rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-10-13 15:22:30 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
7b112debca1027b50dad9e8a28adde359073e9ee
lancedb/docs/web/snippets/tables.mdx
T
Jack Ye b21fb2a4dc docs: bring the open-source documentation into this repository 
The pages describing this code lived in lancedb/docs, a repository with ten
stars that neither contributing guide mentioned. A user who hit a wrong page
while reading the source had to find a separate, near-invisible repository to
fix it. These 102 pages now sit beside the code, and a documentation fix is a
pull request in the repository the reader already had open.

`docs/web` is a complete Mintlify site: `cd docs/web && mint dev` serves it with
no other checkout. Enterprise pages stay private and are merged in when the
published site is assembled, so links into them do not resolve here — every
open-source page does.

`docs/web-tests` holds the tests the code examples are extracted from. They ran
against a published wheel before; here they can run against this repository's
own SDK, so an example that stops compiling fails the pull request that broke
it rather than being noticed later.

Both directories sit beside `docs/src` and are invisible to it: mkdocs reads
`docs_dir: src`, so the SDK reference builds and deploys exactly as before.
2026-09-02 21:09:30 -07:00

371 lines
84 KiB
Plaintext
Raw Blame History

{/* Auto-generated by scripts/mdx_snippets_gen.py. Do not edit manually. */}
export const PyAddColumnsCalculated = "# Add a discounted price column (10% discount)\ntable.add_columns({\"discounted_price\": \"cast((price * 0.9) as float)\"})\n";
export const PyAddColumnsDefaultValues = "# Add a stock status column with default value\ntable.add_columns({\"in_stock\": \"cast(true as boolean)\"})\n";
export const PyAddColumnsNullable = "# Add a nullable timestamp column\ntable.add_columns({\"last_ordered\": \"cast(NULL as timestamp)\"})\n";
export const PyAddDataNestedModel = "from lancedb.pydantic import LanceModel, Vector\nfrom pydantic import BaseModel\n\nclass Document(BaseModel):\n content: str\n source: str\n\nclass NestedSchema(LanceModel):\n id: str\n vector: Vector(128)\n document: Document\n\n# Create table with nested schema\ntable_name = \"nested_model_example\"\ntable = db.create_table(table_name, schema=NestedSchema, mode=\"overwrite\")\n";
export const PyAddDataPydanticModel = "from lancedb.pydantic import LanceModel, Vector\n\n# Define a Pydantic model\nclass Content(LanceModel):\n movie_id: int\n vector: Vector(128)\n genres: str\n title: str\n imdb_id: int\n\n @property\n def imdb_url(self) -> str:\n return f\"https://www.imdb.com/title/tt{self.imdb_id}\"\n\n# Create table with Pydantic model schema\ntable_name = \"pydantic_example\"\ntable = db.create_table(table_name, schema=Content, mode=\"overwrite\")\n";
export const PyAddDataToTable = "import pyarrow as pa\n\n# create an empty table with schema\ndata = [\n {\"vector\": [3.1, 4.1], \"item\": \"foo\", \"price\": 10.0},\n {\"vector\": [5.9, 26.5], \"item\": \"bar\", \"price\": 20.0},\n {\"vector\": [10.2, 100.8], \"item\": \"baz\", \"price\": 30.0},\n {\"vector\": [1.4, 9.5], \"item\": \"fred\", \"price\": 40.0},\n]\n\nschema = pa.schema(\n [\n pa.field(\"vector\", pa.list_(pa.float32(), 2)),\n pa.field(\"item\", pa.utf8()),\n pa.field(\"price\", pa.float32()),\n ]\n)\n\ntable_name = \"basic_ingestion_example\"\ntable = db.create_table(table_name, schema=schema, mode=\"overwrite\")\n# Add data\ntable.add(data)\n";
export const PyAddFeatureColumnsSql = "table.add_columns(\n {\n \"price_per_id\": \"cast(price / id as float)\",\n \"price_log\": \"ln(price)\",\n \"price_score\": \"cast(price / (price + 100.0) as float)\",\n }\n)\n";
export const PyAddFromDataset = "import pyarrow.dataset as ds\n\ndataset = ds.dataset(data_path, format=\"parquet\")\ndb = tmp_db\ntable = db.create_table(\"my_table\", schema=dataset.schema, mode=\"overwrite\")\ntable.add(dataset)\n";
export const PyAlterColumnsDataType = "# Change price from int32 to int64 for larger numbers\ntable.alter_columns({\"path\": \"price\", \"data_type\": pa.int64()})\n";
export const PyAlterColumnsMultiple = "# Rename, change type, and make nullable in one operation\ntable.alter_columns(\n {\n \"path\": \"sale_price\",\n \"rename\": \"final_price\",\n \"data_type\": pa.float64(),\n \"nullable\": True,\n }\n)\n";
export const PyAlterColumnsNullable = "# Make the name column nullable\ntable.alter_columns({\"path\": \"name\", \"nullable\": True})\n";
export const PyAlterColumnsRename = "# Rename discount_price to sale_price\ntable.alter_columns({\"path\": \"discount_price\", \"rename\": \"sale_price\"})\n";
export const PyAlterColumnsWithExpression = "# For custom transforms, create a new column from a SQL expression.\nexpression_table = tmp_db.create_table(\n \"schema_evolution_expression_example\",\n [{\"id\": 1, \"price_text\": \"$100\"}],\n mode=\"overwrite\",\n)\n\nexpression_table.add_columns(\n {\"price_numeric\": \"cast(replace(price_text, '$', '') as int)\"}\n)\nexpression_table.drop_columns([\"price_text\"])\nexpression_table.alter_columns({\"path\": \"price_numeric\", \"rename\": \"price\"})\n";
export const PyAlterVectorColumn = "vector_dim = 768 # Your embedding dimension\ntable_name = \"vector_alter_example\"\ndb = tmp_db\ndata = [\n {\n \"id\": 1,\n \"embedding\": np.random.random(vector_dim).tolist(),\n },\n]\ntable = db.create_table(table_name, data, mode=\"overwrite\")\n\ntable.alter_columns(\n dict(path=\"embedding\", data_type=pa.list_(pa.float32(), vector_dim))\n)\n";
export const PyBatchDataInsertion = "import pyarrow as pa\n\ndef make_batches():\n for i in range(5): # Create 5 batches\n yield pa.RecordBatch.from_arrays(\n [\n pa.array([[3.1, 4.1], [5.9, 26.5]], pa.list_(pa.float32(), 2)),\n pa.array([f\"item{i * 2 + 1}\", f\"item{i * 2 + 2}\"]),\n pa.array([float((i * 2 + 1) * 10), float((i * 2 + 2) * 10)]),\n ],\n [\"vector\", \"item\", \"price\"],\n )\n\nschema = pa.schema(\n [\n pa.field(\"vector\", pa.list_(pa.float32(), 2)),\n pa.field(\"item\", pa.utf8()),\n pa.field(\"price\", pa.float32()),\n ]\n)\n# Create table with batches\ntable_name = \"batch_ingestion_example\"\ntable = db.create_table(table_name, make_batches(), schema=schema, mode=\"overwrite\")\n";
export const PyBranchCreate = "# Fork an isolated, writable branch from main's latest version.\n# `create` returns a table handle scoped to the new branch.\nbranch = table.branches.create(\"exp\")\n";
export const PyBranchDelete = "# Delete the branch and its branch-local history. Data on main is safe.\ntable.branches.delete(\"exp\")\n";
export const PyBranchIndex = "# Build and validate indexes on a branch before using the configuration on\n# main.\ndev = products.branches.create(\"index-dev\")\n\n# A vector (ANN) index and a full-text search index, both branch-scoped.\ndev.create_index(\n \"vector\",\n config=IvfPq(distance_type=\"cosine\", num_partitions=1, num_sub_vectors=2),\n)\ndev.create_index(\"text\", config=FTS())\n\n# Both indexes live only on the branch; main still has none.\nprint([ix.name for ix in dev.list_indices()]) # branch: two indexes\nprint([ix.name for ix in products.list_indices()]) # main: [] (untouched)\n";
export const PyBranchReopen = "# Reopen an existing branch by name from the table handle...\nchecked_out = table.branches.checkout(\"exp\")\n# ...or open it directly from the database connection.\nbranch_handle = db.open_table(\"quotes_branches_example\", branch=\"exp\")\nprint(checked_out.count_rows(), branch_handle.count_rows()) # both 4\n";
export const PyBranchUpsertToMain = "# This is a row-level upsert, not a merge of branch histories.\n# `merge_insert` updates matching rows and inserts new rows using a stable\n# unique key. Filter the branch read if you only want to apply some results.\nrows_to_apply = candidate.to_arrow()\n(\n table.merge_insert(\"id\")\n .when_matched_update_all() # update rows that already exist on main\n .when_not_matched_insert_all() # insert rows that are new on the branch\n .execute(rows_to_apply)\n)\n";
export const PyBranchWrite = "# Writes land on the branch handle only; main is left untouched.\nbranch.add([{\"id\": 4, \"author\": \"Lancelot\", \"quote\": \"For the realm!\"}])\nprint(branch.count_rows()) # 4 rows on the branch\nprint(table.count_rows()) # 3 rows; main is unaffected\n\n# List every branch, each mapped to its metadata (including its fork point).\nprint(table.branches.list())\n";
export const PyConsistencyCheckoutLatest = "uri = str(tmp_db.uri)\nwriter_db = lancedb.connect(uri)\nreader_db = lancedb.connect(uri)\nwriter_table = writer_db.create_table(\n \"consistency_checkout_latest_table\", [{\"id\": 1}], mode=\"overwrite\"\n)\nreader_table = reader_db.open_table(\"consistency_checkout_latest_table\")\n\nwriter_table.add([{\"id\": 2}])\nrows_before_refresh = reader_table.count_rows()\nprint(f\"Rows before checkout_latest: {rows_before_refresh}\")\n\nreader_table.checkout_latest()\nrows_after_refresh = reader_table.count_rows()\nprint(f\"Rows after checkout_latest: {rows_after_refresh}\")\n";
export const PyConsistencyEventual = "from datetime import timedelta\n\nuri = str(tmp_db.uri)\nwriter_db = lancedb.connect(uri)\nreader_db = lancedb.connect(uri, read_consistency_interval=timedelta(seconds=3600))\nwriter_table = writer_db.create_table(\n \"consistency_eventual_table\", [{\"id\": 1}], mode=\"overwrite\"\n)\nreader_table = reader_db.open_table(\"consistency_eventual_table\")\nwriter_table.add([{\"id\": 2}])\nrows_after_write = reader_table.count_rows()\nprint(f\"Rows visible before eventual refresh interval: {rows_after_write}\")\n";
export const PyConsistencyStrong = "from datetime import timedelta\n\nuri = str(tmp_db.uri)\nwriter_db = lancedb.connect(uri)\nreader_db = lancedb.connect(uri, read_consistency_interval=timedelta(0))\nwriter_table = writer_db.create_table(\n \"consistency_strong_table\", [{\"id\": 1}], mode=\"overwrite\"\n)\nreader_table = reader_db.open_table(\"consistency_strong_table\")\nwriter_table.add([{\"id\": 2}])\nrows_after_write = reader_table.count_rows()\nprint(f\"Rows visible with strong consistency: {rows_after_write}\")\n";
export const PyCreateEmptyTable = "import pyarrow as pa\n\nschema = pa.schema(\n [\n pa.field(\"vector\", pa.list_(pa.float32(), 2)),\n pa.field(\"item\", pa.string()),\n pa.field(\"price\", pa.float32()),\n ]\n)\ndb = tmp_db\ntbl = db.create_table(\"test_empty_table\", schema=schema, mode=\"overwrite\")\n";
export const PyCreateEmptyTablePydantic = "from lancedb.pydantic import LanceModel, Vector\n\nclass Item(LanceModel):\n vector: Vector(2)\n item: str\n price: float\n\ndb = tmp_db\ntbl = db.create_table(\n \"test_empty_table_new\", schema=Item.to_arrow_schema(), mode=\"overwrite\"\n)\n";
export const PyCreateTableConflictHandling = "# Idempotent open: reuse the existing table if it exists.\n# The provided data is ignored; the schema is validated against the\n# existing table and a mismatch raises an error.\ntbl = db.create_table(\"conflict_table\", data, exist_ok=True)\n\n# Overwrite: drop the existing table and create a new one with the\n# provided data. This permanently discards the old table's data.\ntbl = db.create_table(\"conflict_table\", data, mode=\"overwrite\")\n";
export const PyCreateTableCustomSchema = "import pyarrow as pa\n\ncustom_schema = pa.schema(\n [\n pa.field(\"vector\", pa.list_(pa.float32(), 4)),\n pa.field(\"lat\", pa.float32()),\n pa.field(\"long\", pa.float32()),\n ]\n)\n\ndata = [\n {\"vector\": [1.1, 1.2, 1.3, 1.4], \"lat\": 45.5, \"long\": -122.7},\n {\"vector\": [0.2, 1.8, 0.4, 3.6], \"lat\": 40.1, \"long\": -74.1},\n]\ndb = tmp_db\ntbl = db.create_table(\n \"my_table_custom_schema\", data, schema=custom_schema, mode=\"overwrite\"\n)\n";
export const PyCreateTableFromArrow = "import numpy as np\nimport pyarrow as pa\n\ndim = 16\ntotal = 2\nschema = pa.schema(\n [pa.field(\"vector\", pa.list_(pa.float16(), dim)), pa.field(\"text\", pa.string())]\n)\ndata = pa.Table.from_arrays(\n [\n pa.array(\n [np.random.randn(dim).astype(np.float16) for _ in range(total)],\n pa.list_(pa.float16(), dim),\n ),\n pa.array([\"foo\", \"bar\"]),\n ],\n [\"vector\", \"text\"],\n)\ndb = tmp_db\ntbl = db.create_table(\"f16_tbl\", data, schema=schema, mode=\"overwrite\")\n";
export const PyCreateTableFromDicts = "data = [\n {\"vector\": [1.1, 1.2], \"lat\": 45.5, \"long\": -122.7},\n {\"vector\": [0.2, 1.8], \"lat\": 40.1, \"long\": -74.1},\n]\ndb = tmp_db\ndb.create_table(\"test_table\", data, mode=\"overwrite\")\ntbl = db[\"test_table\"]\ntbl.head()\n";
export const PyCreateTableFromIterator = "import pyarrow as pa\n\nschema = pa.schema(\n [\n pa.field(\"vector\", pa.list_(pa.float32(), 4)),\n pa.field(\"item\", pa.utf8()),\n pa.field(\"price\", pa.float32()),\n ]\n)\n\ndef make_batches():\n for i in range(5):\n yield pa.RecordBatch.from_arrays(\n [\n pa.array(\n [[3.1, 4.1, 5.1, 6.1], [5.9, 26.5, 4.7, 32.8]],\n pa.list_(pa.float32(), 4),\n ),\n pa.array([\"foo\", \"bar\"]),\n pa.array([10.0, 20.0]),\n ],\n [\"vector\", \"item\", \"price\"],\n )\n\ndb = tmp_db\ndb.create_table(\"batched_table\", make_batches(), schema=schema, mode=\"overwrite\")\n";
export const PyCreateTableFromPandas = "import pandas as pd\n\ndata = pd.DataFrame(\n {\n \"vector\": [[1.1, 1.2, 1.3, 1.4], [0.2, 1.8, 0.4, 3.6]],\n \"lat\": [45.5, 40.1],\n \"long\": [-122.7, -74.1],\n }\n)\ndb = tmp_db\ndb.create_table(\"my_table_pandas\", data, mode=\"overwrite\")\ndb[\"my_table_pandas\"].head()\n";
export const PyCreateTableFromPolars = "import polars as pl\n\ndata = pl.DataFrame(\n {\n \"vector\": [[3.1, 4.1], [5.9, 26.5]],\n \"item\": [\"foo\", \"bar\"],\n \"price\": [10.0, 20.0],\n }\n)\ndb = tmp_db\ntbl = db.create_table(\"my_table_pl\", data, mode=\"overwrite\")\n";
export const PyCreateTableFromPydantic = "from lancedb.pydantic import LanceModel, Vector\n\nclass Content(LanceModel):\n movie_id: int\n vector: Vector(128)\n genres: str\n title: str\n imdb_id: int\n\n @property\n def imdb_url(self) -> str:\n return f\"https://www.imdb.com/title/tt{self.imdb_id}\"\n\ndb = tmp_db\ntbl = db.create_table(\"movielens_small\", schema=Content, mode=\"overwrite\")\n";
export const PyCreateTableNestedSchema = "from lancedb.pydantic import LanceModel, Vector\n\n# --8<-- [start:tables_document_model]\nfrom pydantic import BaseModel\n\nclass Document(BaseModel):\n content: str\n source: str\n\n# --8<-- [end:tables_document_model]\n\nclass NestedSchema(LanceModel):\n id: str\n vector: Vector(1536)\n document: Document\n\ndb = tmp_db\ntbl = db.create_table(\"nested_table\", schema=NestedSchema, mode=\"overwrite\")\n";
export const PyDeleteOperation = "# delete data\npredicate = \"id = 3\"\ntable.delete(predicate)\n";
export const PyDropColumnsMultiple = "# Remove the second temporary column\ntable.drop_columns([\"temp_col2\"])\n";
export const PyDropColumnsSingle = "# Remove the first temporary column\ntable.drop_columns([\"temp_col1\"])\n";
export const PyDropTable = "db = tmp_db\n# Create a table first\ndata = [{\"vector\": [1.1, 1.2], \"lat\": 45.5}]\ndb.create_table(\"my_table\", data, mode=\"overwrite\")\n\n# Drop the table\ndb.drop_table(\"my_table\")\n";
export const PyInsertIfNotExists = "import pyarrow as pa\n\ntable = db.create_table(\n \"users_example\",\n data=pa.table(\n {\n \"id\": [1, 2],\n \"name\": [\"Alice\", \"Bob\"],\n \"login_count\": [10, 20],\n }\n ),\n mode=\"overwrite\",\n)\n\nincoming_users = pa.table(\n {\n \"id\": [2, 3],\n \"name\": [\"Bobby\", \"Charlie\"],\n \"login_count\": [21, 5],\n }\n)\n\n(table.merge_insert(\"id\").when_not_matched_insert_all().execute(incoming_users))\n";
export const PyMergeDeleteMissingBySource = "import pyarrow as pa\n\ntable = db.create_table(\n \"users_example\",\n data=pa.table(\n {\n \"id\": [1, 2, 3],\n \"name\": [\"Alice\", \"Bob\", \"Charlie\"],\n \"login_count\": [10, 20, 5],\n }\n ),\n mode=\"overwrite\",\n)\n\nincoming_users = pa.table(\n {\n \"id\": [2, 3],\n \"name\": [\"Bobby\", \"Charlie\"],\n \"login_count\": [21, 5],\n }\n)\n\n(\n table.merge_insert(\"id\")\n .when_matched_update_all()\n .when_not_matched_insert_all()\n .when_not_matched_by_source_delete()\n .execute(incoming_users)\n)\n";
export const PyMergeMatchedUpdateOnly = "import pyarrow as pa\n\ntable = db.create_table(\n \"users_example\",\n data=pa.table(\n {\n \"id\": [1, 2],\n \"name\": [\"Alice\", \"Bob\"],\n \"login_count\": [10, 20],\n }\n ),\n mode=\"overwrite\",\n)\n\nincoming_users = pa.table(\n {\n \"id\": [2, 3],\n \"name\": [\"Bobby\", \"Charlie\"],\n \"login_count\": [21, 5],\n }\n)\n\n(table.merge_insert(\"id\").when_matched_update_all().execute(incoming_users))\n";
export const PyMergePartialColumns = "import pyarrow as pa\n\ntable = db.create_table(\n \"users_example\",\n data=pa.table(\n {\n \"id\": [1, 2],\n \"name\": [\"Alice\", \"Bob\"],\n \"login_count\": [10, 20],\n }\n ),\n mode=\"overwrite\",\n)\n\nincoming_users = pa.table(\n {\n \"id\": [2, 3],\n \"name\": [\"Bobby\", \"Charlie\"],\n }\n)\n\n(\n table.merge_insert(\"id\")\n .when_matched_update_all()\n .when_not_matched_insert_all()\n .execute(incoming_users)\n)\n";
export const PyMergeUpdateInsert = "import pyarrow as pa\n\ntable = db.create_table(\n \"users_example\",\n data=pa.table(\n {\n \"id\": [1, 2],\n \"name\": [\"Alice\", \"Bob\"],\n \"login_count\": [10, 20],\n }\n ),\n mode=\"overwrite\",\n)\n\nincoming_users = pa.table(\n {\n \"id\": [2, 3],\n \"name\": [\"Bobby\", \"Charlie\"],\n \"login_count\": [21, 5],\n }\n)\n\n(\n table.merge_insert(\"id\")\n .when_matched_update_all()\n .when_not_matched_insert_all()\n .execute(incoming_users)\n)\n";
export const PyOpenExistingTable = "db = tmp_db\n# Create a table first\ndata = [{\"vector\": [1.1, 1.2], \"lat\": 45.5, \"long\": -122.7}]\ndb.create_table(\"test_table\", data, mode=\"overwrite\")\n\n# List table names\nprint(db.list_tables().tables)\n\n# Open existing table\ntbl = db.open_table(\"test_table\")\n";
export const PySchemaAddSetup = "table_name = \"schema_evolution_add_example\"\nif data is None:\n data = [\n {\n \"id\": 1,\n \"name\": \"Laptop\",\n \"price\": 1200.00,\n \"vector\": np.random.random(128).tolist(),\n },\n {\n \"id\": 2,\n \"name\": \"Smartphone\",\n \"price\": 800.00,\n \"vector\": np.random.random(128).tolist(),\n },\n {\n \"id\": 3,\n \"name\": \"Headphones\",\n \"price\": 150.00,\n \"vector\": np.random.random(128).tolist(),\n },\n ]\ntable = tmp_db.create_table(table_name, data, mode=\"overwrite\")\n";
export const PySchemaAlterSetup = "table_name = \"schema_evolution_alter_example\"\nif data is None:\n data = [\n {\n \"id\": 1,\n \"name\": \"Laptop\",\n \"price\": 1200,\n \"discount_price\": 1080.0,\n \"vector\": np.random.random(128).tolist(),\n },\n {\n \"id\": 2,\n \"name\": \"Smartphone\",\n \"price\": 800,\n \"discount_price\": 720.0,\n \"vector\": np.random.random(128).tolist(),\n },\n ]\nschema = pa.schema(\n {\n \"id\": pa.int64(),\n \"name\": pa.string(),\n \"price\": pa.int32(),\n \"discount_price\": pa.float64(),\n \"vector\": pa.list_(pa.float32(), 128),\n }\n)\ntable = tmp_db.create_table(table_name, data, schema=schema, mode=\"overwrite\")\n";
export const PySchemaDropSetup = "if data is None:\n data = [\n {\n \"id\": 1,\n \"name\": \"Laptop\",\n \"price\": 1200.00,\n \"temp_col1\": \"X\",\n \"temp_col2\": 100,\n \"vector\": np.random.random(128).tolist(),\n },\n {\n \"id\": 2,\n \"name\": \"Smartphone\",\n \"price\": 800.00,\n \"temp_col1\": \"Y\",\n \"temp_col2\": 200,\n \"vector\": np.random.random(128).tolist(),\n },\n {\n \"id\": 3,\n \"name\": \"Headphones\",\n \"price\": 150.00,\n \"temp_col1\": \"Z\",\n \"temp_col2\": 300,\n \"vector\": np.random.random(128).tolist(),\n },\n ]\ntable = tmp_db.create_table(\"schema_evolution_drop_example\", data, mode=\"overwrite\")\n";
export const PySchemaFieldMetadataMerge = "# Set two metadata keys on the `category` field.\nres = table.update_field_metadata(\n {\"path\": \"category\", \"metadata\": {\"unit\": \"label\", \"pii\": \"false\"}}\n)\nprint(res.version)\n\n# Merge: add a new key, delete one with None, keep the rest.\ntable.update_field_metadata(\n {\"path\": \"category\", \"metadata\": {\"source\": \"import\", \"pii\": None}}\n)\n\n# Arrow stores field metadata as bytes.\nassert table.schema.field(\"category\").metadata == {\n b\"unit\": b\"label\",\n b\"source\": b\"import\",\n}\n";
export const PySchemaFieldMetadataReplace = "table.update_field_metadata(\n {\n \"path\": \"category\",\n \"metadata\": {\"owner\": \"search-team\"},\n \"replace\": True,\n }\n)\n";
export const PyTablesBasicConnect = "import lancedb\n\nuri = \"data/sample-lancedb\"\ndb = lancedb.connect(uri)\n";
export const PyTablesDocumentModel = "from pydantic import BaseModel\n\nclass Document(BaseModel):\n content: str\n source: str\n";
export const PyTablesImports = "import lancedb\nimport numpy as np\nimport pandas as pd\nimport pyarrow as pa\nimport pytest\nfrom numpy.random import randint, random\n";
export const PyTablesTzValidator = "from datetime import datetime\nfrom zoneinfo import ZoneInfo\n\nfrom lancedb.pydantic import LanceModel\nfrom pydantic import Field, ValidationError, ValidationInfo, field_validator\n\ntzname = \"America/New_York\"\ntz = ZoneInfo(tzname)\n\nclass TestModel(LanceModel):\n dt_with_tz: datetime = Field(json_schema_extra={\"tz\": tzname})\n\n @field_validator(\"dt_with_tz\")\n @classmethod\n def tz_must_match(cls, dt: datetime) -> datetime:\n assert dt.tzinfo == tz\n return dt\n\nok = TestModel(dt_with_tz=datetime.now(tz))\n\ntry:\n TestModel(dt_with_tz=datetime.now(ZoneInfo(\"Asia/Shanghai\")))\n assert 0 == 1, \"this should raise ValidationError\"\nexcept ValidationError:\n print(\"A ValidationError was raised.\")\n pass\n";
export const PyUpdateConnectEnterprise = "import lancedb\n\ndb = lancedb.connect(\n uri=\"db://your-project-slug\",\n api_key=\"your-api-key\",\n region=\"us-east-1\",\n)\n";
export const PyUpdateConnectLocal = "import lancedb\n\ndb = lancedb.connect(\"./data\")\n";
export const PyUpdateExampleTableSetup = "import pyarrow as pa\n\ntable = db.create_table(\n \"users_example\",\n data=pa.table(\n {\n \"id\": [1, 2],\n \"name\": [\"Alice\", \"Bob\"],\n \"login_count\": [10, 20],\n }\n ),\n mode=\"overwrite\",\n)\n";
export const PyUpdateOperation = "import pyarrow as pa\n\ntable = db.create_table(\n \"users_example\",\n data=pa.table(\n {\n \"id\": [1, 2],\n \"name\": [\"Alice\", \"Bob\"],\n \"login_count\": [10, 20],\n }\n ),\n mode=\"overwrite\",\n)\ntable.update(where=\"id = 2\", values={\"name\": \"Bobby\"})\n";
export const PyUpdateOptimizeCleanup = "from datetime import timedelta\n\ntable.optimize(cleanup_older_than=timedelta(days=1))\n";
export const PyUpdateUsingSql = "import pyarrow as pa\n\ntable = db.create_table(\n \"users_example\",\n data=pa.table(\n {\n \"id\": [1, 2],\n \"name\": [\"Alice\", \"Bob\"],\n \"login_count\": [10, 20],\n }\n ),\n mode=\"overwrite\",\n)\ntable.update(where=\"id = 2\", values_sql={\"login_count\": \"login_count + 1\"})\n";
export const PyVersioningAddData = "more_data = [\n {\n \"id\": 4,\n \"author\": \"Richard Daniel Sanchez\",\n \"quote\": \"That's the way the news goes!\",\n },\n {\"id\": 5, \"author\": \"Morty\", \"quote\": \"Aww geez, Rick!\"},\n]\ntable.add(more_data)\n";
export const PyVersioningBasicSetup = "import pyarrow as pa\n\ndb = tmp_db\n\ntable_name = \"quotes_versioning_example\"\ndata = [\n {\"id\": 1, \"author\": \"Richard\", \"quote\": \"Wubba Lubba Dub Dub!\"},\n {\"id\": 2, \"author\": \"Morty\", \"quote\": \"Rick, what's going on?\"},\n {\n \"id\": 3,\n \"author\": \"Richard\",\n \"quote\": \"I turned myself into a pickle, Morty!\",\n },\n]\n\n# Define schema\nschema = pa.schema(\n [\n pa.field(\"id\", pa.int64()),\n pa.field(\"author\", pa.string()),\n pa.field(\"quote\", pa.string()),\n ]\n)\n\ntable = db.create_table(table_name, data, schema=schema, mode=\"overwrite\")\n";
export const PyVersioningCheckInitialVersion = "versions = table.list_versions()\ncurrent_version = table.version\nprint(f\"Number of versions after creation: {len(versions)}\")\nprint(f\"Current version: {current_version}\")\n";
export const PyVersioningCheckVersionsAfterMod = "versions = table.list_versions()\nversion_count_after_mod = len(versions)\nversion_after_mod = table.version\nprint(f\"Number of versions after modifications: {version_count_after_mod}\")\nprint(f\"Current version: {version_after_mod}\")\n";
export const PyVersioningCheckoutLatest = "table.checkout_latest()\n";
export const PyVersioningDeleteData = "table.delete(\"author = 'Morty'\")\nrows_after_deletion = table.count_rows()\nprint(f\"Number of rows after deletion: {rows_after_deletion}\")\n";
export const PyVersioningListAllVersions = "versions = table.list_versions()\nfor v in versions:\n print(f\"Version {v['version']}, created at {v['timestamp']}\")\n";
export const PyVersioningRollback = "table.restore(version_after_mod)\nversions = table.list_versions()\nversion_count_after_rollback = len(versions)\nprint(f\"Total number of versions after rollback: {version_count_after_rollback}\")\n";
export const PyVersioningTags = "# Create a tag pointing at a specific version\ntable.tags.create(\"baseline\", 1)\ntable.tags.create(\"with-edits\", table.version)\n\n# List all tags on this table\nprint(table.tags.list())\n\n# Look up the version a tag points at\nprint(table.tags.get_version(\"baseline\"))\n\n# Move an existing tag to a different version\ntable.tags.update(\"baseline\", 2)\n\n# Check out a version by tag name\ntable.checkout(\"baseline\")\nprint(table.version)\n\n# Delete a tag (does not delete the underlying version)\ntable.tags.delete(\"with-edits\")\n\n# Return to the latest version\ntable.checkout_latest()\n";
export const PyVersioningUpdateData = "table.update(where=\"author='Richard'\", values={\"author\": \"Richard Daniel Sanchez\"})\nrows_after_update = table.count_rows(\"author = 'Richard Daniel Sanchez'\")\nprint(f\"Rows updated to Richard Daniel Sanchez: {rows_after_update}\")\n";
export const TsAddColumnsCalculated = "// Add a discounted price column (10% discount)\nawait schemaAddTable.addColumns([\n {\n name: \"discounted_price\",\n valueSql: \"cast((price * 0.9) as float)\",\n },\n]);\n";
export const TsAddColumnsDefaultValues = "// Add a stock status column with default value\nawait schemaAddTable.addColumns([\n {\n name: \"in_stock\",\n valueSql: \"cast(true as boolean)\",\n },\n]);\n";
export const TsAddColumnsNullable = "// Add a nullable timestamp column\nawait schemaAddTable.addColumns([\n {\n name: \"last_ordered\",\n valueSql: \"cast(NULL as timestamp)\",\n },\n]);\n";
export const TsAddFeatureColumnsSql = "await schemaAddTable.addColumns([\n {\n name: \"price_per_id\",\n valueSql: \"cast(price / id as float)\",\n },\n {\n name: \"price_log\",\n valueSql: \"ln(price)\",\n },\n {\n name: \"price_score\",\n valueSql: \"cast(price / (price + 100.0) as float)\",\n },\n]);\n";
export const TsAlterColumnsDataType = "// Change price from int32 to int64 for larger numbers\nawait schemaAlterTable.alterColumns([\n { path: \"price\", dataType: new arrow.Int64() },\n]);\n";
export const TsAlterColumnsMultiple = "// Rename, change type, and make nullable in one operation\nawait schemaAlterTable.alterColumns([\n {\n path: \"sale_price\",\n rename: \"final_price\",\n dataType: new arrow.Float64(),\n nullable: true,\n },\n]);\n";
export const TsAlterColumnsNullable = "// Make the name column nullable\nawait schemaAlterTable.alterColumns([{ path: \"name\", nullable: true }]);\n";
export const TsAlterColumnsRename = "// Rename discount_price to sale_price\nawait schemaAlterTable.alterColumns([\n { path: \"discount_price\", rename: \"sale_price\" },\n]);\n";
export const TsAlterColumnsWithExpression = "// For custom transforms, create a new column from a SQL expression.\nconst expressionTable = await db.createTable(\n \"schema_evolution_expression_example\",\n [{ id: 1, price_text: \"$100\" }],\n { mode: \"overwrite\" },\n);\n\nawait expressionTable.addColumns([\n {\n name: \"price_numeric\",\n valueSql: \"cast(replace(price_text, '$', '') as int)\",\n },\n]);\nawait expressionTable.dropColumns([\"price_text\"]);\nawait expressionTable.alterColumns([\n { path: \"price_numeric\", rename: \"price\" },\n]);\n";
export const TsAlterVectorColumn = "const oldDim = 384;\nconst newDim = 1024;\nconst vectorSchema = new arrow.Schema([\n new arrow.Field(\"id\", new arrow.Int64()),\n new arrow.Field(\n \"embedding\",\n new arrow.FixedSizeList(\n oldDim,\n new arrow.Field(\"item\", new arrow.Float16(), true),\n ),\n true,\n ),\n]);\nconst vectorData = lancedb.makeArrowTable(\n [{ id: 1, embedding: Array.from({ length: oldDim }, () => Math.random()) }],\n { schema: vectorSchema },\n);\nconst vectorTable = await db.createTable(\"vector_alter_example\", vectorData, {\n mode: \"overwrite\",\n});\n\n// Changing FixedSizeList dimensions (384 -> 1024) is not supported via alterColumns.\n// Use addColumns + dropColumns + alterColumns(rename) to replace the column.\nawait vectorTable.addColumns([\n {\n name: \"embedding_v2\",\n valueSql: `arrow_cast(NULL, 'FixedSizeList(${newDim}, Float16)')`,\n },\n]);\nawait vectorTable.dropColumns([\"embedding\"]);\nawait vectorTable.alterColumns([{ path: \"embedding_v2\", rename: \"embedding\" }]);\n";
export const TsBranchCreate = "// Fork an isolated, writable branch from main's latest version.\n// `create` returns a table handle scoped to the new branch.\nconst branch = await branches.create(\"exp\");\n";
export const TsBranchDelete = "// Delete the branch and its branch-local history. Data on main is safe.\nawait branches.delete(\"exp\");\n";
export const TsBranchIndex = "// Build and validate indexes on a branch before using the configuration on\n// main.\nconst dev = await productBranches.create(\"index-dev\");\n\n// A vector (ANN) index and a full-text search index, both branch-scoped.\nawait dev.createIndex(\"vector\", {\n config: lancedb.Index.ivfPq({\n distanceType: \"cosine\",\n numPartitions: 1,\n numSubVectors: 2,\n }),\n});\nawait dev.createIndex(\"text\", { config: lancedb.Index.fts() });\n\n// Both indexes live only on the branch; main still has none.\nconsole.log((await dev.listIndices()).map((ix) => ix.name)); // branch: two indexes\nconsole.log((await products.listIndices()).map((ix) => ix.name)); // main: [] (untouched)\n";
export const TsBranchReopen = "// Reopen an existing branch by name from the table handle...\nconst checkedOut = await branches.checkout(\"exp\");\n// ...or open it directly from the database connection.\nconst branchHandle = await db.openTable(\n \"quotes_branches_example\",\n undefined,\n { branch: \"exp\" },\n);\nconsole.log(await checkedOut.countRows(), await branchHandle.countRows()); // both 4\n";
export const TsBranchUpsertToMain = "// This is a row-level upsert, not a merge of branch histories.\n// `mergeInsert` updates matching rows and inserts new rows using a stable\n// unique key. Filter the branch read if you only want to apply some results.\nconst rowsToApply = await candidate.toArrow();\nawait table\n .mergeInsert(\"id\")\n .whenMatchedUpdateAll() // update rows that already exist on main\n .whenNotMatchedInsertAll() // insert rows that are new on the branch\n .execute(rowsToApply);\n";
export const TsBranchWrite = "// Writes land on the branch handle only; main is left untouched.\nawait branch.add([{ id: 4, author: \"Lancelot\", quote: \"For the realm!\" }]);\nconsole.log(await branch.countRows()); // 4 rows on the branch\nconsole.log(await table.countRows()); // 3 rows; main is unaffected\n\n// List every branch, each mapped to its metadata (including its fork point).\nconsole.log(await branches.list());\n";
export const TsConsistencyCheckoutLatest = "const checkoutWriterDb = await lancedb.connect(databaseDir);\nconst checkoutReaderDb = await lancedb.connect(databaseDir);\nconst checkoutWriterTable = await checkoutWriterDb.createTable(\n \"consistency_checkout_latest_table\",\n [{ id: 1 }],\n { mode: \"overwrite\" },\n);\nconst checkoutReaderTable = await checkoutReaderDb.openTable(\n \"consistency_checkout_latest_table\",\n);\nawait checkoutWriterTable.add([{ id: 2 }]);\nconst rowsBeforeRefresh = await checkoutReaderTable.countRows();\nconsole.log(`Rows before checkoutLatest: ${rowsBeforeRefresh}`);\nawait checkoutReaderTable.checkoutLatest();\nconst rowsAfterRefresh = await checkoutReaderTable.countRows();\nconsole.log(`Rows after checkoutLatest: ${rowsAfterRefresh}`);\n";
export const TsConsistencyEventual = "const eventualWriterDb = await lancedb.connect(databaseDir);\nconst eventualReaderDb = await lancedb.connect(databaseDir, {\n readConsistencyInterval: 3600,\n});\nconst eventualWriterTable = await eventualWriterDb.createTable(\n \"consistency_eventual_table\",\n [{ id: 1 }],\n { mode: \"overwrite\" },\n);\nconst eventualReaderTable = await eventualReaderDb.openTable(\n \"consistency_eventual_table\",\n);\nawait eventualWriterTable.add([{ id: 2 }]);\nconst eventualRowsAfterWrite = await eventualReaderTable.countRows();\nconsole.log(\n `Rows visible before eventual refresh interval: ${eventualRowsAfterWrite}`,\n);\n";
export const TsConsistencyStrong = "const strongWriterDb = await lancedb.connect(databaseDir);\nconst strongReaderDb = await lancedb.connect(databaseDir, {\n readConsistencyInterval: 0,\n});\nconst strongWriterTable = await strongWriterDb.createTable(\n \"consistency_strong_table\",\n [{ id: 1 }],\n { mode: \"overwrite\" },\n);\nconst strongReaderTable = await strongReaderDb.openTable(\n \"consistency_strong_table\",\n);\nawait strongWriterTable.add([{ id: 2 }]);\nconst strongRowsAfterWrite = await strongReaderTable.countRows();\nconsole.log(`Rows visible with strong consistency: ${strongRowsAfterWrite}`);\n";
export const TsCreateEmptyTable = "const emptySchema = new arrow.Schema([\n new arrow.Field(\n \"vector\",\n new arrow.FixedSizeList(\n 2,\n new arrow.Field(\"item\", new arrow.Float32(), true),\n ),\n ),\n new arrow.Field(\"item\", new arrow.Utf8()),\n new arrow.Field(\"price\", new arrow.Float32()),\n]);\nconst emptyTable = await db.createEmptyTable(\n \"test_empty_table\",\n emptySchema,\n {\n mode: \"overwrite\",\n },\n);\n";
export const TsCreateTableConflictHandling = "// Idempotent open: reuse the existing table if it exists.\n// The provided data is ignored; the schema is validated against the\n// existing table and a mismatch raises an error.\nlet conflictTable = await db.createTable(\"conflict_table\", data, {\n existOk: true,\n});\n\n// Overwrite: drop the existing table and create a new one with the\n// provided data. This permanently discards the old table's data.\nconflictTable = await db.createTable(\"conflict_table\", data, {\n mode: \"overwrite\",\n});\n";
export const TsCreateTableCustomSchema = "const customSchema = new arrow.Schema([\n new arrow.Field(\n \"vector\",\n new arrow.FixedSizeList(\n 4,\n new arrow.Field(\"item\", new arrow.Float32(), true),\n ),\n ),\n new arrow.Field(\"lat\", new arrow.Float32()),\n new arrow.Field(\"long\", new arrow.Float32()),\n]);\n\nconst customSchemaData = lancedb.makeArrowTable(\n [\n { vector: [1.1, 1.2, 1.3, 1.4], lat: 45.5, long: -122.7 },\n { vector: [0.2, 1.8, 0.4, 3.6], lat: 40.1, long: -74.1 },\n ],\n { schema: customSchema },\n);\nconst customSchemaTable = await db.createTable(\n \"my_table_custom_schema\",\n customSchemaData,\n { mode: \"overwrite\" },\n);\n";
export const TsCreateTableFromArrow = "const arrowSchema = new arrow.Schema([\n new arrow.Field(\n \"vector\",\n new arrow.FixedSizeList(\n 16,\n new arrow.Field(\"item\", new arrow.Float32(), true),\n ),\n ),\n new arrow.Field(\"text\", new arrow.Utf8()),\n]);\nconst arrowData = lancedb.makeArrowTable(\n [\n { vector: Array(16).fill(0.1), text: \"foo\" },\n { vector: Array(16).fill(0.2), text: \"bar\" },\n ],\n { schema: arrowSchema },\n);\nconst arrowTable = await db.createTable(\"f32_tbl\", arrowData, {\n mode: \"overwrite\",\n});\n";
export const TsCreateTableFromDicts = "type Location = {\n vector: number[];\n lat: number;\n long: number;\n};\n\nconst data: Location[] = [\n { vector: [1.1, 1.2], lat: 45.5, long: -122.7 },\n { vector: [0.2, 1.8], lat: 40.1, long: -74.1 },\n];\nconst table = await db.createTable(\"test_table\", data, {\n mode: \"overwrite\",\n});\n";
export const TsCreateTableFromIterator = "const batchSchema = new arrow.Schema([\n new arrow.Field(\n \"vector\",\n new arrow.FixedSizeList(\n 4,\n new arrow.Field(\"item\", new arrow.Float32(), true),\n ),\n ),\n new arrow.Field(\"item\", new arrow.Utf8()),\n new arrow.Field(\"price\", new arrow.Float32()),\n]);\n\nconst tableForBatches = await db.createEmptyTable(\n \"batched_table\",\n batchSchema,\n {\n mode: \"overwrite\",\n },\n);\n\nconst rows = Array.from({ length: 10 }, (_, i) => ({\n vector: [i + 0.1, i + 0.2, i + 0.3, i + 0.4],\n item: `item-${i + 1}`,\n price: (i + 1) * 10,\n}));\n\nconst chunkSize = 2;\nfor (let i = 0; i < rows.length; i += chunkSize) {\n const batch = lancedb.makeArrowTable(rows.slice(i, i + chunkSize), {\n schema: batchSchema,\n });\n await tableForBatches.add(batch);\n}\n";
export const TsDeleteOperation = "// delete data\nconst predicate = \"id = 3\";\nawait table.delete(predicate);\n";
export const TsDropColumnsMultiple = "// Remove the second temporary column\nawait schemaDropTable.dropColumns([\"temp_col2\"]);\n";
export const TsDropColumnsSingle = "// Remove the first temporary column\nawait schemaDropTable.dropColumns([\"temp_col1\"]);\n";
export const TsDropTable = "await db.createTable(\"my_table\", [{ vector: [1.1, 1.2], lat: 45.5 }], {\n mode: \"overwrite\",\n});\n\nawait db.dropTable(\"my_table\");\n";
export const TsInsertIfNotExists = "const table = await db.createTable(\n \"users_example\",\n [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n ],\n { mode: \"overwrite\" },\n);\n\nconst incomingUsers = [\n { id: 2, name: \"Bobby\", login_count: 21 },\n { id: 3, name: \"Charlie\", login_count: 5 },\n];\n\nawait table\n .mergeInsert(\"id\")\n .whenNotMatchedInsertAll()\n .execute(incomingUsers);\n";
export const TsMergeDeleteMissingBySource = "const table = await db.createTable(\n \"users_example\",\n [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n { id: 3, name: \"Charlie\", login_count: 5 },\n ],\n { mode: \"overwrite\" },\n);\n\nconst incomingUsers = [\n { id: 2, name: \"Bobby\", login_count: 21 },\n { id: 3, name: \"Charlie\", login_count: 5 },\n];\n\nawait table\n .mergeInsert(\"id\")\n .whenMatchedUpdateAll()\n .whenNotMatchedInsertAll()\n .whenNotMatchedBySourceDelete()\n .execute(incomingUsers);\n";
export const TsMergeMatchedUpdateOnly = "const table = await db.createTable(\n \"users_example\",\n [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n ],\n { mode: \"overwrite\" },\n);\n\nconst incomingUsers = [\n { id: 2, name: \"Bobby\", login_count: 21 },\n { id: 3, name: \"Charlie\", login_count: 5 },\n];\n\nawait table\n .mergeInsert(\"id\")\n .whenMatchedUpdateAll()\n .execute(incomingUsers);\n";
export const TsMergePartialColumns = "const table = await db.createTable(\n \"users_example\",\n [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n ],\n { mode: \"overwrite\" },\n);\n\nconst incomingUsers = [\n { id: 2, name: \"Bobby\" },\n { id: 3, name: \"Charlie\" },\n];\n\nawait table\n .mergeInsert(\"id\")\n .whenMatchedUpdateAll()\n .whenNotMatchedInsertAll()\n .execute(incomingUsers);\n";
export const TsMergeUpdateInsert = "const table = await db.createTable(\n \"users_example\",\n [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n ],\n { mode: \"overwrite\" },\n);\n\nconst incomingUsers = [\n { id: 2, name: \"Bobby\", login_count: 21 },\n { id: 3, name: \"Charlie\", login_count: 5 },\n];\n\nawait table\n .mergeInsert(\"id\")\n .whenMatchedUpdateAll()\n .whenNotMatchedInsertAll()\n .execute(incomingUsers);\n";
export const TsOpenExistingTable = "const openTableData = [{ vector: [1.1, 1.2], lat: 45.5, long: -122.7 }];\nawait db.createTable(\"test_table_open\", openTableData, {\n mode: \"overwrite\",\n});\n\nconsole.log(await db.tableNames());\n\nconst openedTable = await db.openTable(\"test_table_open\");\n";
export const TsSchemaAddSetup = "const schemaAddData = [\n {\n id: 1,\n name: \"Laptop\",\n price: 1200.0,\n vector: Array.from({ length: 128 }, () => Math.random()),\n },\n {\n id: 2,\n name: \"Smartphone\",\n price: 800.0,\n vector: Array.from({ length: 128 }, () => Math.random()),\n },\n {\n id: 3,\n name: \"Headphones\",\n price: 150.0,\n vector: Array.from({ length: 128 }, () => Math.random()),\n },\n];\nconst schemaAddTable = await db.createTable(\n \"schema_evolution_add_example\",\n schemaAddData,\n { mode: \"overwrite\" },\n);\n";
export const TsSchemaAlterSetup = "const schemaAlter = new arrow.Schema([\n new arrow.Field(\"id\", new arrow.Int64()),\n new arrow.Field(\"name\", new arrow.Utf8()),\n new arrow.Field(\"price\", new arrow.Int32()),\n new arrow.Field(\"discount_price\", new arrow.Float64()),\n new arrow.Field(\n \"vector\",\n new arrow.FixedSizeList(\n 128,\n new arrow.Field(\"item\", new arrow.Float32(), true),\n ),\n ),\n]);\nconst schemaAlterData = lancedb.makeArrowTable(\n [\n {\n id: 1,\n name: \"Laptop\",\n price: 1200,\n discount_price: 1080.0,\n vector: Array.from({ length: 128 }, () => Math.random()),\n },\n {\n id: 2,\n name: \"Smartphone\",\n price: 800,\n discount_price: 720.0,\n vector: Array.from({ length: 128 }, () => Math.random()),\n },\n ],\n { schema: schemaAlter },\n);\nconst schemaAlterTable = await db.createTable(\n \"schema_evolution_alter_example\",\n schemaAlterData,\n { mode: \"overwrite\" },\n);\n";
export const TsSchemaDropSetup = "const schemaDropData = [\n {\n id: 1,\n name: \"Laptop\",\n price: 1200.0,\n temp_col1: \"X\",\n temp_col2: 100,\n vector: Array.from({ length: 128 }, () => Math.random()),\n },\n {\n id: 2,\n name: \"Smartphone\",\n price: 800.0,\n temp_col1: \"Y\",\n temp_col2: 200,\n vector: Array.from({ length: 128 }, () => Math.random()),\n },\n {\n id: 3,\n name: \"Headphones\",\n price: 150.0,\n temp_col1: \"Z\",\n temp_col2: 300,\n vector: Array.from({ length: 128 }, () => Math.random()),\n },\n];\nconst schemaDropTable = await db.createTable(\n \"schema_evolution_drop_example\",\n schemaDropData,\n { mode: \"overwrite\" },\n);\n";
export const TsSchemaFieldMetadataMerge = "// Set two metadata keys on the `category` field.\nconst res = await fieldMetadataTable.updateFieldMetadata([\n { path: \"category\", metadata: { unit: \"label\", pii: \"false\" } },\n]);\nconsole.log(res.version);\n\n// Merge: add a new key, delete one via null, keep the rest.\nawait fieldMetadataTable.updateFieldMetadata([\n { path: \"category\", metadata: { source: \"import\", pii: null } },\n]);\n";
export const TsSchemaFieldMetadataReplace = "await fieldMetadataTable.updateFieldMetadata([\n {\n path: \"category\",\n metadata: { owner: \"search-team\" },\n replace: true,\n },\n]);\n";
export const TsUpdateConnectEnterprise = "const db = await lancedb.connect(\"db://your-project-slug\", {\n apiKey: \"your-api-key\",\n region: \"us-east-1\",\n});\n";
export const TsUpdateConnectLocal = "const db = await lancedb.connect(\"./data\");\n";
export const TsUpdateExampleTableSetup = "const table = await db.createTable(\n \"users_example\",\n [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n ],\n { mode: \"overwrite\" },\n);\n";
export const TsUpdateOperation = "const table = await db.createTable(\n \"users_example\",\n [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n ],\n { mode: \"overwrite\" },\n);\nawait table.update({ where: \"id = 2\", values: { name: \"Bobby\" } });\n";
export const TsUpdateOptimizeCleanup = "const olderThan = new Date();\nolderThan.setDate(olderThan.getDate() - 1);\nawait table.optimize({ cleanupOlderThan: olderThan });\n";
export const TsUpdateUsingSql = "const table = await db.createTable(\n \"users_example\",\n [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n ],\n { mode: \"overwrite\" },\n);\nawait table.update({\n where: \"id = 2\",\n valuesSql: { login_count: \"login_count + 1\" },\n});\n";
export const TsVersioningAddData = "const moreData = [\n {\n id: 4,\n author: \"Richard Daniel Sanchez\",\n quote: \"That's the way the news goes!\",\n },\n { id: 5, author: \"Morty\", quote: \"Aww geez, Rick!\" },\n];\nawait table.add(moreData);\n";
export const TsVersioningBasicSetup = "const tableName = \"quotes_versioning_example\";\nconst data = [\n { id: 1, author: \"Richard\", quote: \"Wubba Lubba Dub Dub!\" },\n { id: 2, author: \"Morty\", quote: \"Rick, what's going on?\" },\n {\n id: 3,\n author: \"Richard\",\n quote: \"I turned myself into a pickle, Morty!\",\n },\n];\nconst table = await db.createTable(tableName, data, { mode: \"overwrite\" });\n";
export const TsVersioningCheckInitialVersion = "const versions = await table.listVersions();\nconst currentVersion = await table.version();\nconsole.log(`Number of versions after creation: ${versions.length}`);\nconsole.log(`Current version: ${currentVersion}`);\n";
export const TsVersioningCheckVersionsAfterMod = "const versionsAfterMod = await table.listVersions();\nconst versionCountAfterMod = versionsAfterMod.length;\nconst versionAfterMod = await table.version();\nconsole.log(\n `Number of versions after modifications: ${versionCountAfterMod}`,\n);\nconsole.log(`Current version: ${versionAfterMod}`);\n";
export const TsVersioningCheckoutLatest = "await table.checkoutLatest();\n";
export const TsVersioningDeleteData = "await table.delete(\"author = 'Morty'\");\nconst rowsAfterDeletion = await table.countRows();\nconsole.log(`Number of rows after deletion: ${rowsAfterDeletion}`);\n";
export const TsVersioningListAllVersions = "const allVersions = await table.listVersions();\nfor (const v of allVersions) {\n console.log(`Version ${v.version}, created at ${v.timestamp}`);\n}\n";
export const TsVersioningRollback = "await table.checkout(versionAfterMod);\nawait table.restore();\nconst versionsAfterRollback = await table.listVersions();\nconst versionCountAfterRollback = versionsAfterRollback.length;\nconsole.log(\n `Total number of versions after rollback: ${versionCountAfterRollback}`,\n);\n";
export const TsVersioningTags = "const tags = await tagsTable.tags();\n\n// Create a tag pointing at a specific version\nawait tags.create(\"baseline\", 1);\nawait tags.create(\"with-edits\", await tagsTable.version());\n\n// List all tags on this table\nconsole.log(await tags.list());\n\n// Look up the version a tag points at\nconsole.log(await tags.getVersion(\"baseline\"));\n\n// Move an existing tag to a different version\nawait tags.update(\"baseline\", 2);\n\n// Check out a version by tag name\nawait tagsTable.checkout(\"baseline\");\nconsole.log(await tagsTable.version());\n\n// Delete a tag (does not delete the underlying version)\nawait tags.delete(\"with-edits\");\n\n// Return to the latest version\nawait tagsTable.checkoutLatest();\n";
export const TsVersioningUpdateData = "await table.update({\n where: \"author = 'Richard'\",\n values: { author: \"Richard Daniel Sanchez\" },\n});\nconst rowsAfterUpdate = await table.countRows(\n \"author = 'Richard Daniel Sanchez'\",\n);\nconsole.log(`Rows updated to Richard Daniel Sanchez: ${rowsAfterUpdate}`);\n";
export const RsAddColumnsCalculated = "// Add a discounted price column (10% discount)\nschema_add_table\n .add_columns(\n NewColumnTransform::SqlExpressions(vec![(\n \"discounted_price\".to_string(),\n \"cast((price * 0.9) as float)\".to_string(),\n )]),\n None,\n )\n .await\n .unwrap();\n";
export const RsAddColumnsDefaultValues = "// Add a stock status column with default value\nschema_add_table\n .add_columns(\n NewColumnTransform::SqlExpressions(vec![(\n \"in_stock\".to_string(),\n \"cast(true as boolean)\".to_string(),\n )]),\n None,\n )\n .await\n .unwrap();\n";
export const RsAddColumnsNullable = "// Add a nullable timestamp column\nschema_add_table\n .add_columns(\n NewColumnTransform::SqlExpressions(vec![(\n \"last_ordered\".to_string(),\n \"cast(NULL as timestamp)\".to_string(),\n )]),\n None,\n )\n .await\n .unwrap();\n";
export const RsAddFeatureColumnsSql = "schema_add_table\n .add_columns(\n NewColumnTransform::SqlExpressions(vec![\n (\n \"price_per_id\".to_string(),\n \"cast(price / id as float)\".to_string(),\n ),\n (\"price_log\".to_string(), \"ln(price)\".to_string()),\n (\n \"price_score\".to_string(),\n \"cast(price / (price + 100.0) as float)\".to_string(),\n ),\n ]),\n None,\n )\n .await\n .unwrap();\n";
export const RsAlterColumnsDataType = "// Change price from int32 to int64 for larger numbers\nschema_alter_table\n .alter_columns(&[ColumnAlteration::new(\"price\".to_string()).cast_to(DataType::Int64)])\n .await\n .unwrap();\n";
export const RsAlterColumnsMultiple = "// Rename, change type, and make nullable in one operation\nschema_alter_table\n .alter_columns(&[ColumnAlteration::new(\"sale_price\".to_string())\n .rename(\"final_price\".to_string())\n .cast_to(DataType::Float64)\n .set_nullable(true)])\n .await\n .unwrap();\n";
export const RsAlterColumnsNullable = "// Make the name column nullable\nschema_alter_table\n .alter_columns(&[ColumnAlteration::new(\"name\".to_string()).set_nullable(true)])\n .await\n .unwrap();\n";
export const RsAlterColumnsRename = "// Rename discount_price to sale_price\nschema_alter_table\n .alter_columns(&[ColumnAlteration::new(\"discount_price\".to_string())\n .rename(\"sale_price\".to_string())])\n .await\n .unwrap();\n";
export const RsAlterColumnsWithExpression = "// For custom transforms, create a new column from a SQL expression.\nlet expression_schema = Arc::new(Schema::new(vec![\n Field::new(\"id\", DataType::Int64, false),\n Field::new(\"price_text\", DataType::Utf8, false),\n]));\nlet expression_batch = RecordBatch::try_new(\n expression_schema.clone(),\n vec![\n Arc::new(Int64Array::from(vec![1])),\n Arc::new(StringArray::from(vec![\"$100\"])),\n ],\n)\n.unwrap();\nlet expression_reader: Box<dyn RecordBatchReader + Send> = Box::new(RecordBatchIterator::new(\n vec![Ok(expression_batch)].into_iter(),\n expression_schema.clone(),\n));\nlet expression_table = db\n .create_table(\"schema_evolution_expression_example\", expression_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\nexpression_table\n .add_columns(\n NewColumnTransform::SqlExpressions(vec![(\n \"price_numeric\".to_string(),\n \"cast(replace(price_text, '$', '') as int)\".to_string(),\n )]),\n None,\n )\n .await\n .unwrap();\nexpression_table.drop_columns(&[\"price_text\"]).await.unwrap();\nexpression_table\n .alter_columns(&[ColumnAlteration::new(\"price_numeric\".to_string())\n .rename(\"price\".to_string())])\n .await\n .unwrap();\n";
export const RsAlterVectorColumn = "let old_dim = 384;\nlet new_dim = 1024;\nlet vector_schema = Arc::new(Schema::new(vec![\n Field::new(\"id\", DataType::Int64, false),\n Field::new(\n \"embedding\",\n DataType::FixedSizeList(\n Arc::new(Field::new(\"item\", DataType::Float32, true)),\n old_dim,\n ),\n true,\n ),\n]));\nlet vector_batch = RecordBatch::try_new(\n vector_schema.clone(),\n vec![\n Arc::new(Int64Array::from(vec![1])),\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![Some(vec![Some(0.1_f32); old_dim as usize])],\n old_dim,\n ),\n ),\n ],\n)\n.unwrap();\nlet vector_reader: Box<dyn RecordBatchReader + Send> =\n Box::new(RecordBatchIterator::new(vec![Ok(vector_batch)].into_iter(), vector_schema.clone()));\nlet vector_table = db\n .create_table(\"vector_alter_example\", vector_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\n// Changing FixedSizeList dimensions (384 -> 1024) is not supported via alter_columns.\n// Use add_columns + drop_columns + alter_columns(rename) to replace the column.\nvector_table\n .add_columns(\n NewColumnTransform::SqlExpressions(vec![(\n \"embedding_v2\".to_string(),\n format!(\"arrow_cast(NULL, 'FixedSizeList({}, Float32)')\", new_dim),\n )]),\n None,\n )\n .await\n .unwrap();\nvector_table.drop_columns(&[\"embedding\"]).await.unwrap();\nvector_table\n .alter_columns(&[ColumnAlteration::new(\"embedding_v2\".to_string())\n .rename(\"embedding\".to_string())])\n .await\n .unwrap();\n";
export const RsBranchCreate = "// Fork an isolated, writable branch from main's latest version.\n// `create_branch` returns a table handle scoped to the new branch.\nlet branch = branches_table\n .create_branch(\"exp\", Ref::Version(None, None))\n .await\n .unwrap();\n";
export const RsBranchDelete = "// Delete the branch and its branch-local history. Data on main is safe.\nbranches_table.delete_branch(\"exp\").await.unwrap();\n";
export const RsBranchIndex = "use lancedb::index::scalar::FtsIndexBuilder;\nuse lancedb::index::Index;\n\n// Build and validate indexes on a branch before using the configuration on\n// main.\nlet dev = products\n .create_branch(\"index-dev\", Ref::Version(None, None))\n .await\n .unwrap();\n\n// A vector (ANN) index and a full-text search index, both branch-scoped.\ndev.create_index(&[\"vector\"], Index::Auto)\n .execute()\n .await\n .unwrap();\ndev.create_index(&[\"text\"], Index::FTS(FtsIndexBuilder::default()))\n .execute()\n .await\n .unwrap();\n\n// Both indexes live only on the branch; main still has none.\nprintln!(\"Branch indexes: {}\", dev.list_indices().await.unwrap().len()); // 2\nprintln!(\"Main indexes: {}\", products.list_indices().await.unwrap().len()); // 0\n";
export const RsBranchReopen = "// Reopen an existing branch by name from the table handle...\nlet checked_out = branches_table.checkout_branch(\"exp\", None).await.unwrap();\n// ...or open it directly via the connection's builder.\nlet opened = db\n .open_table(\"quotes_branches_example\")\n .branch(\"exp\")\n .execute()\n .await\n .unwrap();\nprintln!(\n \"Reopened rows: {}, {}\",\n checked_out.count_rows(None).await.unwrap(),\n opened.count_rows(None).await.unwrap()\n); // both 4\n";
export const RsBranchUpsertToMain = "// This is a row-level upsert, not a merge of branch histories.\n// `merge_insert` updates matching rows and inserts new rows using a stable\n// unique key. Filter the branch read if you only want to apply some results.\nlet schema = candidate.schema().await.unwrap();\nlet batches = candidate\n .query()\n .execute()\n .await\n .unwrap()\n .try_collect::<Vec<_>>()\n .await\n .unwrap();\nlet rows_to_apply = RecordBatchIterator::new(batches.into_iter().map(Ok), schema);\n\nlet mut merge = branches_table.merge_insert(&[\"id\"]);\nmerge\n .when_matched_update_all(None) // update rows that already exist on main\n .when_not_matched_insert_all(); // insert rows that are new on the branch\nmerge.execute(Box::new(rows_to_apply)).await.unwrap();\n";
export const RsBranchWrite = "// Writes land on the branch handle only; main is left untouched.\nbranch\n .add(make_quotes_reader(vec![(4, \"Lancelot\", \"For the realm!\")]))\n .execute()\n .await\n .unwrap();\nprintln!(\"Branch rows: {}\", branch.count_rows(None).await.unwrap()); // 4\nprintln!(\"Main rows: {}\", branches_table.count_rows(None).await.unwrap()); // 3\n\n// List every branch, each mapped to its metadata (including its fork point).\nprintln!(\"Branches: {:?}\", branches_table.list_branches().await.unwrap());\n";
export const RsConsistencyCheckoutLatest = "let checkout_writer_db = connect(&db_uri).execute().await.unwrap();\nlet checkout_reader_db = connect(&db_uri).execute().await.unwrap();\nlet checkout_writer_table = checkout_writer_db\n .create_table(\n \"consistency_checkout_latest_table\",\n make_users_reader(vec![1], vec![\"Alice\"], None),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\nlet checkout_reader_table = checkout_reader_db\n .open_table(\"consistency_checkout_latest_table\")\n .execute()\n .await\n .unwrap();\ncheckout_writer_table\n .add(make_users_reader(vec![2], vec![\"Bob\"], None))\n .execute()\n .await\n .unwrap();\nlet rows_before_refresh = checkout_reader_table.count_rows(None).await.unwrap();\nprintln!(\"Rows before checkout_latest: {}\", rows_before_refresh);\ncheckout_reader_table.checkout_latest().await.unwrap();\nlet rows_after_refresh = checkout_reader_table.count_rows(None).await.unwrap();\nprintln!(\"Rows after checkout_latest: {}\", rows_after_refresh);\n";
export const RsConsistencyEventual = "let eventual_writer_db = connect(&db_uri).execute().await.unwrap();\nlet eventual_reader_db = connect(&db_uri)\n .read_consistency_interval(StdDuration::from_secs(3600))\n .execute()\n .await\n .unwrap();\nlet eventual_writer_table = eventual_writer_db\n .create_table(\n \"consistency_eventual_table\",\n make_users_reader(vec![1], vec![\"Alice\"], None),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\nlet eventual_reader_table = eventual_reader_db\n .open_table(\"consistency_eventual_table\")\n .execute()\n .await\n .unwrap();\neventual_writer_table\n .add(make_users_reader(vec![2], vec![\"Bob\"], None))\n .execute()\n .await\n .unwrap();\nlet eventual_rows_after_write = eventual_reader_table.count_rows(None).await.unwrap();\nprintln!(\n \"Rows visible before eventual refresh interval: {}\",\n eventual_rows_after_write\n);\n";
export const RsConsistencyStrong = "let strong_writer_db = connect(&db_uri).execute().await.unwrap();\nlet strong_reader_db = connect(&db_uri)\n .read_consistency_interval(StdDuration::from_secs(0))\n .execute()\n .await\n .unwrap();\nlet strong_writer_table = strong_writer_db\n .create_table(\n \"consistency_strong_table\",\n make_users_reader(vec![1], vec![\"Alice\"], None),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\nlet strong_reader_table = strong_reader_db\n .open_table(\"consistency_strong_table\")\n .execute()\n .await\n .unwrap();\nstrong_writer_table\n .add(make_users_reader(vec![2], vec![\"Bob\"], None))\n .execute()\n .await\n .unwrap();\nlet strong_rows_after_write = strong_reader_table.count_rows(None).await.unwrap();\nprintln!(\n \"Rows visible with strong consistency: {}\",\n strong_rows_after_write\n);\n";
export const RsCreateEmptyTable = "let empty_schema = Arc::new(Schema::new(vec![\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 2),\n false,\n ),\n Field::new(\"item\", DataType::Utf8, false),\n Field::new(\"price\", DataType::Float32, false),\n]));\nlet empty_table = db\n .create_empty_table(\"test_empty_table\", empty_schema)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsCreateTableConflictHandling = "// Idempotent open: reuse the existing table if it exists.\n// The provided data is ignored; the schema is validated against the\n// existing table and a mismatch raises an error.\nlet _conflict_table = db\n .create_table(\"conflict_table\", exist_ok_reader)\n .mode(CreateTableMode::exist_ok(|req| req))\n .execute()\n .await\n .unwrap();\n\n// Overwrite: drop the existing table and create a new one with the\n// provided data. This permanently discards the old table's data.\nlet conflict_table = db\n .create_table(\"conflict_table\", overwrite_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsCreateTableCustomSchema = "let custom_schema = Arc::new(Schema::new(vec![\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 4),\n false,\n ),\n Field::new(\"lat\", DataType::Float32, false),\n Field::new(\"long\", DataType::Float32, false),\n]));\n\nlet custom_batch = RecordBatch::try_new(\n custom_schema.clone(),\n vec![\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![\n Some(vec![Some(1.1), Some(1.2), Some(1.3), Some(1.4)]),\n Some(vec![Some(0.2), Some(1.8), Some(0.4), Some(3.6)]),\n ],\n 4,\n ),\n ),\n Arc::new(Float32Array::from(vec![45.5, 40.1])),\n Arc::new(Float32Array::from(vec![-122.7, -74.1])),\n ],\n)\n.unwrap();\nlet custom_reader: Box<dyn RecordBatchReader + Send> =\n Box::new(RecordBatchIterator::new(vec![Ok(custom_batch)].into_iter(), custom_schema.clone()));\nlet custom_table = db\n .create_table(\"my_table_custom_schema\", custom_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsCreateTableFromArrow = "let arrow_schema = Arc::new(Schema::new(vec![\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 16),\n false,\n ),\n Field::new(\"text\", DataType::Utf8, false),\n]));\n\nlet arrow_batch = RecordBatch::try_new(\n arrow_schema.clone(),\n vec![\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![Some(vec![Some(0.1); 16]), Some(vec![Some(0.2); 16])],\n 16,\n ),\n ),\n Arc::new(StringArray::from(vec![\"foo\", \"bar\"])),\n ],\n)\n.unwrap();\nlet arrow_reader: Box<dyn RecordBatchReader + Send> =\n Box::new(RecordBatchIterator::new(vec![Ok(arrow_batch)].into_iter(), arrow_schema.clone()));\nlet arrow_table = db\n .create_table(\"arrow_table_example\", arrow_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsCreateTableFromDicts = "struct Location {\n vector: [f32; 2],\n lat: f32,\n long: f32,\n}\n\nlet data = vec![\n Location {\n vector: [1.1, 1.2],\n lat: 45.5,\n long: -122.7,\n },\n Location {\n vector: [0.2, 1.8],\n lat: 40.1,\n long: -74.1,\n },\n];\n\nlet schema = Arc::new(Schema::new(vec![\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 2),\n false,\n ),\n Field::new(\"lat\", DataType::Float32, false),\n Field::new(\"long\", DataType::Float32, false),\n]));\n\nlet batch = RecordBatch::try_new(\n schema.clone(),\n vec![\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n data.iter()\n .map(|row| Some(row.vector.iter().copied().map(Some).collect::<Vec<_>>())),\n 2,\n ),\n ),\n Arc::new(Float32Array::from_iter_values(\n data.iter().map(|row| row.lat),\n )),\n Arc::new(Float32Array::from_iter_values(\n data.iter().map(|row| row.long),\n )),\n ],\n)\n.unwrap();\nlet reader: Box<dyn RecordBatchReader + Send> =\n Box::new(RecordBatchIterator::new(vec![Ok(batch)].into_iter(), schema.clone()));\nlet table = db\n .create_table(\"test_table\", reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsCreateTableFromIterator = "let batch_schema = Arc::new(Schema::new(vec![\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 4),\n false,\n ),\n Field::new(\"item\", DataType::Utf8, false),\n Field::new(\"price\", DataType::Float32, false),\n]));\n\nlet batches = (0..5)\n .map(|i| {\n RecordBatch::try_new(\n batch_schema.clone(),\n vec![\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![\n Some(vec![Some(3.1 + i as f32), Some(4.1), Some(5.1), Some(6.1)]),\n Some(vec![\n Some(5.9),\n Some(26.5 + i as f32),\n Some(4.7),\n Some(32.8),\n ]),\n ],\n 4,\n ),\n ),\n Arc::new(StringArray::from(vec![\n format!(\"item{}\", i * 2 + 1),\n format!(\"item{}\", i * 2 + 2),\n ])),\n Arc::new(Float32Array::from(vec![\n ((i * 2 + 1) * 10) as f32,\n ((i * 2 + 2) * 10) as f32,\n ])),\n ],\n )\n .unwrap()\n })\n .collect::<Vec<_>>();\n\nlet batch_reader: Box<dyn RecordBatchReader + Send> =\n Box::new(RecordBatchIterator::new(batches.into_iter().map(Ok), batch_schema.clone()));\nlet batch_table = db\n .create_table(\"batched_table\", batch_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsDeleteOperation = "// delete data\nlet predicate = \"id = 3\";\ntable.delete(predicate).await.unwrap();\n";
export const RsDropColumnsMultiple = "// Remove the second temporary column\nschema_drop_table.drop_columns(&[\"temp_col2\"]).await.unwrap();\n";
export const RsDropColumnsSingle = "// Remove the first temporary column\nschema_drop_table.drop_columns(&[\"temp_col1\"]).await.unwrap();\n";
export const RsDropTable = "let drop_schema = Arc::new(Schema::new(vec![\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 2),\n false,\n ),\n Field::new(\"lat\", DataType::Float32, false),\n]));\nlet drop_batch = RecordBatch::try_new(\n drop_schema.clone(),\n vec![\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![Some(vec![Some(1.1), Some(1.2)])],\n 2,\n ),\n ),\n Arc::new(Float32Array::from(vec![45.5])),\n ],\n)\n.unwrap();\nlet drop_reader: Box<dyn RecordBatchReader + Send> =\n Box::new(RecordBatchIterator::new(vec![Ok(drop_batch)].into_iter(), drop_schema.clone()));\ndb.create_table(\"my_table\", drop_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\ndb.drop_table(\"my_table\", &[]).await.unwrap();\n";
export const RsInsertIfNotExists = "let table = db\n .create_table(\n \"users_example\",\n make_users_reader(vec![1, 2], vec![\"Alice\", \"Bob\"], Some(vec![10, 20])),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\nlet mut merge_insert = table.merge_insert(&[\"id\"]);\nmerge_insert.when_not_matched_insert_all();\nmerge_insert\n .execute(make_users_reader(\n vec![2, 3],\n vec![\"Bobby\", \"Charlie\"],\n Some(vec![21, 5]),\n ))\n .await\n .unwrap();\n";
export const RsMergeDeleteMissingBySource = "let table = db\n .create_table(\n \"users_example\",\n make_users_reader(\n vec![1, 2, 3],\n vec![\"Alice\", \"Bob\", \"Charlie\"],\n Some(vec![10, 20, 5]),\n ),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\nlet mut merge_insert = table.merge_insert(&[\"id\"]);\nmerge_insert\n .when_matched_update_all(None)\n .when_not_matched_insert_all()\n .when_not_matched_by_source_delete(None);\nmerge_insert\n .execute(make_users_reader(\n vec![2, 3],\n vec![\"Bobby\", \"Charlie\"],\n Some(vec![21, 5]),\n ))\n .await\n .unwrap();\n";
export const RsMergeMatchedUpdateOnly = "let table = db\n .create_table(\n \"users_example\",\n make_users_reader(vec![1, 2], vec![\"Alice\", \"Bob\"], Some(vec![10, 20])),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\nlet mut merge_insert = table.merge_insert(&[\"id\"]);\nmerge_insert.when_matched_update_all(None);\nmerge_insert\n .execute(make_users_reader(\n vec![2, 3],\n vec![\"Bobby\", \"Charlie\"],\n Some(vec![21, 5]),\n ))\n .await\n .unwrap();\n";
export const RsMergePartialColumns = "let table = db\n .create_table(\n \"users_example\",\n make_users_reader(vec![1, 2], vec![\"Alice\", \"Bob\"], Some(vec![10, 20])),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\nlet mut merge_insert = table.merge_insert(&[\"id\"]);\nmerge_insert\n .when_matched_update_all(None)\n .when_not_matched_insert_all();\nmerge_insert\n .execute(make_users_reader(vec![2, 3], vec![\"Bobby\", \"Charlie\"], None))\n .await\n .unwrap();\n";
export const RsMergeUpdateInsert = "let table = db\n .create_table(\n \"users_example\",\n make_users_reader(vec![1, 2], vec![\"Alice\", \"Bob\"], Some(vec![10, 20])),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\nlet mut merge_insert = table.merge_insert(&[\"id\"]);\nmerge_insert\n .when_matched_update_all(None)\n .when_not_matched_insert_all();\nmerge_insert\n .execute(make_users_reader(\n vec![2, 3],\n vec![\"Bobby\", \"Charlie\"],\n Some(vec![21, 5]),\n ))\n .await\n .unwrap();\n";
export const RsOpenExistingTable = "let open_schema = Arc::new(Schema::new(vec![\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 2),\n false,\n ),\n Field::new(\"lat\", DataType::Float32, false),\n Field::new(\"long\", DataType::Float32, false),\n]));\nlet open_batch = RecordBatch::try_new(\n open_schema.clone(),\n vec![\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![Some(vec![Some(1.1), Some(1.2)])],\n 2,\n ),\n ),\n Arc::new(Float32Array::from(vec![45.5])),\n Arc::new(Float32Array::from(vec![-122.7])),\n ],\n)\n.unwrap();\nlet open_reader: Box<dyn RecordBatchReader + Send> =\n Box::new(RecordBatchIterator::new(vec![Ok(open_batch)].into_iter(), open_schema.clone()));\ndb.create_table(\"test_table\", open_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n\nprintln!(\"{:?}\", db.table_names().execute().await.unwrap());\n\nlet opened_table = db.open_table(\"test_table\").execute().await.unwrap();\n";
export const RsSchemaAddSetup = "let schema_add_schema = Arc::new(Schema::new(vec![\n Field::new(\"id\", DataType::Int64, false),\n Field::new(\"name\", DataType::Utf8, false),\n Field::new(\"price\", DataType::Float64, false),\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 128),\n false,\n ),\n]));\nlet schema_add_batch = RecordBatch::try_new(\n schema_add_schema.clone(),\n vec![\n Arc::new(Int64Array::from(vec![1, 2, 3])),\n Arc::new(StringArray::from(vec![\"Laptop\", \"Smartphone\", \"Headphones\"])),\n Arc::new(Float64Array::from(vec![1200.0, 800.0, 150.0])),\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![\n Some(vec![Some(0.1_f32); 128]),\n Some(vec![Some(0.2_f32); 128]),\n Some(vec![Some(0.3_f32); 128]),\n ],\n 128,\n ),\n ),\n ],\n)\n.unwrap();\nlet schema_add_reader: Box<dyn RecordBatchReader + Send> = Box::new(RecordBatchIterator::new(\n vec![Ok(schema_add_batch)].into_iter(),\n schema_add_schema.clone(),\n));\nlet schema_add_table = db\n .create_table(\"schema_evolution_add_example\", schema_add_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsSchemaAlterSetup = "let schema_alter_schema = Arc::new(Schema::new(vec![\n Field::new(\"id\", DataType::Int64, false),\n Field::new(\"name\", DataType::Utf8, false),\n Field::new(\"price\", DataType::Int32, false),\n Field::new(\"discount_price\", DataType::Float64, false),\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 128),\n false,\n ),\n]));\nlet schema_alter_batch = RecordBatch::try_new(\n schema_alter_schema.clone(),\n vec![\n Arc::new(Int64Array::from(vec![1, 2])),\n Arc::new(StringArray::from(vec![\"Laptop\", \"Smartphone\"])),\n Arc::new(Int32Array::from(vec![1200, 800])),\n Arc::new(Float64Array::from(vec![1080.0, 720.0])),\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![Some(vec![Some(0.1_f32); 128]), Some(vec![Some(0.2_f32); 128])],\n 128,\n ),\n ),\n ],\n)\n.unwrap();\nlet schema_alter_reader: Box<dyn RecordBatchReader + Send> = Box::new(RecordBatchIterator::new(\n vec![Ok(schema_alter_batch)].into_iter(),\n schema_alter_schema.clone(),\n));\nlet schema_alter_table = db\n .create_table(\"schema_evolution_alter_example\", schema_alter_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsSchemaDropSetup = "let schema_drop_schema = Arc::new(Schema::new(vec![\n Field::new(\"id\", DataType::Int64, false),\n Field::new(\"name\", DataType::Utf8, false),\n Field::new(\"price\", DataType::Float64, false),\n Field::new(\"temp_col1\", DataType::Utf8, false),\n Field::new(\"temp_col2\", DataType::Int32, false),\n Field::new(\n \"vector\",\n DataType::FixedSizeList(Arc::new(Field::new(\"item\", DataType::Float32, true)), 128),\n false,\n ),\n]));\nlet schema_drop_batch = RecordBatch::try_new(\n schema_drop_schema.clone(),\n vec![\n Arc::new(Int64Array::from(vec![1, 2, 3])),\n Arc::new(StringArray::from(vec![\"Laptop\", \"Smartphone\", \"Headphones\"])),\n Arc::new(Float64Array::from(vec![1200.0, 800.0, 150.0])),\n Arc::new(StringArray::from(vec![\"X\", \"Y\", \"Z\"])),\n Arc::new(Int32Array::from(vec![100, 200, 300])),\n Arc::new(\n FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(\n vec![\n Some(vec![Some(0.1_f32); 128]),\n Some(vec![Some(0.2_f32); 128]),\n Some(vec![Some(0.3_f32); 128]),\n ],\n 128,\n ),\n ),\n ],\n)\n.unwrap();\nlet schema_drop_reader: Box<dyn RecordBatchReader + Send> = Box::new(RecordBatchIterator::new(\n vec![Ok(schema_drop_batch)].into_iter(),\n schema_drop_schema.clone(),\n));\nlet schema_drop_table = db\n .create_table(\"schema_evolution_drop_example\", schema_drop_reader)\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsSchemaFieldMetadataMerge = "// Set two metadata keys on the `category` field.\nlet res = field_metadata_table\n .update_field_metadata(&[FieldMetadataUpdate::new(\"category\")\n .set(\"unit\", \"label\")\n .set(\"pii\", \"false\")])\n .await\n .unwrap();\nprintln!(\"version: {}\", res.version);\n\n// Merge: add a new key, delete one with `.remove`, keep the rest.\nfield_metadata_table\n .update_field_metadata(&[FieldMetadataUpdate::new(\"category\")\n .set(\"source\", \"import\")\n .remove(\"pii\")])\n .await\n .unwrap();\n";
export const RsSchemaFieldMetadataReplace = "field_metadata_table\n .update_field_metadata(&[FieldMetadataUpdate::new(\"category\")\n .set(\"owner\", \"search-team\")\n .replace()])\n .await\n .unwrap();\n";
export const RsUpdateConnectEnterprise = "let uri = \"db://your-project-slug\";\nlet api_key = \"your-api-key\";\nlet region = \"us-east-1\";\n";
export const RsUpdateConnectLocal = "let db = connect(\"./data\").execute().await.unwrap();\n";
export const RsUpdateExampleTableSetup = "let table = db\n .create_table(\n \"users_example\",\n make_users_reader(vec![1, 2], vec![\"Alice\", \"Bob\"], Some(vec![10, 20])),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsUpdateMakeUsersReader = "fn make_users_reader(\n ids: Vec<i64>,\n names: Vec<&str>,\n login_counts: Option<Vec<i64>>,\n) -> Box<dyn RecordBatchReader + Send> {\n let mut fields = vec![\n Field::new(\"id\", DataType::Int64, false),\n Field::new(\"name\", DataType::Utf8, false),\n ];\n let mut columns: Vec<Arc<dyn Array>> =\n vec![Arc::new(Int64Array::from(ids)), Arc::new(StringArray::from(names))];\n\n if let Some(login_counts) = login_counts {\n fields.push(Field::new(\"login_count\", DataType::Int64, true));\n columns.push(Arc::new(Int64Array::from(login_counts)));\n }\n\n let schema = Arc::new(Schema::new(fields));\n let batch = RecordBatch::try_new(schema.clone(), columns).unwrap();\n let reader = RecordBatchIterator::new(vec![Ok(batch)].into_iter(), schema);\n Box::new(reader)\n}\n";
export const RsUpdateOperation = "let table = db\n .create_table(\n \"users_example\",\n make_users_reader(vec![1, 2], vec![\"Alice\", \"Bob\"], Some(vec![10, 20])),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\ntable\n .update()\n .only_if(\"id = 2\")\n .column(\"name\", \"'Bobby'\")\n .execute()\n .await\n .unwrap();\n";
export const RsUpdateOptimizeCleanup = "table\n .optimize(OptimizeAction::Prune {\n older_than: Some(Duration::days(1)),\n delete_unverified: None,\n error_if_tagged_old_versions: None,\n })\n .await\n .unwrap();\n";
export const RsUpdateUsingSql = "let table = db\n .create_table(\n \"users_example\",\n make_users_reader(vec![1, 2], vec![\"Alice\", \"Bob\"], Some(vec![10, 20])),\n )\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\ntable\n .update()\n .only_if(\"id = 2\")\n .column(\"login_count\", \"login_count + 1\")\n .execute()\n .await\n .unwrap();\n";
export const RsVersioningAddData = "let more_data = vec![\n (4, \"Richard Daniel Sanchez\", \"That's the way the news goes!\"),\n (5, \"Morty\", \"Aww geez, Rick!\"),\n];\ntable\n .add(make_quotes_reader(more_data))\n .execute()\n .await\n .unwrap();\n";
export const RsVersioningBasicSetup = "let table_name = \"quotes_versioning_example\";\nlet data = vec![\n (1, \"Richard\", \"Wubba Lubba Dub Dub!\"),\n (2, \"Morty\", \"Rick, what's going on?\"),\n (3, \"Richard\", \"I turned myself into a pickle, Morty!\"),\n];\n\nlet table = db\n .create_table(table_name, make_quotes_reader(data))\n .mode(CreateTableMode::Overwrite)\n .execute()\n .await\n .unwrap();\n";
export const RsVersioningCheckInitialVersion = "let versions = table.list_versions().await.unwrap();\nlet current_version = table.version().await.unwrap();\nprintln!(\"Number of versions after creation: {}\", versions.len());\nprintln!(\"Current version: {}\", current_version);\n";
export const RsVersioningCheckVersionsAfterMod = "let versions_after_mod = table.list_versions().await.unwrap();\nlet version_count_after_mod = versions_after_mod.len();\nlet version_after_mod = table.version().await.unwrap();\nprintln!(\n \"Number of versions after modifications: {}\",\n version_count_after_mod\n);\nprintln!(\"Current version: {}\", version_after_mod);\n";
export const RsVersioningCheckoutLatest = "table.checkout_latest().await.unwrap();\n";
export const RsVersioningDeleteData = "table.delete(\"author = 'Morty'\").await.unwrap();\nlet rows_after_deletion = table.count_rows(None).await.unwrap();\nprintln!(\"Number of rows after deletion: {}\", rows_after_deletion);\n";
export const RsVersioningListAllVersions = "let all_versions = table.list_versions().await.unwrap();\nfor v in &all_versions {\n println!(\"Version {}, created at {}\", v.version, v.timestamp);\n}\n";
export const RsVersioningMakeQuotesReader = "fn make_quotes_reader(rows: Vec<(i64, &str, &str)>) -> Box<dyn RecordBatchReader + Send> {\n let ids: Vec<i64> = rows.iter().map(|(id, _, _)| *id).collect();\n let authors: Vec<&str> = rows.iter().map(|(_, author, _)| *author).collect();\n let quotes: Vec<&str> = rows.iter().map(|(_, _, quote)| *quote).collect();\n\n let schema = Arc::new(Schema::new(vec![\n Field::new(\"id\", DataType::Int64, false),\n Field::new(\"author\", DataType::Utf8, false),\n Field::new(\"quote\", DataType::Utf8, false),\n ]));\n\n let batch = RecordBatch::try_new(\n schema.clone(),\n vec![\n Arc::new(Int64Array::from(ids)),\n Arc::new(StringArray::from(authors)),\n Arc::new(StringArray::from(quotes)),\n ],\n )\n .unwrap();\n let reader = RecordBatchIterator::new(vec![Ok(batch)].into_iter(), schema);\n Box::new(reader)\n}\n";
export const RsVersioningRollback = "table.checkout(version_after_mod).await.unwrap();\ntable.restore().await.unwrap();\nlet versions_after_rollback = table.list_versions().await.unwrap();\nlet version_count_after_rollback = versions_after_rollback.len();\nprintln!(\n \"Total number of versions after rollback: {}\",\n version_count_after_rollback\n);\n";
export const RsVersioningTags = "let mut tags = tags_table.tags().await.unwrap();\n\n// Create a tag pointing at a specific version\ntags.create(\"baseline\", 1).await.unwrap();\nlet current_version = tags_table.version().await.unwrap();\ntags.create(\"with-edits\", current_version).await.unwrap();\n\n// List all tags on this table\nlet all_tags = tags.list().await.unwrap();\nprintln!(\"Tags: {:?}\", all_tags);\n\n// Look up the version a tag points at\nlet baseline_version = tags.get_version(\"baseline\").await.unwrap();\nprintln!(\"baseline -> v{}\", baseline_version);\n\n// Move an existing tag to a different version\ntags.update(\"baseline\", 2).await.unwrap();\n\n// Check out a version by tag name (separate method in Rust)\ntags_table.checkout_tag(\"baseline\").await.unwrap();\nprintln!(\"Current version: {}\", tags_table.version().await.unwrap());\n\n// Delete a tag (does not delete the underlying version)\ntags.delete(\"with-edits\").await.unwrap();\n\n// Return to the latest version\ntags_table.checkout_latest().await.unwrap();\n";
export const RsVersioningUpdateData = "table\n .update()\n .only_if(\"author = 'Richard'\")\n .column(\"author\", \"'Richard Daniel Sanchez'\")\n .execute()\n .await\n .unwrap();\nlet rows_after_update = table\n .count_rows(Some(\"author = 'Richard Daniel Sanchez'\".to_string()))\n .await\n .unwrap();\nprintln!(\n \"Rows updated to Richard Daniel Sanchez: {}\",\n rows_after_update\n);\n";
Reference in New Issue View Git Blame Copy Permalink