mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-17 01:02:28 +00:00
Brendan Clement
758f738b8c
This PR is part of the documentation revamp. Once the full set of PRs is merged, we’ll publish the combined site to staging for review before updating docs.lancedb.com. Ingestion, search and integration examples are incomplete or inconsistent across languages, and some guidance misstates SDK behavior. This brings the guides and their example sources together. It includes complete Python, TypeScript and Rust workflows, isolated provider and reranker examples, the Superlinked corrections, and guidance on retries that can duplicate writes. Stacked on #4491. Each MDX file has one PR owner. Rebase onto main after #4491 is squash-merged. Local assembly, Mint validation and link checks pass. Example code is unchanged from the previously validated package. Publication stays held through integration.
67 lines
23 KiB
Plaintext
67 lines
23 KiB
Plaintext
{/* Auto-generated by scripts/mdx_snippets_gen.py. Do not edit manually. */}
|
|
|
|
export const PyAddFromDataset = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n from pathlib import Path\n\n import pyarrow as pa\n import pyarrow.parquet as pq\n\n data_path = str(Path(uri) / \"input.parquet\")\n pq.write_table(pa.table({\"id\": [1, 2], \"name\": [\"Alice\", \"Bob\"]}), data_path)\n import pyarrow.dataset as ds\n\n dataset = ds.dataset(data_path, format=\"parquet\")\n table = db.create_table(\"my_table\", schema=dataset.schema, mode=\"overwrite\")\n table.add(dataset)\n\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyAddProgress = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\ndef report_progress(progress):\n print(f\"Rows written: {progress['output_rows']}\")\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n table = db.create_table(\"users\", [{\"id\": 1, \"name\": \"Alice\"}])\n table.add(\n [{\"id\": 2, \"name\": \"Bob\"}, {\"id\": 3, \"name\": \"Charlie\"}],\n progress=report_progress,\n )\n rows = sorted(table.search().to_list(), key=lambda row: row[\"id\"])\n print(\"After insertion:\", rows)\n";
|
|
|
|
export const PyAppendRows = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n table = db.create_table(\"users\", [{\"id\": 1, \"name\": \"Alice\"}])\n table.add([{\"id\": 2, \"name\": \"Bob\"}, {\"id\": 3, \"name\": \"Charlie\"}])\n rows = sorted(table.search().to_list(), key=lambda row: row[\"id\"])\n print(rows)\n";
|
|
|
|
export const PyCreateEmptyTable = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n schema = 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 )\n tbl = db.create_table(\"test_empty_table\", schema=schema, mode=\"overwrite\")\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyCreateEmptyTablePydantic = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n from lancedb.pydantic import LanceModel, Vector\n\n class Item(LanceModel):\n vector: Vector(2)\n item: str\n price: float\n\n tbl = db.create_table(\n \"test_empty_table_new\", schema=Item.to_arrow_schema(), mode=\"overwrite\"\n )\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyCreateTableConflictHandling = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n data = [{\"vector\": [1.1, 1.2], \"lat\": 45.5, \"long\": -122.7}]\n db.create_table(\"conflict_table\", data)\n # 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.\n tbl = db.create_table(\"conflict_table\", data, exist_ok=True)\n\n # Overwrite: replace the contents with the provided data.\n tbl = db.create_table(\"conflict_table\", data, mode=\"overwrite\")\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyCreateTableCustomSchema = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n custom_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\n data = [\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 tbl = db.create_table(\n \"my_table_custom_schema\", data, schema=custom_schema, mode=\"overwrite\"\n )\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyCreateTableFromArrow = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import numpy as np\n import pyarrow as pa\n\n dim = 16\n total = 2\n schema = pa.schema(\n [\n pa.field(\"vector\", pa.list_(pa.float16(), dim)),\n pa.field(\"text\", pa.string()),\n ]\n )\n data = 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 )\n tbl = db.create_table(\"f16_tbl\", data, schema=schema, mode=\"overwrite\")\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyCreateTableFromDicts = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n 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 ]\n db.create_table(\"test_table\", data, mode=\"overwrite\")\n tbl = db[\"test_table\"]\n tbl.head()\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyCreateTableFromIterator = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n schema = 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\n def 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\n table = db.create_table(\"batched_table\", schema=schema)\n table.add(make_batches())\n\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyCreateTableFromPandas = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pandas as pd\n\n data = 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 )\n db.create_table(\"my_table_pandas\", data, mode=\"overwrite\")\n db[\"my_table_pandas\"].head()\n";
|
|
|
|
export const PyCreateTableFromPolars = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import polars as pl\n\n data = 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 )\n tbl = db.create_table(\"my_table_pl\", data, mode=\"overwrite\")\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyCreateTableFromPydantic = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n from lancedb.pydantic import LanceModel, Vector\n\n class 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 tbl = db.create_table(\"movielens_small\", schema=Content, mode=\"overwrite\")\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyCreateTableNestedSchema = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n from lancedb.pydantic import LanceModel, Vector\n from pydantic import BaseModel\n\n class Document(BaseModel):\n content: str\n source: str\n\n class NestedSchema(LanceModel):\n id: str\n vector: Vector(1536)\n document: Document\n\n tbl = db.create_table(\"nested_table\", schema=NestedSchema, mode=\"overwrite\")\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyDeleteRows = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n table = db.create_table(\n \"users\",\n [\n {\"id\": 1, \"name\": \"Alice\"},\n {\"id\": 2, \"name\": \"Bob\"},\n {\"id\": 3, \"name\": \"Charlie\"},\n ],\n )\n predicate = \"id = 3\"\n print(\"Selected:\", table.search().where(predicate).to_list())\n table.delete(predicate)\n rows = sorted(table.search().to_list(), key=lambda row: row[\"id\"])\n print(\"Remaining:\", rows)\n";
|
|
|
|
export const PyDropTable = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n # Create a table first\n data = [{\"vector\": [1.1, 1.2], \"lat\": 45.5}]\n db.create_table(\"my_table\", data, mode=\"overwrite\")\n\n # Drop the table\n db.drop_table(\"my_table\")\n";
|
|
|
|
export const PyInsertIfNotExists = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n table = 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\n incoming_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\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyMergeDeleteMissingBySource = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n table = 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\n incoming_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\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyMergeMatchedUpdateOnly = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n table = 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\n incoming_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\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyMergePartialColumns = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n table = 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\n incoming_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\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyMergeUpdateInsert = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n table = 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\n incoming_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\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyOpenExistingTable = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n # Create a table first\n data = [{\"vector\": [1.1, 1.2], \"lat\": 45.5, \"long\": -122.7}]\n db.create_table(\"test_table\", data, mode=\"overwrite\")\n\n # List table names\n print(db.list_tables().tables)\n\n # Open existing table\n tbl = db.open_table(\"test_table\")\n\n print(\"Rows:\", tbl.count_rows())\n";
|
|
|
|
export const PyUpdateOperation = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n table = 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 table.update(where=\"id = 2\", values={\"name\": \"Bobby\"})\n\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyUpdateUsingSql = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n import pyarrow as pa\n\n table = 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 table.update(where=\"id = 2\", values_sql={\"login_count\": \"login_count + 1\"})\n\n print(\"Rows:\", table.count_rows())\n";
|
|
|
|
export const PyWriteWorkflow = "from tempfile import TemporaryDirectory\n\nimport lancedb\n\nwith TemporaryDirectory(prefix=\"lancedb-ingestion-\") as uri:\n db = lancedb.connect(uri)\n table = db.create_table(\n \"users\",\n [\n {\"id\": 1, \"name\": \"Alice\", \"login_count\": 10},\n {\"id\": 2, \"name\": \"Bob\", \"login_count\": 20},\n ],\n )\n table.add([{\"id\": 3, \"name\": \"Charlie\", \"login_count\": 5}])\n table.update(where=\"id = 2\", values={\"name\": \"Bobby\"})\n table.update(where=\"id = 2\", values_sql={\"login_count\": \"login_count + 1\"})\n (\n table.merge_insert(\"id\")\n .when_matched_update_all()\n .when_not_matched_insert_all()\n .execute(\n [\n {\"id\": 3, \"name\": \"Charlie\", \"login_count\": 6},\n {\"id\": 4, \"name\": \"Dana\", \"login_count\": 1},\n ]\n )\n )\n print(\"Rows selected for deletion:\", table.search().where(\"id = 4\").to_list())\n table.delete(\"id = 4\")\n rows = sorted(table.search().to_list(), key=lambda row: row[\"id\"])\n print(rows)\n";
|
|
|
|
export const TsAddProgressBody = "const lancedb = await import(\"@lancedb/lancedb\");\nconst { mkdtemp, rm } = await import(\"node:fs/promises\");\nconst { tmpdir } = await import(\"node:os\");\nconst { join } = await import(\"node:path\");\nconst uri = await mkdtemp(join(tmpdir(), \"lancedb-ingestion-\"));\ntry {\n const db = await lancedb.connect(uri);\n const table = await db.createTable(\"users\", [{ id: 1, name: \"Alice\" }]);\n await table.add(\n [\n { id: 2, name: \"Bob\" },\n { id: 3, name: \"Charlie\" },\n ],\n {\n progress: (progress) =>\n console.log(`Rows written: ${progress.outputRows}`),\n },\n );\n const rows = (await table.query().toArray()).sort((a, b) => a.id - b.id);\n console.log(\"After insertion:\", rows);\n";
|
|
|
|
export const TsAddProgressTail = "} finally {\n await rm(uri, { recursive: true, force: true });\n}\n";
|
|
|
|
export const TsDeleteRowsBody = "const lancedb = await import(\"@lancedb/lancedb\");\nconst { mkdtemp, rm } = await import(\"node:fs/promises\");\nconst { tmpdir } = await import(\"node:os\");\nconst { join } = await import(\"node:path\");\nconst uri = await mkdtemp(join(tmpdir(), \"lancedb-ingestion-\"));\ntry {\n const db = await lancedb.connect(uri);\n const table = await db.createTable(\"users\", [\n { id: 1, name: \"Alice\" },\n { id: 2, name: \"Bob\" },\n { id: 3, name: \"Charlie\" },\n ]);\n const predicate = \"id = 3\";\n console.log(\"Selected:\", await table.query().where(predicate).toArray());\n await table.delete(predicate);\n const rows = (await table.query().toArray()).sort((a, b) => a.id - b.id);\n console.log(\"Remaining:\", rows);\n";
|
|
|
|
export const TsDeleteRowsTail = "} finally {\n await rm(uri, { recursive: true, force: true });\n}\n";
|
|
|
|
export const TsWriteWorkflowBody = "const lancedb = await import(\"@lancedb/lancedb\");\nconst { mkdtemp, rm } = await import(\"node:fs/promises\");\nconst { tmpdir } = await import(\"node:os\");\nconst { join } = await import(\"node:path\");\n\nconst uri = await mkdtemp(join(tmpdir(), \"lancedb-ingestion-\"));\ntry {\n const db = await lancedb.connect(uri);\n const table = await db.createTable(\"users\", [\n { id: 1, name: \"Alice\", login_count: 10 },\n { id: 2, name: \"Bob\", login_count: 20 },\n ]);\n await table.add([{ id: 3, name: \"Charlie\", login_count: 5 }]);\n await table.update({ where: \"id = 2\", values: { name: \"Bobby\" } });\n await table.update({\n where: \"id = 2\",\n valuesSql: { login_count: \"login_count + 1\" },\n });\n await table\n .mergeInsert(\"id\")\n .whenMatchedUpdateAll()\n .whenNotMatchedInsertAll()\n .execute([\n { id: 3, name: \"Charlie\", login_count: 6 },\n { id: 4, name: \"Dana\", login_count: 1 },\n ]);\n console.log(\n \"Rows selected for deletion:\",\n await table.query().where(\"id = 4\").toArray(),\n );\n await table.delete(\"id = 4\");\n const rows = (await table.query().toArray()).sort((a, b) => a.id - b.id);\n console.log(rows);\n";
|
|
|
|
export const TsWriteWorkflowTail = "} finally {\n await rm(uri, { recursive: true, force: true });\n}\n";
|
|
|
|
export const RsWriteWorkflow = "use std::sync::Arc;\n\nuse arrow_array::{Int64Array, RecordBatch, RecordBatchIterator, RecordBatchReader, StringArray};\nuse arrow_schema::{DataType, Field, Schema};\nuse futures::TryStreamExt;\nuse lancedb::query::{ExecutableQuery, QueryBase};\n\nfn make_users_reader(rows: &[(i64, &str, i64)]) -> Box<dyn RecordBatchReader + Send> {\n let schema = Arc::new(Schema::new(vec![\n Field::new(\"id\", DataType::Int64, false),\n Field::new(\"name\", DataType::Utf8, false),\n Field::new(\"login_count\", DataType::Int64, false),\n ]));\n let batch = RecordBatch::try_new(\n schema.clone(),\n vec![\n Arc::new(Int64Array::from_iter_values(rows.iter().map(|r| r.0))),\n Arc::new(StringArray::from_iter_values(rows.iter().map(|r| r.1))),\n Arc::new(Int64Array::from_iter_values(rows.iter().map(|r| r.2))),\n ],\n )\n .unwrap();\n Box::new(RecordBatchIterator::new(\n vec![Ok(batch)].into_iter(),\n schema,\n ))\n}\n\n#[tokio::main]\nasync fn main() -> Result<(), Box<dyn std::error::Error>> {\n let directory = tempfile::tempdir()?;\n let db = lancedb::connect(directory.path().to_str().unwrap())\n .execute()\n .await?;\n let table = db\n .create_table(\n \"users\",\n make_users_reader(&[(1, \"Alice\", 10), (2, \"Bob\", 20)]),\n )\n .execute()\n .await?;\n table\n .add(make_users_reader(&[(3, \"Charlie\", 5)]))\n .execute()\n .await?;\n table\n .update()\n .only_if(\"id = 2\")\n .column(\"name\", \"'Bobby'\")\n .execute()\n .await?;\n table\n .update()\n .only_if(\"id = 2\")\n .column(\"login_count\", \"login_count + 1\")\n .execute()\n .await?;\n let mut merge = table.merge_insert(&[\"id\"]);\n merge\n .when_matched_update_all(None)\n .when_not_matched_insert_all();\n merge\n .execute(make_users_reader(&[(3, \"Charlie\", 6), (4, \"Dana\", 1)]))\n .await?;\n let selected: Vec<RecordBatch> = table\n .query()\n .only_if(\"id = 4\")\n .execute()\n .await?\n .try_collect()\n .await?;\n println!(\"Rows selected for deletion: {selected:?}\");\n table.delete(\"id = 4\").await?;\n let rows: Vec<RecordBatch> = table.query().execute().await?.try_collect().await?;\n println!(\"Remaining rows: {rows:?}\");\n assert_eq!(table.count_rows(None).await?, 3);\n assert_eq!(\n table\n .count_rows(Some(\n \"id = 2 AND name = 'Bobby' AND login_count = 21\".into()\n ))\n .await?,\n 1\n );\n assert_eq!(\n table\n .count_rows(Some(\"id = 3 AND login_count = 6\".into()))\n .await?,\n 1\n );\n Ok(())\n}\n";
|
|
|