query: str, vector_results: pa.Table, fts_results: pa.Table):
-        # Use the built-in merging function
-        combined_result = self.merge_results(vector_results, fts_results)
-        
-        # Do something with the combined results
-        # ...
-
-        # Return the combined results
-        return combined_result
-
-```
-
-### Example of a Custom Reranker
-For the sake of simplicity let's build custom reranker that just enchances the Cohere Reranker by accepting a filter query, and accept other CohereReranker params as kwags.
-
-```python
-
-from typing import List, Union
-import pandas as pd
-from lancedb.rerankers import CohereReranker
-
-class MofidifiedCohereReranker(CohereReranker):
-    def __init__(self, filters: Union[str, List[str]], **kwargs):
-        super().__init__(**kwargs)
-        filters = filters if isinstance(filters, list) else [filters]
-        self.filters = filters
-
-    def rerank_hybrid(self, query: str, vector_results: pa.Table, fts_results: pa.Table)-> pa.Table:
-        combined_result = super().rerank_hybrid(query, vector_results, fts_results)
-        df = combined_result.to_pandas()
-        for filter in self.filters:
-            df = df.query("not text.str.contains(@filter)")
-
-        return pa.Table.from_pandas(df)
-
-```
-
-!!! tip
-    The `vector_results` and `fts_results` are pyarrow tables. You can convert them to pandas dataframes using `to_pandas()` method and perform any operations you want. After you are done, you can convert the dataframe back to pyarrow table using `pa.Table.from_pandas()` method and return it.
+## Custom Rerankers
+You can also create custom rerankers by extending the base `Reranker` class. The custom reranker should implement the `rerank` method that takes a list of search results and returns a reranked list of search results. Visit the [custom rerankers](../reranking/custom_reranker.md) page for more information on creating custom rerankers.

docs/src/migration.md

@@ -0,0 +1,76 @@
+# Rust-backed Client Migration Guide
+
+In an effort to ensure all clients have the same set of capabilities we have begun migrating the
+python and node clients onto a common Rust base library. In python, this new client is part of
+the same lancedb package, exposed as an asynchronous client. Once the asynchronous client has
+reached full functionality we will begin migrating the synchronous library to be a thin wrapper
+around the asynchronous client.
+
+This guide describes the differences between the two APIs and will hopefully assist users
+that would like to migrate to the new API.
+
+## Closeable Connections
+
+The Connection now has a `close` method. You can call this when
+you are done with the connection to eagerly free resources. Currently
+this is limited to freeing/closing the HTTP connection for remote
+connections. In the future we may add caching or other resources to
+native connections so this is probably a good practice even if you
+aren't using remote connections.
+
+In addition, the connection can be used as a context manager which may
+be a more convenient way to ensure the connection is closed.
+
+```python
+import lancedb
+
+async def my_async_fn():
+    with await lancedb.connect_async("my_uri") as db:
+        print(await db.table_names())
+```
+
+It is not mandatory to call the `close` method. If you do not call it
+then the connection will be closed when the object is garbage collected.
+
+## Closeable Table
+
+The Table now also has a `close` method, similar to the connection. This
+can be used to eagerly free the cache used by a Table object. Similar to
+the connection, it can be used as a context manager and it is not mandatory
+to call the `close` method.
+
+### Changes to Table APIs
+
+- Previously `Table.schema` was a property. Now it is an async method.
+- The method `Table.__len__` was removed and `len(table)` will no longer
+  work. Use `Table.count_rows` instead.
+
+### Creating Indices
+
+The `Table.create_index` method is now used for creating both vector indices
+and scalar indices. It currently requires a column name to be specified (the
+column to index). Vector index defaults are now smarter and scale better with
+the size of the data.
+
+To specify index configuration details you will need to specify which kind of
+index you are using.
+
+### Querying
+
+The `Table.search` method has been renamed to `AsyncTable.vector_search` for
+clarity.
+
+## Features not yet supported
+
+The following features are not yet supported by the asynchronous API. However,
+we plan to support them soon.
+
+- You cannot specify an embedding function when creating or opening a table.
+  You must calculate embeddings yourself if using the asynchronous API
+- The merge insert operation is not supported in the asynchronous API
+- Cleanup / compact / optimize indices are not supported in the asynchronous API
+- add / alter columns is not supported in the asynchronous API
+- The asynchronous API does not yet support any full text search or reranking
+  search
+- Remote connections to LanceDb Cloud are not yet supported.
+- The method Table.head is not yet supported.

docs/src/python/python.md

@@ -8,17 +8,20 @@ This section contains the API reference for the OSS Python API.
 pip install lancedb
 ```
 
-## Connection
+The following methods describe the synchronous API client. There
+is also an [asynchronous API client](#connections-asynchronous).
+
+## Connections (Synchronous)
 
 ::: lancedb.connect
 
 ::: lancedb.db.DBConnection
 
-## Table
+## Tables (Synchronous)
 
 ::: lancedb.table.Table
 
-## Querying
+## Querying (Synchronous)
 
 ::: lancedb.query.Query
 
@@ -86,4 +89,42 @@ pip install lancedb
 
 ::: lancedb.rerankers.cross_encoder.CrossEncoderReranker
 
-::: lancedb.rerankers.openai.OpenaiReranker
+::: lancedb.rerankers.openai.OpenaiReranker
+
+## Connections (Asynchronous)
+
+Connections represent a connection to a LanceDb database and
+can be used to create, list, or open tables.
+
+::: lancedb.connect_async
+
+::: lancedb.db.AsyncConnection
+
+## Tables (Asynchronous)
+
+Table hold your actual data as a collection of records / rows.
+
+::: lancedb.table.AsyncTable
+
+## Indices (Asynchronous)
+
+Indices can be created on a table to speed up queries. This section
+lists the indices that LanceDb supports.
+
+::: lancedb.index.BTree
+
+::: lancedb.index.IvfPq
+
+## Querying (Asynchronous)
+
+Queries allow you to return data from your database. Basic queries can be
+created with the [AsyncTable.query][lancedb.table.AsyncTable.query] method
+to return the entire (typically filtered) table. Vector searches return the
+rows nearest to a query vector and can be created with the
+[AsyncTable.vector_search][lancedb.table.AsyncTable.vector_search] method.
+
+::: lancedb.query.AsyncQueryBase
+
+::: lancedb.query.AsyncQuery
+
+::: lancedb.query.AsyncVectorQuery

docs/src/reranking/cohere.md

@@ -0,0 +1,75 @@
+# Cohere Reranker
+
+This re-ranker uses the [Cohere](https://cohere.ai/) API to rerank the search results. You can use this re-ranker by passing `CohereReranker()` to the `rerank()` method. Note that you'll either need to set the `COHERE_API_KEY` environment variable or pass the `api_key` argument to use this re-ranker.
+
+
+!!! note
+    Supported Query Types: Hybrid, Vector, FTS
+
+
+```python
+import numpy
+import lancedb
+from lancedb.embeddings import get_registry
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.rerankers import CohereReranker
+
+embedder = get_registry().get("sentence-transformers").create()
+db = lancedb.connect("~/.lancedb")
+
+class Schema(LanceModel):
+    text: str = embedder.SourceField()
+    vector: Vector(embedder.ndims()) = embedder.VectorField()
+
+data = [
+    {"text": "hello world"},
+    {"text": "goodbye world"}
+    ]
+tbl = db.create_table("test", schema=Schema, mode="overwrite")
+tbl.add(data)
+reranker = CohereReranker(api_key="key")
+
+# Run vector search with a reranker
+result = tbl.search("hello").rerank(reranker=reranker).to_list() 
+
+# Run FTS search with a reranker
+result = tbl.search("hello", query_type="fts").rerank(reranker=reranker).to_list()
+
+# Run hybrid search with a reranker
+tbl.create_fts_index("text", replace=True)
+result = tbl.search("hello", query_type="hybrid").rerank(reranker=reranker).to_list()
+
+```
+
+Accepted Arguments
+----------------
+| Argument | Type | Default | Description |
+| --- | --- | --- | --- |
+| `model_name` | `str` | `"rerank-english-v2.0"` | The name of the reranker model to use. Available cohere models are: rerank-english-v2.0, rerank-multilingual-v2.0 |
+| `column` | `str` | `"text"` | The name of the column to use as input to the cross encoder model. |
+| `top_n` | `str` | `None` | The number of results to return. If None, will return all results. |
+| `api_key` | `str` | `None` | The API key for the Cohere API. If not provided, the `COHERE_API_KEY` environment variable is used. |
+| `return_score` | str | `"relevance"` | Options are "relevance" or "all". The type of score to return. If "relevance", will return only the `_relevance_score. If "all" is supported, will return relevance score along with the vector and/or fts scores depending on query type |
+
+
+
+## Supported Scores for each query type
+You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:
+
+### Hybrid Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ❌ Not Supported | Returns have vector(`_distance`) and FTS(`score`) along with Hybrid Search score(`_relevance_score`) |
+
+### Vector Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have vector(`_distance`) along with Hybrid Search score(`_relevance_score`) |
+
+### FTS Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have FTS(`score`) along with Hybrid Search score(`_relevance_score`) |

docs/src/reranking/colbert.md

@@ -0,0 +1,71 @@
+# ColBERT Reranker
+
+This re-ranker uses ColBERT model to rerank the search results. You can use this re-ranker by passing `ColbertReranker()` to the `rerank()` method. 
+!!! note
+    Supported Query Types: Hybrid, Vector, FTS
+
+
+```python
+import numpy
+import lancedb
+from lancedb.embeddings import get_registry
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.rerankers import ColbertReranker
+
+embedder = get_registry().get("sentence-transformers").create()
+db = lancedb.connect("~/.lancedb")
+
+class Schema(LanceModel):
+    text: str = embedder.SourceField()
+    vector: Vector(embedder.ndims()) = embedder.VectorField()
+
+data = [
+    {"text": "hello world"},
+    {"text": "goodbye world"}
+    ]
+tbl = db.create_table("test", schema=Schema, mode="overwrite")
+tbl.add(data)
+reranker = ColbertReranker()
+
+# Run vector search with a reranker
+result = tbl.search("hello").rerank(reranker=reranker).to_list() 
+
+# Run FTS search with a reranker
+result = tbl.search("hello", query_type="fts").rerank(reranker=reranker).to_list()
+
+# Run hybrid search with a reranker
+tbl.create_fts_index("text", replace=True)
+result = tbl.search("hello", query_type="hybrid").rerank(reranker=reranker).to_list()
+
+```
+
+Accepted Arguments
+----------------
+| Argument | Type | Default | Description |
+| --- | --- | --- | --- |
+| `model_name` | `str` | `"colbert-ir/colbertv2.0"` | The name of the reranker model to use.|
+| `column` | `str` | `"text"` | The name of the column to use as input to the cross encoder model. |
+| `device` | `str` | `None` | The device to use for the cross encoder model. If None, will use "cuda" if available, otherwise "cpu". |
+| `return_score` | str | `"relevance"` | Options are "relevance" or "all". The type of score to return. If "relevance", will return only the `_relevance_score. If "all" is supported, will return relevance score along with the vector and/or fts scores depending on query type |
+
+
+## Supported Scores for each query type
+You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:
+
+### Hybrid Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ❌ Not Supported | Returns have vector(`_distance`) and FTS(`score`) along with Hybrid Search score(`_relevance_score`) |
+
+### Vector Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have vector(`_distance`) along with Hybrid Search score(`_relevance_score`) |
+
+### FTS Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have FTS(`score`) along with Hybrid Search score(`_relevance_score`) |

docs/src/reranking/cross_encoder.md

@@ -0,0 +1,70 @@
+# Cross Encoder Reranker
+
+This re-ranker uses Cross Encoder models from sentence-transformers to rerank the search results. You can use this re-ranker by passing `CrossEncoderReranker()` to the `rerank()` method. 
+!!! note
+    Supported Query Types: Hybrid, Vector, FTS
+
+
+```python
+import numpy
+import lancedb
+from lancedb.embeddings import get_registry
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.rerankers import CrossEncoderReranker
+
+embedder = get_registry().get("sentence-transformers").create()
+db = lancedb.connect("~/.lancedb")
+
+class Schema(LanceModel):
+    text: str = embedder.SourceField()
+    vector: Vector(embedder.ndims()) = embedder.VectorField()
+
+data = [
+    {"text": "hello world"},
+    {"text": "goodbye world"}
+    ]
+tbl = db.create_table("test", schema=Schema, mode="overwrite")
+tbl.add(data)
+reranker = CrossEncoderReranker()
+
+# Run vector search with a reranker
+result = tbl.search("hello").rerank(reranker=reranker).to_list() 
+
+# Run FTS search with a reranker
+result = tbl.search("hello", query_type="fts").rerank(reranker=reranker).to_list()
+
+# Run hybrid search with a reranker
+tbl.create_fts_index("text", replace=True)
+result = tbl.search("hello", query_type="hybrid").rerank(reranker=reranker).to_list()
+
+```
+
+Accepted Arguments
+----------------
+| Argument | Type | Default | Description |
+| --- | --- | --- | --- |
+| `model_name` | `str` | `""cross-encoder/ms-marco-TinyBERT-L-6"` | The name of the reranker model to use.|
+| `column` | `str` | `"text"` | The name of the column to use as input to the cross encoder model. |
+| `device` | `str` | `None` | The device to use for the cross encoder model. If None, will use "cuda" if available, otherwise "cpu". |
+| `return_score` | str | `"relevance"` | Options are "relevance" or "all". The type of score to return. If "relevance", will return only the `_relevance_score. If "all" is supported, will return relevance score along with the vector and/or fts scores depending on query type |
+
+## Supported Scores for each query type
+You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:
+
+### Hybrid Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ❌ Not Supported | Returns have vector(`_distance`) and FTS(`score`) along with Hybrid Search score(`_relevance_score`) |
+
+### Vector Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have vector(`_distance`) along with Hybrid Search score(`_relevance_score`) |
+
+### FTS Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have FTS(`score`) along with Hybrid Search score(`_relevance_score`) |

docs/src/reranking/custom_reranker.md

@@ -0,0 +1,89 @@
+## Building Custom Rerankers
+You can build your own custom reranker by subclassing the `Reranker` class and implementing the `rerank_hybrid()` method. Optionally, you can also implement the `rerank_vector()` and `rerank_fts()` methods if you want to support reranking for vector and FTS search separately.
+Here's an example of a custom reranker that combines the results of semantic and full-text search using a linear combination of the scores.
+
+The `Reranker` base interface comes with a `merge_results()` method that can be used to combine the results of semantic and full-text search. This is a vanilla merging algorithm that simply concatenates the results and removes the duplicates without taking the scores into consideration. It only keeps the first copy of the row encountered. This works well in cases that don't require the scores of semantic and full-text search to combine the results. If you want to use the scores or want to support `return_score="all"`, you'll need to implement your own merging algorithm.
+
+```python
+
+from lancedb.rerankers import Reranker
+import pyarrow as pa
+
+class MyReranker(Reranker):
+    def __init__(self, param1, param2, ..., return_score="relevance"):
+        super().__init__(return_score)
+        self.param1 = param1
+        self.param2 = param2
+    
+    def rerank_hybrid(self, query: str, vector_results: pa.Table, fts_results: pa.Table):
+        # Use the built-in merging function
+        combined_result = self.merge_results(vector_results, fts_results)
+        
+        # Do something with the combined results
+        # ...
+
+        # Return the combined results
+        return combined_result
+    
+    def rerank_vector(self, query: str, vector_results: pa.Table):
+        # Do something with the vector results
+        # ...
+
+        # Return the vector results
+        return vector_results
+    
+    def rerank_fts(self, query: str, fts_results: pa.Table):
+        # Do something with the FTS results
+        # ...
+
+        # Return the FTS results
+        return fts_results
+
+```
+
+### Example of a Custom Reranker
+For the sake of simplicity let's build custom reranker that just enchances the Cohere Reranker by accepting a filter query, and accept other CohereReranker params as kwags.
+
+```python
+
+from typing import List, Union
+import pandas as pd
+from lancedb.rerankers import CohereReranker
+
+class ModifiedCohereReranker(CohereReranker):
+    def __init__(self, filters: Union[str, List[str]], **kwargs):
+        super().__init__(**kwargs)
+        filters = filters if isinstance(filters, list) else [filters]
+        self.filters = filters
+
+    def rerank_hybrid(self, query: str, vector_results: pa.Table, fts_results: pa.Table)-> pa.Table:
+        combined_result = super().rerank_hybrid(query, vector_results, fts_results)
+        df = combined_result.to_pandas()
+        for filter in self.filters:
+            df = df.query("not text.str.contains(@filter)")
+
+        return pa.Table.from_pandas(df)
+    
+    def rerank_vector(self, query: str, vector_results: pa.Table)-> pa.Table:
+        vector_results = super().rerank_vector(query, vector_results)
+        df = vector_results.to_pandas()
+        for filter in self.filters:
+            df = df.query("not text.str.contains(@filter)")
+
+        return pa.Table.from_pandas(df)
+    
+    def rerank_fts(self, query: str, fts_results: pa.Table)-> pa.Table:
+        fts_results = super().rerank_fts(query, fts_results)
+        df = fts_results.to_pandas()
+        for filter in self.filters:
+            df = df.query("not text.str.contains(@filter)")
+
+        return pa.Table.from_pandas(df)
+
+```
+
+!!! tip
+    The `vector_results` and `fts_results` are pyarrow tables. Lean more about pyarrow tables [here](https://arrow.apache.org/docs/python). It can be convered to other data types like pandas dataframe, pydict, pylist etc.
+
+    For example, You can convert them to pandas dataframes using `to_pandas()` method and perform any operations you want. After you are done, you can convert the dataframe back to pyarrow table using `pa.Table.from_pandas()` method and return it.
+

docs/src/reranking/index.md

@@ -0,0 +1,61 @@
+Reranking is the process of reordering a list of items based on some criteria. In the context of search, reranking is used to reorder the search results returned by a search engine based on some criteria. This can be useful when the initial ranking of the search results is not satisfactory or when the user has provided additional information that can be used to improve the ranking of the search results.
+
+LanceDB comes with some built-in rerankers. Some of the rerankers that are available in LanceDB are:
+
+| Reranker | Description | Supported Query Types |
+| --- | --- | --- |
+| `LinearCombinationReranker` | Reranks search results based on a linear combination of FTS and vector search scores | Hybrid |
+| `CohereReranker` | Uses cohere Reranker API to rerank results | Vector, FTS, Hybrid |
+| `CrossEncoderReranker` | Uses a cross-encoder model to rerank search results | Vector, FTS, Hybrid |
+| `ColbertReranker` | Uses a colbert model to rerank search results | Vector, FTS, Hybrid |
+| `OpenaiReranker`(Experimental) | Uses OpenAI's chat model to rerank search results | Vector, FTS, Hybrid |
+
+
+## Using a Reranker
+Using rerankers is optional for vector and FTS. However, for hybrid search, rerankers are required. To use a reranker, you need to create an instance of the reranker and pass it to the `rerank` method of the query builder.
+
+```python
+import numpy
+import lancedb
+from lancedb.embeddings import get_registry
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.rerankers import CohereReranker
+
+embedder = get_registry().get("sentence-transformers").create()
+db = lancedb.connect("~/.lancedb")
+
+class Schema(LanceModel):
+    text: str = embedder.SourceField()
+    vector: Vector(embedder.ndims()) = embedder.VectorField()
+
+data = [
+    {"text": "hello world"},
+    {"text": "goodbye world"}
+    ]
+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() 
+
+# Run FTS search with a reranker
+result = tbl.query("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()
+```
+
+## Available Rerankers
+LanceDB comes with some built-in rerankers. Here are some of the rerankers that are available in LanceDB:
+
+- [Cohere Reranker](./cohere.md)
+- [Cross Encoder Reranker](./cross_encoder.md)
+- [ColBERT Reranker](./colbert.md)
+- [OpenAI Reranker](./openai.md)
+- [Linear Combination Reranker](./linear_combination.md)
+
+## Creating Custom Rerankers
+
+LanceDB also you to create custom rerankers by extending the base `Reranker` class. The custom reranker should implement the `rerank` method that takes a list of search results and returns a reranked list of search results. This is covered in more detail in the [Creating Custom Rerankers](./custom_reranker.md) section.
+

docs/src/reranking/linear_combination.md

@@ -0,0 +1,52 @@
+# Linear Combination Reranker
+
+This is the default re-ranker used by LanceDB hybrid search. It combines the results of semantic and full-text search using a linear combination of the scores. The weights for the linear combination can be specified. It defaults to 0.7, i.e, 70% weight for semantic search and 30% weight for full-text search.
+
+!!! note
+    Supported Query Types: Hybrid
+
+
+```python
+import numpy
+import lancedb
+from lancedb.embeddings import get_registry
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.rerankers import LinearCombinationReranker
+
+embedder = get_registry().get("sentence-transformers").create()
+db = lancedb.connect("~/.lancedb")
+
+class Schema(LanceModel):
+    text: str = embedder.SourceField()
+    vector: Vector(embedder.ndims()) = embedder.VectorField()
+
+data = [
+    {"text": "hello world"},
+    {"text": "goodbye world"}
+    ]
+tbl = db.create_table("test", schema=Schema, mode="overwrite")
+tbl.add(data)
+reranker = LinearCombinationReranker()
+
+# Run hybrid search with a reranker
+tbl.create_fts_index("text", replace=True)
+result = tbl.search("hello", query_type="hybrid").rerank(reranker=reranker).to_list()
+
+```
+
+Accepted Arguments
+----------------
+| Argument | Type | Default | Description |
+| --- | --- | --- | --- |
+| `weight` | `float` | `0.7` | The weight to use for the semantic search score. The weight for the full-text search score is `1 - weights`. |
+| `return_score` | str | `"relevance"` | Options are "relevance" or "all". The type of score to return. If "relevance", will return only the `_relevance_score. If "all", will return all scores from the vector and FTS search along with the relevance score. |
+
+
+## Supported Scores for each query type
+You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:
+
+### Hybrid Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have vector(`_distance`) and FTS(`score`) along with Hybrid Search score(`_distance`) |

docs/src/reranking/openai.md

@@ -0,0 +1,73 @@
+# OpenAI Reranker (Experimental)
+
+This re-ranker uses OpenAI chat model to rerank the search results. You can use this re-ranker by passing `OpenAI()` to the `rerank()` method. 
+!!! note
+    Supported Query Types: Hybrid, Vector, FTS
+
+!!! warning
+    This re-ranker is experimental. OpenAI doesn't have a dedicated reranking model, so we are using the chat model for reranking. 
+
+```python
+import numpy
+import lancedb
+from lancedb.embeddings import get_registry
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.rerankers import OpenaiReranker
+
+embedder = get_registry().get("sentence-transformers").create()
+db = lancedb.connect("~/.lancedb")
+
+class Schema(LanceModel):
+    text: str = embedder.SourceField()
+    vector: Vector(embedder.ndims()) = embedder.VectorField()
+
+data = [
+    {"text": "hello world"},
+    {"text": "goodbye world"}
+    ]
+tbl = db.create_table("test", schema=Schema, mode="overwrite")
+tbl.add(data)
+reranker = OpenaiReranker()
+
+# Run vector search with a reranker
+result = tbl.search("hello").rerank(reranker=reranker).to_list() 
+
+# Run FTS search with a reranker
+result = tbl.search("hello", query_type="fts").rerank(reranker=reranker).to_list()
+
+# Run hybrid search with a reranker
+tbl.create_fts_index("text", replace=True)
+result = tbl.search("hello", query_type="hybrid").rerank(reranker=reranker).to_list()
+
+```
+
+Accepted Arguments
+----------------
+| Argument | Type | Default | Description |
+| --- | --- | --- | --- |
+| `model_name` | `str` | `"gpt-4-turbo-preview"` | The name of the reranker model to use.|
+| `column` | `str` | `"text"` | The name of the column to use as input to the cross encoder model. |
+| `return_score` | str | `"relevance"` | Options are "relevance" or "all". The type of score to return. If "relevance", will return only the `_relevance_score. If "all" is supported, will return relevance score along with the vector and/or fts scores depending on query type |
+| `api_key` | str | `None` | The API key to use. If None, will use the OPENAI_API_KEY environment variable.
+
+
+## Supported Scores for each query type
+You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:
+
+### Hybrid Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ❌ Not Supported | Returns have vector(`_distance`) and FTS(`score`) along with Hybrid Search score(`_relevance_score`) |
+
+### Vector Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have vector(`_distance`) along with Hybrid Search score(`_relevance_score`) |
+
+### FTS Search
+|`return_score`| Status | Description |
+| --- | --- | --- |
+| `relevance` | ✅ Supported | Returns only have the `_relevance_score` column |
+| `all` | ✅ Supported | Returns have FTS(`score`) along with Hybrid Search score(`_relevance_score`) |

docs/test/md_testing.py

@@ -15,6 +15,7 @@ excluded_globs = [
     "../src/ann_indexes.md",
     "../src/basic.md",
     "../src/hybrid_search/hybrid_search.md",
+    "../src/reranking/*.md",
 ]
 
 python_prefix = "py"

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.4.13",
+  "version": "0.4.14",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.4.13",
+      "version": "0.4.14",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.4.13",
-        "@lancedb/vectordb-darwin-x64": "0.4.13",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.4.13",
-        "@lancedb/vectordb-linux-x64-gnu": "0.4.13",
-        "@lancedb/vectordb-win32-x64-msvc": "0.4.13"
+        "@lancedb/vectordb-darwin-arm64": "0.4.14",
+        "@lancedb/vectordb-darwin-x64": "0.4.14",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.4.14",
+        "@lancedb/vectordb-linux-x64-gnu": "0.4.14",
+        "@lancedb/vectordb-win32-x64-msvc": "0.4.14"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -334,9 +334,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.13.tgz",
-      "integrity": "sha512-JfroNCG8yKIU931Y+x8d0Fp8C9DHUSC5j+CjI+e5err7rTWtie4j3JbsXlWAnPFaFEOg0Xk3BWkSikCvhPGJGg==",
+      "version": "0.4.14",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.14.tgz",
+      "integrity": "sha512-fw6mf6UhFf4j2kKdFcw0P+SOiIqmRbt+YQSgDbF4BFU3OUSW0XyfETIj9cUMQbSwPFsofhlGp5BRpCd7W9noew==",
       "cpu": [
         "arm64"
       ],
@@ -345,22 +345,10 @@
         "darwin"
       ]
     },
-    "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.13.tgz",
-      "integrity": "sha512-dG6IMvfpHpnHdbJ0UffzJ7cZfMiC02MjIi6YJzgx+hKz2UNXWNBIfTvvhqli85mZsGRXL1OYDdYv0K1YzNjXlA==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ]
-    },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.13.tgz",
-      "integrity": "sha512-BRR1VzaMviXby7qmLm0axNZM8eUZF3ZqfvnDKdVRpC3LaRueD6pMXHuC2IUKaFkn7xktf+8BlDZb6foFNEj8bQ==",
+      "version": "0.4.14",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.14.tgz",
+      "integrity": "sha512-1+LFI8vU+f/lnGy1s3XCySuV4oj3ZUW03xtmedGBW8nv/Y/jWXP0OYJCRI72eu+dLIdu0tCPsEiu8Hl+o02t9g==",
       "cpu": [
         "arm64"
       ],
@@ -369,22 +357,10 @@
         "linux"
       ]
     },
-    "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.13.tgz",
-      "integrity": "sha512-WnekZ7ZMlria+NODZ6aBCljCFQSe2bBNUS9ZpyFl/Y1vHduSQPuBxM6V7vp2QubC0daq/rifgjDob89DF+x3xw==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "linux"
-      ]
-    },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.13.tgz",
-      "integrity": "sha512-3NDpMWBL2ksDHXAraXhowiLqQcNWM5bdbeHwze4+InYMD54hyQ2ODNc+4usxp63Nya9biVnFS27yXULqkzIEqQ==",
+      "version": "0.4.14",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.14.tgz",
+      "integrity": "sha512-fpuNMZ4aHSpZC3ztp5a0Wh18N6DpCx5EPWhS7bGA5XulGc0l+sZAJHfHwalx76ys//0Ns1z7cuKJhZpSa4SrdQ==",
       "cpu": [
         "x64"
       ],

python/python/lancedb/__init__.py

@@ -145,34 +145,20 @@ async def connect_async(
         the last check, then the table will be checked for updates. Note: this
         consistency only applies to read operations. Write operations are
         always consistent.
-    request_thread_pool: int or ThreadPoolExecutor, optional
-        The thread pool to use for making batch requests to the LanceDB Cloud API.
-        If an integer, then a ThreadPoolExecutor will be created with that
-        number of threads. If None, then a ThreadPoolExecutor will be created
-        with the default number of threads. If a ThreadPoolExecutor, then that
-        executor will be used for making requests. This is for LanceDB Cloud
-        only and is only used when making batch requests (i.e., passing in
-        multiple queries to the search method at once).
 
     Examples
     --------
 
-    For a local directory, provide a path for the database:
-
     >>> import lancedb
-    >>> db = lancedb.connect("~/.lancedb")
-
-    For object storage, use a URI prefix:
-
-    >>> db = lancedb.connect("s3://my-bucket/lancedb")
-
-    Connect to LancdDB cloud:
-
-    >>> db = lancedb.connect("db://my_database", api_key="ldb_...")
+    >>> async def doctest_example():
+    ...     # For a local directory, provide a path to the database
+    ...     db = await lancedb.connect_async("~/.lancedb")
+    ...     # For object storage, use a URI prefix
+    ...     db = await lancedb.connect_async("s3://my-bucket/lancedb")
 
     Returns
     -------
-    conn : DBConnection
+    conn : AsyncConnection
         A connection to a LanceDB database.
     """
     if read_consistency_interval is not None:

python/python/lancedb/db.py

@@ -25,7 +25,6 @@ from overrides import EnforceOverrides, override
 from pyarrow import fs
 
 from lancedb.common import data_to_reader, validate_schema
-from lancedb.embeddings.registry import EmbeddingFunctionRegistry
 from lancedb.utils.events import register_event
 
 from ._lancedb import connect as lancedb_connect
@@ -451,16 +450,17 @@ class LanceDBConnection(DBConnection):
 class AsyncConnection(object):
     """An active LanceDB connection
 
-    To obtain a connection you can use the [connect] function.
+    To obtain a connection you can use the [connect_async][lancedb.connect_async]
+    function.
 
     This could be a native connection (using lance) or a remote connection (e.g. for
     connecting to LanceDb Cloud)
 
     Local connections do not currently hold any open resources but they may do so in the
     future (for example, for shared cache or connections to catalog services) Remote
-    connections represent an open connection to the remote server.  The [close] method
-    can be used to release any underlying resources eagerly.  The connection can also
-    be used as a context manager:
+    connections represent an open connection to the remote server.  The
+    [close][lancedb.db.AsyncConnection.close] method can be used to release any
+    underlying resources eagerly.  The connection can also be used as a context manager.
 
     Connections can be shared on multiple threads and are expected to be long lived.
     Connections can also be used as a context manager, however, in many cases a single
@@ -471,10 +471,9 @@ class AsyncConnection(object):
     Examples
     --------
 
-    >>> import asyncio
     >>> import lancedb
-    >>> async def my_connect():
-    ...   with await lancedb.connect("/tmp/my_dataset") as conn:
+    >>> async def doctest_example():
+    ...   with await lancedb.connect_async("/tmp/my_dataset") as conn:
     ...     # do something with the connection
     ...     pass
     ...   # conn is closed here
@@ -535,9 +534,8 @@ class AsyncConnection(object):
         exist_ok: Optional[bool] = None,
         on_bad_vectors: Optional[str] = None,
         fill_value: Optional[float] = None,
-        embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
     ) -> AsyncTable:
-        """Create a [Table][lancedb.table.Table] in the database.
+        """Create an [AsyncTable][lancedb.table.AsyncTable] in the database.
 
         Parameters
         ----------
@@ -576,7 +574,7 @@ class AsyncConnection(object):
 
         Returns
         -------
-        LanceTable
+        AsyncTable
             A reference to the newly created table.
 
         !!! note
@@ -590,12 +588,14 @@ class AsyncConnection(object):
         Can create with list of tuples or dictionaries:
 
         >>> import lancedb
-        >>> db = lancedb.connect("./.lancedb")
-        >>> 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)
-        LanceTable(connection=..., name="my_table")
-        >>> db["my_table"].head()
+        >>> async def doctest_example():
+        ...     db = await lancedb.connect_async("./.lancedb")
+        ...     data = [{"vector": [1.1, 1.2], "lat": 45.5, "long": -122.7},
+        ...             {"vector": [0.2, 1.8], "lat": 40.1, "long":  -74.1}]
+        ...     my_table = await db.create_table("my_table", data)
+        ...     print(await my_table.query().limit(5).to_arrow())
+        >>> import asyncio
+        >>> asyncio.run(doctest_example())
         pyarrow.Table
         vector: fixed_size_list<item: float>[2]
           child 0, item: float
@@ -614,9 +614,11 @@ class AsyncConnection(object):
         ...    "lat": [45.5, 40.1],
         ...    "long": [-122.7, -74.1]
         ... })
-        >>> db.create_table("table2", data)
-        LanceTable(connection=..., name="table2")
-        >>> db["table2"].head()
+        >>> async def pandas_example():
+        ...     db = await lancedb.connect_async("./.lancedb")
+        ...     my_table = await db.create_table("table2", data)
+        ...     print(await my_table.query().limit(5).to_arrow())
+        >>> asyncio.run(pandas_example())
         pyarrow.Table
         vector: fixed_size_list<item: float>[2]
           child 0, item: float
@@ -636,9 +638,11 @@ class AsyncConnection(object):
         ...   pa.field("lat", pa.float32()),
         ...   pa.field("long", pa.float32())
         ... ])
-        >>> db.create_table("table3", data, schema = custom_schema)
-        LanceTable(connection=..., name="table3")
-        >>> db["table3"].head()
+        >>> async def with_schema():
+        ...     db = await lancedb.connect_async("./.lancedb")
+        ...     my_table = await db.create_table("table3", data, schema = custom_schema)
+        ...     print(await my_table.query().limit(5).to_arrow())
+        >>> asyncio.run(with_schema())
         pyarrow.Table
         vector: fixed_size_list<item: float>[2]
           child 0, item: float
@@ -670,9 +674,10 @@ class AsyncConnection(object):
         ...     pa.field("item", pa.utf8()),
         ...     pa.field("price", pa.float32()),
         ... ])
-        >>> db.create_table("table4", make_batches(), schema=schema)
-        LanceTable(connection=..., name="table4")
-
+        >>> async def iterable_example():
+        ...     db = await lancedb.connect_async("./.lancedb")
+        ...     await db.create_table("table4", make_batches(), schema=schema)
+        >>> asyncio.run(iterable_example())
         """
         if inspect.isclass(schema) and issubclass(schema, LanceModel):
             # convert LanceModel to pyarrow schema
@@ -681,12 +686,6 @@ class AsyncConnection(object):
             schema = schema.to_arrow_schema()
 
         metadata = None
-        if embedding_functions is not None:
-            # If we passed in embedding functions explicitly
-            # then we'll override any schema metadata that
-            # may was implicitly specified by the LanceModel schema
-            registry = EmbeddingFunctionRegistry.get_instance()
-            metadata = registry.get_table_metadata(embedding_functions)
 
         # Defining defaults here and not in function prototype.  In the future
         # these defaults will move into rust so better to keep them as None.
@@ -767,11 +766,11 @@ class AsyncConnection(object):
         name: str
             The name of the table.
         """
-        raise NotImplementedError
+        await self._inner.drop_table(name)
 
     async def drop_database(self):
         """
         Drop database
         This is the same thing as dropping all the tables
         """
-        raise NotImplementedError
+        await self._inner.drop_db()

python/python/lancedb/query.py

@@ -1033,7 +1033,7 @@ class AsyncQueryBase(object):
         Construct an AsyncQueryBase
 
         This method is not intended to be called directly.  Instead, use the
-        [Table.query][] method to create a query.
+        [AsyncTable.query][lancedb.table.AsyncTable.query] method to create a query.
         """
         self._inner = inner
 
@@ -1041,7 +1041,10 @@ class AsyncQueryBase(object):
         """
         Only return rows matching the given predicate
 
-        The predicate should be supplied as an SQL query string.  For example:
+        The predicate should be supplied as an SQL query string.
+
+        Examples
+        --------
 
         >>> predicate = "x > 10"
         >>> predicate = "y > 0 AND y < 100"
@@ -1112,7 +1115,8 @@ class AsyncQueryBase(object):
         Execute the query and collect the results into an Apache Arrow Table.
 
         This method will collect all results into memory before returning.  If
-        you expect a large number of results, you may want to use [to_batches][]
+        you expect a large number of results, you may want to use
+        [to_batches][lancedb.query.AsyncQueryBase.to_batches]
         """
         batch_iter = await self.to_batches()
         return pa.Table.from_batches(
@@ -1123,12 +1127,13 @@ class AsyncQueryBase(object):
         """
         Execute the query and collect the results into a pandas DataFrame.
 
-        This method will collect all results into memory before returning.  If
-        you expect a large number of results, you may want to use [to_batches][]
-        and convert each batch to pandas separately.
+        This method will collect all results into memory before returning.  If you
+        expect a large number of results, you may want to use
+        [to_batches][lancedb.query.AsyncQueryBase.to_batches] and convert each batch to
+        pandas separately.
 
-        Example
-        -------
+        Examples
+        --------
 
         >>> import asyncio
         >>> from lancedb import connect_async
@@ -1148,7 +1153,7 @@ class AsyncQuery(AsyncQueryBase):
         Construct an AsyncQuery
 
         This method is not intended to be called directly.  Instead, use the
-        [Table.query][] method to create a query.
+        [AsyncTable.query][lancedb.table.AsyncTable.query] method to create a query.
         """
         super().__init__(inner)
         self._inner = inner
@@ -1189,8 +1194,8 @@ class AsyncQuery(AsyncQueryBase):
         If there is only one vector column (a column whose data type is a
         fixed size list of floats) then the column does not need to be specified.
         If there is more than one vector column you must use
-        [AsyncVectorQuery::column][] to specify which column you would like to
-        compare with.
+        [AsyncVectorQuery.column][lancedb.query.AsyncVectorQuery.column] to specify
+        which column you would like to compare with.
 
         If no index has been created on the vector column then a vector query
         will perform a distance comparison between the query vector and every
@@ -1221,8 +1226,10 @@ class AsyncVectorQuery(AsyncQueryBase):
         Construct an AsyncVectorQuery
 
         This method is not intended to be called directly.  Instead, create
-        a query first with [Table.query][] and then use [AsyncQuery.nearest_to][]
-        to convert to a vector query.
+        a query first with [AsyncTable.query][lancedb.table.AsyncTable.query] and then
+        use [AsyncQuery.nearest_to][lancedb.query.AsyncQuery.nearest_to]] to convert to
+        a vector query.  Or you can use
+        [AsyncTable.vector_search][lancedb.table.AsyncTable.vector_search]
         """
         super().__init__(inner)
         self._inner = inner
@@ -1232,7 +1239,7 @@ class AsyncVectorQuery(AsyncQueryBase):
         Set the vector column to query
 
         This controls which column is compared to the query vector supplied in
-        the call to [Query.nearest_to][].
+        the call to [AsyncQuery.nearest_to][lancedb.query.AsyncQuery.nearest_to].
 
         This parameter must be specified if the table has more than one column
         whose data type is a fixed-size-list of floats.

python/python/lancedb/rerankers/base.py

@@ -118,6 +118,11 @@ class Reranker(ABC):
             The results from the vector search
         fts_results : pa.Table
             The results from the FTS search
+
+        Returns
+        -------
+        pa.Table
+            The merged results
         """
         combined = pa.concat_tables([vector_results, fts_results], promote=True)
         row_id = combined.column("_rowid")

python/python/lancedb/rerankers/cross_encoder.py

@@ -14,7 +14,7 @@ class CrossEncoderReranker(Reranker):
 
     Parameters
     ----------
-    model : str, default "cross-encoder/ms-marco-TinyBERT-L-6"
+    model_name : str, default "cross-encoder/ms-marco-TinyBERT-L-6"
         The name of the cross encoder model to use. See the sentence transformers
         documentation for a list of available models.
     column : str, default "text"

python/python/lancedb/table.py

@@ -1893,8 +1893,8 @@ class AsyncTable:
     An AsyncTable object is expected to be long lived and reused for multiple
     operations. AsyncTable objects will cache a certain amount of index data in memory.
     This cache will be freed when the Table is garbage collected.  To eagerly free the
-    cache you can call the [close][AsyncTable.close] method.  Once the AsyncTable is
-    closed, it cannot be used for any further operations.
+    cache you can call the [close][lancedb.AsyncTable.close] method.  Once the
+    AsyncTable is closed, it cannot be used for any further operations.
 
     An AsyncTable can also be used as a context manager, and will automatically close
     when the context is exited.  Closing a table is optional.  If you do not close the
@@ -1903,13 +1903,17 @@ class AsyncTable:
     Examples
     --------
 
-    Create using [DBConnection.create_table][lancedb.DBConnection.create_table]
+    Create using [AsyncConnection.create_table][lancedb.AsyncConnection.create_table]
     (more examples in that method's documentation).
 
     >>> import lancedb
-    >>> db = lancedb.connect("./.lancedb")
-    >>> table = db.create_table("my_table", data=[{"vector": [1.1, 1.2], "b": 2}])
-    >>> table.head()
+    >>> async def create_a_table():
+    ...     db = await lancedb.connect_async("./.lancedb")
+    ...     data = [{"vector": [1.1, 1.2], "b": 2}]
+    ...     table = await db.create_table("my_table", data=data)
+    ...     print(await table.query().limit(5).to_arrow())
+    >>> import asyncio
+    >>> asyncio.run(create_a_table())
     pyarrow.Table
     vector: fixed_size_list<item: float>[2]
       child 0, item: float
@@ -1918,25 +1922,37 @@ class AsyncTable:
     vector: [[[1.1,1.2]]]
     b: [[2]]
 
-    Can append new data with [Table.add()][lancedb.table.Table.add].
+    Can append new data with [AsyncTable.add()][lancedb.table.AsyncTable.add].
 
-    >>> table.add([{"vector": [0.5, 1.3], "b": 4}])
+    >>> async def add_to_table():
+    ...     db = await lancedb.connect_async("./.lancedb")
+    ...     table = await db.open_table("my_table")
+    ...     await table.add([{"vector": [0.5, 1.3], "b": 4}])
+    >>> asyncio.run(add_to_table())
 
-    Can query the table with [Table.search][lancedb.table.Table.search].
+    Can query the table with
+    [AsyncTable.vector_search][lancedb.table.AsyncTable.vector_search].
 
-    >>> table.search([0.4, 0.4]).select(["b", "vector"]).to_pandas()
+    >>> async def search_table_for_vector():
+    ...     db = await lancedb.connect_async("./.lancedb")
+    ...     table = await db.open_table("my_table")
+    ...     results = (
+    ...       await table.vector_search([0.4, 0.4]).select(["b", "vector"]).to_pandas()
+    ...     )
+    ...     print(results)
+    >>> asyncio.run(search_table_for_vector())
        b      vector  _distance
     0  4  [0.5, 1.3]       0.82
     1  2  [1.1, 1.2]       1.13
 
     Search queries are much faster when an index is created. See
-    [Table.create_index][lancedb.table.Table.create_index].
+    [AsyncTable.create_index][lancedb.table.AsyncTable.create_index].
     """
 
     def __init__(self, table: LanceDBTable):
-        """Create a new Table object.
+        """Create a new AsyncTable object.
 
-        You should not create Table objects directly.
+        You should not create AsyncTable objects directly.
 
         Use [AsyncConnection.create_table][lancedb.AsyncConnection.create_table] and
         [AsyncConnection.open_table][lancedb.AsyncConnection.open_table] to obtain
@@ -1988,6 +2004,14 @@ class AsyncTable:
         return await self._inner.count_rows(filter)
 
     def query(self) -> AsyncQuery:
+        """
+        Returns an [AsyncQuery][lancedb.query.AsyncQuery] that can be used
+        to search the table.
+
+        Use methods on the returned query to control query behavior.  The query
+        can be executed with methods like [to_arrow][lancedb.query.AsyncQuery.to_arrow],
+        [to_pandas][lancedb.query.AsyncQuery.to_pandas] and more.
+        """
         return AsyncQuery(self._inner.query())
 
     async def to_pandas(self) -> "pd.DataFrame":
@@ -2024,20 +2048,8 @@ class AsyncTable:
 
         Parameters
         ----------
-        index: Index
-            The index to create.
-
-            LanceDb supports multiple types of indices.  See the static methods on
-            the Index class for more details.
-        column: str, default None
+        column: str
             The column to index.
-
-            When building a scalar index this must be set.
-
-            When building a vector index, this is optional.  The default will look
-            for any columns of type fixed-size-list with floating point values.  If
-            there is only one column of this type then it will be used.  Otherwise
-            an error will be returned.
         replace: bool, default True
             Whether to replace the existing index
 
@@ -2046,6 +2058,10 @@ class AsyncTable:
             that index is out of date.
 
             The default is True
+        config: Union[IvfPq, BTree], default None
+            For advanced configuration you can specify the type of index you would
+            like to create.   You can also specify index-specific parameters when
+            creating an index object.
         """
         index = None
         if config is not None:
@@ -2167,7 +2183,8 @@ class AsyncTable:
         Search the table with a given query vector.
         This is a convenience method for preparing a vector query and
         is the same thing as calling `nearestTo` on the builder returned
-        by `query`.  Seer [nearest_to][AsyncQuery.nearest_to] for more details.
+        by `query`.  Seer [nearest_to][lancedb.query.AsyncQuery.nearest_to] for more
+        details.
         """
         return self.query().nearest_to(query_vector)
 
@@ -2233,7 +2250,7 @@ class AsyncTable:
            x      vector
         0  3  [5.0, 6.0]
         """
-        raise NotImplementedError
+        return await self._inner.delete(where)
 
     async def update(
         self,
@@ -2289,102 +2306,6 @@ class AsyncTable:
 
         return await self._inner.update(updates_sql, where)
 
-    async def cleanup_old_versions(
-        self,
-        older_than: Optional[timedelta] = None,
-        *,
-        delete_unverified: bool = False,
-    ) -> CleanupStats:
-        """
-        Clean up old versions of the table, freeing disk space.
-
-        Note: This function is not available in LanceDb Cloud (since LanceDb
-        Cloud manages cleanup for you automatically)
-
-        Parameters
-        ----------
-        older_than: timedelta, default None
-            The minimum age of the version to delete. If None, then this defaults
-            to two weeks.
-        delete_unverified: bool, default False
-            Because they may be part of an in-progress transaction, files newer
-            than 7 days old are not deleted by default. If you are sure that
-            there are no in-progress transactions, then you can set this to True
-            to delete all files older than `older_than`.
-
-        Returns
-        -------
-        CleanupStats
-            The stats of the cleanup operation, including how many bytes were
-            freed.
-        """
-        raise NotImplementedError
-
-    async def compact_files(self, *args, **kwargs):
-        """
-        Run the compaction process on the table.
-
-        Note: This function is not available in LanceDb Cloud (since LanceDb
-        Cloud manages compaction for you automatically)
-
-        This can be run after making several small appends to optimize the table
-        for faster reads.
-
-        Arguments are passed onto :meth:`lance.dataset.DatasetOptimizer.compact_files`.
-        For most cases, the default should be fine.
-        """
-        raise NotImplementedError
-
-    async def add_columns(self, transforms: Dict[str, str]):
-        """
-        Add new columns with defined values.
-
-        This is not yet available in LanceDB Cloud.
-
-        Parameters
-        ----------
-        transforms: Dict[str, str]
-            A map of column name to a SQL expression to use to calculate the
-            value of the new column. These expressions will be evaluated for
-            each row in the table, and can reference existing columns.
-        """
-        raise NotImplementedError
-
-    async def alter_columns(self, alterations: Iterable[Dict[str, str]]):
-        """
-        Alter column names and nullability.
-
-        This is not yet available in LanceDB Cloud.
-
-        alterations : Iterable[Dict[str, Any]]
-            A sequence of dictionaries, each with the following keys:
-            - "path": str
-                The column path to alter. For a top-level column, this is the name.
-                For a nested column, this is the dot-separated path, e.g. "a.b.c".
-            - "name": str, optional
-                The new name of the column. If not specified, the column name is
-                not changed.
-            - "nullable": bool, optional
-                Whether the column should be nullable. If not specified, the column
-                nullability is not changed. Only non-nullable columns can be changed
-                to nullable. Currently, you cannot change a nullable column to
-                non-nullable.
-        """
-        raise NotImplementedError
-
-    async def drop_columns(self, columns: Iterable[str]):
-        """
-        Drop columns from the table.
-
-        This is not yet available in LanceDB Cloud.
-
-        Parameters
-        ----------
-        columns : Iterable[str]
-            The names of the columns to drop.
-        """
-        raise NotImplementedError
-
     async def version(self) -> int:
         """
         Retrieve the version of the table

python/python/tests/docs/test_basic.py

@@ -0,0 +1,162 @@
+import shutil
+
+# --8<-- [start:imports]
+import lancedb
+import pandas as pd
+import pyarrow as pa
+
+# --8<-- [end:imports]
+import pytest
+from numpy.random import randint, random
+
+shutil.rmtree("data/sample-lancedb", ignore_errors=True)
+
+
+def test_quickstart():
+    # --8<-- [start:connect]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+    # --8<-- [end:connect]
+
+    # --8<-- [start:create_table]
+    data = [
+        {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+        {"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
+    ]
+
+    # Synchronous client
+    tbl = db.create_table("my_table", data=data)
+    # --8<-- [end:create_table]
+
+    # --8<-- [start:create_table_pandas]
+    df = pd.DataFrame(
+        [
+            {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+            {"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
+        ]
+    )
+    # Synchronous client
+    tbl = db.create_table("table_from_df", data=df)
+    # --8<-- [end:create_table_pandas]
+
+    # --8<-- [start:create_empty_table]
+    schema = pa.schema([pa.field("vector", pa.list_(pa.float32(), list_size=2))])
+    # Synchronous client
+    tbl = db.create_table("empty_table", schema=schema)
+    # --8<-- [end:create_empty_table]
+    # --8<-- [start:open_table]
+    # Synchronous client
+    tbl = db.open_table("my_table")
+    # --8<-- [end:open_table]
+    # --8<-- [start:table_names]
+    # Synchronous client
+    print(db.table_names())
+    # --8<-- [end:table_names]
+    # Synchronous client
+    # --8<-- [start:add_data]
+    # Option 1: Add a list of dicts to a table
+    data = [
+        {"vector": [1.3, 1.4], "item": "fizz", "price": 100.0},
+        {"vector": [9.5, 56.2], "item": "buzz", "price": 200.0},
+    ]
+    tbl.add(data)
+
+    # Option 2: Add a pandas DataFrame to a table
+    df = pd.DataFrame(data)
+    tbl.add(data)
+    # --8<-- [end:add_data]
+    # --8<-- [start:vector_search]
+    # Synchronous client
+    tbl.search([100, 100]).limit(2).to_pandas()
+    # --8<-- [end:vector_search]
+    tbl.add(
+        [
+            {"vector": random(2), "item": "autogen", "price": randint(100)}
+            for _ in range(1000)
+        ]
+    )
+    # --8<-- [start:create_index]
+    # Synchronous client
+    tbl.create_index(num_sub_vectors=1)
+    # --8<-- [end:create_index]
+    # --8<-- [start:delete_rows]
+    # Synchronous client
+    tbl.delete('item = "fizz"')
+    # --8<-- [end:delete_rows]
+    # --8<-- [start:drop_table]
+    # Synchronous client
+    db.drop_table("my_table")
+    # --8<-- [end:drop_table]
+
+
+@pytest.mark.asyncio
+async def test_quickstart_async():
+    # --8<-- [start:connect_async]
+    # LanceDb offers both a synchronous and an asynchronous client.  There are still a
+    # few operations that are only supported by the synchronous client (e.g. embedding
+    # functions, full text search) but both APIs should soon be equivalent
+
+    # In this guide we will give examples of both clients.  In other guides we will
+    # typically only provide examples with one client or the other.
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri)
+    # --8<-- [end:connect_async]
+
+    data = [
+        {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+        {"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
+    ]
+
+    # --8<-- [start:create_table_async]
+    # Asynchronous client
+    async_tbl = await async_db.create_table("my_table2", data=data)
+    # --8<-- [end:create_table_async]
+
+    df = pd.DataFrame(
+        [
+            {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+            {"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
+        ]
+    )
+
+    # --8<-- [start:create_table_async_pandas]
+    # Asynchronous client
+    async_tbl = await async_db.create_table("table_from_df2", 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)
+    # --8<-- [end:create_empty_table_async]
+    # --8<-- [start:open_table_async]
+    # Asynchronous client
+    async_tbl = await async_db.open_table("my_table2")
+    # --8<-- [end:open_table_async]
+    # --8<-- [start:table_names_async]
+    # Asynchronous client
+    print(await async_db.table_names())
+    # --8<-- [end:table_names_async]
+    # --8<-- [start:add_data_async]
+    # Asynchronous client
+    await async_tbl.add(data)
+    # --8<-- [end:add_data_async]
+    # Add sufficient data for training
+    data = [{"vector": [x, x], "item": "filler", "price": x * x} for x in range(1000)]
+    await async_tbl.add(data)
+    # --8<-- [start:vector_search_async]
+    # Asynchronous client
+    await async_tbl.vector_search([100, 100]).limit(2).to_pandas()
+    # --8<-- [end:vector_search_async]
+    # --8<-- [start:create_index_async]
+    # Asynchronous client (must specify column to index)
+    await async_tbl.create_index("vector")
+    # --8<-- [end:create_index_async]
+    # --8<-- [start:delete_rows_async]
+    # Asynchronous client
+    await async_tbl.delete('item = "fizz"')
+    # --8<-- [end:delete_rows_async]
+    # --8<-- [start:drop_table_async]
+    # Asynchronous client
+    await async_db.drop_table("my_table2")
+    # --8<-- [end:drop_table_async]

python/src/connection.rs

@@ -137,6 +137,21 @@ impl Connection {
             Ok(Table::new(table))
         })
     }
+
+    pub fn drop_table(self_: PyRef<'_, Self>, name: String) -> PyResult<&PyAny> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.drop_table(name).await.infer_error()
+        })
+    }
+
+    pub fn drop_db(self_: PyRef<'_, Self>) -> PyResult<&PyAny> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(
+            self_.py(),
+            async move { inner.drop_db().await.infer_error() },
+        )
+    }
 }
 
 #[pyfunction]

python/src/table.rs

@@ -80,6 +80,13 @@ impl Table {
         })
     }
 
+    pub fn delete<'a>(self_: PyRef<'a, Self>, condition: String) -> PyResult<&'a PyAny> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.delete(&condition).await.infer_error()
+        })
+    }
+
     pub fn update<'a>(
         self_: PyRef<'a, Self>,
         updates: &PyDict,