mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-13 15:22:30 +00:00
Jack Ye
b21fb2a4dc
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.
173 lines
23 KiB
Plaintext
173 lines
23 KiB
Plaintext
{/* Auto-generated by scripts/mdx_snippets_gen.py. Do not edit manually. */}
|
|
|
|
export const PyBasicFts = "uri = \"data/sample-lancedb\"\ndb = lancedb.connect(uri)\n\ntable = db.create_table(\n \"my_table_fts\",\n data=[\n {\"vector\": [3.1, 4.1], \"text\": \"Frodo was a happy puppy\"},\n {\"vector\": [5.9, 26.5], \"text\": \"There are several kittens playing\"},\n ],\n mode=\"overwrite\",\n)\n\ntable.create_fts_index(\"text\")\ntable.search(\"puppy\").limit(10).select([\"text\"]).to_list()\n# [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]\n# ...\n";
|
|
|
|
export const PyBasicFtsAsync = "uri = \"data/sample-lancedb\"\nasync_db = await lancedb.connect_async(uri)\n\nasync_tbl = await async_db.create_table(\n \"my_table_fts_async\",\n data=[\n {\"vector\": [3.1, 4.1], \"text\": \"Frodo was a happy puppy\"},\n {\"vector\": [5.9, 26.5], \"text\": \"There are several kittens playing\"},\n ],\n mode=\"overwrite\",\n)\n\n# async API uses our native FTS algorithm\nawait async_tbl.create_index(\"text\", config=FTS())\nawait (await async_tbl.search(\"puppy\")).select([\"text\"]).limit(10).to_list()\n# [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]\n# ...\n";
|
|
|
|
export const PyBasicHybridSearch = "data = [\n {\"text\": \"rebel spaceships striking from a hidden base\"},\n {\"text\": \"have won their first victory against the evil Galactic Empire\"},\n {\"text\": \"during the battle rebel spies managed to steal secret plans\"},\n {\"text\": \"to the Empire's ultimate weapon the Death Star\"},\n]\nuri = \"data/sample-lancedb\"\ndb = lancedb.connect(uri)\ntable = db.create_table(\"documents\", schema=Documents)\n# ingest docs with auto-vectorization\ntable.add(data)\n# Create a fts index before the hybrid search\ntable.create_fts_index(\"text\")\n# hybrid search with default re-ranker\ntable.search(\"flower moon\", query_type=\"hybrid\").to_pandas()\n";
|
|
|
|
export const PyBasicHybridSearchAsync = "uri = \"data/sample-lancedb\"\nasync_db = await lancedb.connect_async(uri)\ndata = [\n {\"text\": \"rebel spaceships striking from a hidden base\"},\n {\"text\": \"have won their first victory against the evil Galactic Empire\"},\n {\"text\": \"during the battle rebel spies managed to steal secret plans\"},\n {\"text\": \"to the Empire's ultimate weapon the Death Star\"},\n]\nasync_tbl = await async_db.create_table(\"documents_async\", schema=Documents)\n# ingest docs with auto-vectorization\nawait async_tbl.add(data)\n# Create a fts index before the hybrid search\nawait async_tbl.create_index(\"text\", config=FTS())\ntext_query = \"flower moon\"\n# hybrid search with default re-ranker\nawait (await async_tbl.search(\"flower moon\", query_type=\"hybrid\")).to_pandas()\n";
|
|
|
|
export const PyBatchSearch = "# Load a batch of query embeddings\nquery_dataset = load_dataset(\n \"sunhaozhepy/ag_news_sbert_keywords_embeddings\", split=\"test[5000:5005]\"\n)\nquery_embeds = query_dataset[\"keywords_embeddings\"]\nbatch_results = table.search(query_embeds).limit(5).to_pandas()\nprint(batch_results)\n";
|
|
|
|
export const PyBruteForceSearch = "tbl.search(np.random.random((1536))).limit(3).to_list()\n";
|
|
|
|
export const PyBypassVectorIndex = "table.search(embedding).bypass_vector_index().limit(5).to_pandas()\n";
|
|
|
|
export const PyClassDefinition = "class Metadata(BaseModel):\n source: str\n timestamp: datetime\n\n\nclass Document(BaseModel):\n content: str\n meta: Metadata\n\n\nclass LanceSchema(LanceModel):\n id: str\n vector: Vector(1536)\n payload: Document\n";
|
|
|
|
export const PyClassDocuments = "class Documents(LanceModel):\n vector: Vector(embeddings.ndims()) = embeddings.VectorField()\n text: str = embeddings.SourceField()\n";
|
|
|
|
export const PyConfigureDistanceMetric = "tbl.search(np.random.random((1536))).distance_type(\"cosine\").limit(10).to_list()\n";
|
|
|
|
export const PyCreateTableAsyncWithNestedSchema = "# Let's add 100 sample rows to our dataset\ndata = [\n LanceSchema(\n id=f\"id{i}\",\n vector=np.random.randn(1536),\n payload=Document(\n content=f\"document{i}\",\n meta=Metadata(source=f\"source{i % 10}\", timestamp=datetime.now()),\n ),\n )\n for i in range(100)\n]\n\nasync_tbl = await async_db.create_table(\n \"documents_async\", data=data, mode=\"overwrite\"\n)\n";
|
|
|
|
export const PyCreateTableWithNestedSchema = "# Let's add 100 sample rows to our dataset\ndata = [\n LanceSchema(\n id=f\"id{i}\",\n vector=np.random.randn(1536),\n payload=Document(\n content=f\"document{i}\",\n meta=Metadata(source=f\"source{i % 10}\", timestamp=datetime.now()),\n ),\n )\n for i in range(100)\n]\n\n# Synchronous client\ntbl = db.create_table(\"documents\", data=data, mode=\"overwrite\")\n";
|
|
|
|
export const PyExactVsApproximateDistances = "# Indexed ANN search without refinement (fast, approximate `_distance`)\nfast_results = (\n table.search(embedding)\n .limit(10)\n .to_pandas()\n)\n\n# Recompute distances on full vectors for reranked candidates\nexact_distance_results = (\n table.search(embedding)\n .limit(10)\n .refine_factor(1)\n .to_pandas()\n)\n\n# Rerank a larger candidate set for better recall (higher latency)\nhigher_recall_results = (\n table.search(embedding)\n .limit(10)\n .refine_factor(20)\n .to_pandas()\n)\n";
|
|
|
|
export const PyExhaustiveSearch = "uri = \"data/sample-lancedb\"\ndb = lancedb.connect(uri)\ndata = [\n {\"vector\": row, \"item\": f\"item {i}\"}\n for i, row in enumerate(np.random.random((10_000, 1536)).astype(\"float32\"))\n]\ntbl = db.create_table(\"vector_search\", data=data, mode=\"overwrite\")\ntbl.search(np.random.random((1536))).limit(10).to_list()\n";
|
|
|
|
export const PyExhaustiveSearchAsync = "uri = \"data/sample-lancedb\"\nasync_db = await lancedb.connect_async(uri)\ndata = [\n {\"vector\": row, \"item\": f\"item {i}\"}\n for i, row in enumerate(np.random.random((10_000, 1536)).astype(\"float32\"))\n]\nasync_tbl = await async_db.create_table(\n \"vector_search_async\", data=data, mode=\"overwrite\"\n)\n(await (await async_tbl.search(np.random.random((1536)))).limit(10).to_list())\n";
|
|
|
|
export const PyExhaustiveSearchAsyncCosine = "(\n await (await async_tbl.search(np.random.random((1536))))\n .distance_type(\"cosine\")\n .limit(10)\n .to_list()\n)\n";
|
|
|
|
export const PyExhaustiveSearchCosine = "tbl.search(np.random.random((1536))).distance_type(\"cosine\").limit(10).to_list()\n";
|
|
|
|
export const PyFastSearch = "table.search(embedding, fast_search=True).limit(5).to_pandas()\n";
|
|
|
|
export const PyFtsConfigFolding = "table.create_fts_index(\n \"text\",\n language=\"French\",\n stem=True,\n ascii_folding=True,\n replace=True,\n)\n";
|
|
|
|
export const PyFtsConfigFoldingAsync = "await async_tbl.create_index(\n \"text\", config=FTS(language=\"French\", stem=True, ascii_folding=True)\n)\n";
|
|
|
|
export const PyFtsConfigStem = "table.create_fts_index(\"text\", tokenizer_name=\"en_stem\", replace=True)\n";
|
|
|
|
export const PyFtsConfigStemAsync = "await async_tbl.create_index(\n \"text\", config=FTS(language=\"English\", stem=True, remove_stop_words=True)\n)\n";
|
|
|
|
export const PyFtsIncrementalIndex = "table.add([{\"vector\": [3.1, 4.1], \"text\": \"Frodo was a happy puppy\"}])\ntable.optimize()\n";
|
|
|
|
export const PyFtsIncrementalIndexAsync = "await async_tbl.add([{\"vector\": [3.1, 4.1], \"text\": \"Frodo was a happy puppy\"}])\nawait async_tbl.optimize()\n";
|
|
|
|
export const PyFtsPostfiltering = "table.search(\"puppy\").limit(10).where(\"text='foo'\", prefilter=False).to_list()\n";
|
|
|
|
export const PyFtsPostfilteringAsync = "await (\n (await async_tbl.search(\"puppy\"))\n .limit(10)\n .where(\"text='foo'\")\n .postfilter()\n .to_list()\n)\n";
|
|
|
|
export const PyFtsPrefiltering = "table.search(\"puppy\").limit(10).where(\"text='foo'\", prefilter=True).to_list()\n";
|
|
|
|
export const PyFtsPrefilteringAsync = "await (await async_tbl.search(\"puppy\")).limit(10).where(\"text='foo'\").to_list()\n";
|
|
|
|
export const PyFtsWithPosition = "table.create_fts_index(\"text\", with_position=True, replace=True)\n";
|
|
|
|
export const PyFtsWithPositionAsync = "await async_tbl.create_index(\"text\", config=FTS(with_position=True))\n";
|
|
|
|
export const PyHybridSearchPassVectorText = "vector_query = [0.1, 0.2, 0.3, 0.4, 0.5]\ntext_query = \"flower moon\"\n(\n table.search(query_type=\"hybrid\")\n .vector(vector_query)\n .text(text_query)\n .limit(5)\n .to_pandas()\n)\n";
|
|
|
|
export const PyHybridSearchPassVectorTextAsync = "vector_query = [0.1, 0.2, 0.3, 0.4, 0.5]\ntext_query = \"flower moon\"\nawait (\n async_tbl.query()\n .nearest_to(vector_query)\n .nearest_to_text(text_query)\n .limit(5)\n .to_pandas()\n)\n";
|
|
|
|
export const PyImportDatetime = "from datetime import datetime\n";
|
|
|
|
export const PyImportEmbeddings = "from lancedb.embeddings import get_registry\n";
|
|
|
|
export const PyImportLancedb = "import lancedb\n";
|
|
|
|
export const PyImportLancedbFts = "from lancedb.index import FTS\n";
|
|
|
|
export const PyImportLancedbPydantic = "from lancedb.pydantic import Vector, LanceModel\n";
|
|
|
|
export const PyImportNumpy = "from lancedb.query import BoostQuery, MatchQuery\nimport numpy as np\nimport pyarrow as pa\n";
|
|
|
|
export const PyImportOpenai = "import openai\n";
|
|
|
|
export const PyImportOs = "import os\n";
|
|
|
|
export const PyImportPydanticBaseModel = "from pydantic import BaseModel\n";
|
|
|
|
export const PyIndexNestedColumn = "table.create_index(vector_column_name=\"image.embedding\")\n";
|
|
|
|
export const PyMultivectorSearch = "query_multi = np.random.random(size=(2, 256))\nresults_multi = tbl.search(query_multi).limit(5).to_pandas()\n";
|
|
|
|
export const PyOpenaiEmbeddings = "# Ingest embedding function in LanceDB table\n# Configuring the environment variable OPENAI_API_KEY\nif \"OPENAI_API_KEY\" not in os.environ:\n # OR set the key here as a variable\n openai.api_key = \"sk-...\"\nembeddings = get_registry().get(\"openai\").create()\n";
|
|
|
|
export const PySearchBinaryVectors = "import numpy as np\nimport pyarrow as pa\n\nschema = pa.schema(\n [\n pa.field(\"id\", pa.int64()),\n # for dim=256, lance stores every 8 bits in a byte\n # so the vector field should be a list of 256 / 8 = 32 bytes\n pa.field(\"vector\", pa.list_(pa.uint8(), 32)),\n ]\n)\ntbl = db.create_table(\"my_binary_vectors\", schema=schema)\n\ndata = []\nfor i in range(1024):\n vector = np.random.randint(0, 2, size=256)\n # pack the binary vector into bytes to save space\n packed_vector = np.packbits(vector)\n data.append(\n {\n \"id\": i,\n \"vector\": packed_vector,\n }\n )\ntbl.add(data)\n\nquery = np.random.randint(0, 2, size=256)\npacked_query = np.packbits(query)\ntbl.search(packed_query).distance_type(\"hamming\").to_arrow()\n";
|
|
|
|
export const PySearchDistanceRange = "query = np.random.random(256)\n\n# Search for the vectors within the range of [0.1, 0.5)\ntbl.search(query).distance_range(0.1, 0.5).to_arrow()\n\n# Search for the vectors with the distance less than 0.5\ntbl.search(query).distance_range(upper_bound=0.5).to_arrow()\n\n# Search for the vectors with the distance greater or equal to 0.1\ntbl.search(query).distance_range(lower_bound=0.1).to_arrow()\n";
|
|
|
|
export const PySearchResultAsList = "tbl.search(np.random.randn(1536)).to_list()\n";
|
|
|
|
export const PySearchResultAsPandas = "tbl.search(np.random.randn(1536)).to_pandas()\n";
|
|
|
|
export const PySearchResultAsPandasFlatten1 = "tbl.search(np.random.randn(1536)).to_pandas(flatten=1)\n";
|
|
|
|
export const PySearchResultAsPandasFlattenTrue = "tbl.search(np.random.randn(1536)).to_pandas(flatten=True)\n";
|
|
|
|
export const PySearchResultAsPyarrow = "tbl.search(np.random.randn(1536)).to_arrow()\n";
|
|
|
|
export const PySearchResultAsPydantic = "tbl.search(np.random.randn(1536)).to_pydantic(LanceSchema)\n";
|
|
|
|
export const PySearchResultAsyncAsList = "await (await async_tbl.search(np.random.randn(1536))).to_list()\n";
|
|
|
|
export const PySearchResultAsyncAsPandas = "await (await async_tbl.search(np.random.randn(1536))).to_pandas()\n";
|
|
|
|
export const PySearchResultAsyncAsPyarrow = "await (await async_tbl.search(np.random.randn(1536))).to_arrow()\n";
|
|
|
|
export const PySelectVectorColumn = "import pyarrow as pa\n\nschema = pa.schema([\n pa.field(\"id\", pa.int32()),\n pa.field(\n \"image\",\n pa.struct([pa.field(\"embedding\", pa.list_(pa.float32(), 2))]),\n ),\n])\ntable = db.create_table(\n \"nested\",\n data=[{\"id\": 0, \"image\": {\"embedding\": [0.0, 1.0]}}],\n schema=schema,\n)\n\n# Inferred: the only vector leaf is `image.embedding`.\ntable.search([0.0, 1.0]).limit(1).to_list()\n\n# Explicit: required when more than one vector column matches.\ntable.search([0.0, 1.0], vector_column_name=\"image.embedding\").limit(1).to_list()\n";
|
|
|
|
export const PyVectorSearchPostfilter = "results_post_filtered = (\n table.search(query_embed)\n .where(\"label > 1\", prefilter=False)\n .select([\"text\", \"keywords\", \"label\"])\n .limit(5)\n .to_pandas()\n)\n\nprint(\"Vector search results with post-filter:\")\nprint(results_post_filtered)\n";
|
|
|
|
export const PyVectorSearchPrefilter = "from datasets import load_dataset\n\n# Load query vector from dataset\nquery_dataset = load_dataset(\"sunhaozhepy/ag_news_sbert_keywords_embeddings\", split=\"test[5000:5001]\")\nprint(f\"Query keywords: {query_dataset[0]['keywords']}\")\nquery_embed = query_dataset[\"keywords_embeddings\"][0]\n\n# Open table and perform search\ntable_name = \"lancedb-enterprise-quickstart\"\ntable = db.open_table(table_name)\n\n# Vector search with filters (pre-filtering is the default)\nsearch_results = (\n table.search(query_embed)\n .where(\"label > 2\")\n .select([\"text\", \"keywords\", \"label\"])\n .limit(5)\n .to_pandas()\n)\n\nprint(\"Search results (with pre-filtering):\")\nprint(search_results)\n";
|
|
|
|
export const TsBatchSearch = "// Batch query\nconsole.log(\"Performing batch vector search...\");\nconst batchSize = 5;\nconst queryVectors = Array.from({ length: batchSize }, () =>\n Array.from({ length: dimensions }, () => Math.random() * 2 - 1),\n);\nlet batchQuery = table.search(queryVectors[0]) as lancedb.VectorQuery;\nfor (let i = 1; i < batchSize; i++) {\n batchQuery = batchQuery.addQueryVector(queryVectors[i]);\n}\nconst batchResults = await batchQuery\n .select([\"text\", \"keywords\", \"label\"])\n .limit(5)\n .toArray();\nconsole.log(\"Batch vector search results:\");\nconsole.log(batchResults);\n";
|
|
|
|
export const TsBinarySearch = "const tbl = await db.createTable(\"binary_vectors\", data, {\n mode: \"overwrite\",\n});\nawait tbl.createIndex(\"vector\", {\n config: lancedb.Index.ivfFlat({\n numPartitions: 10,\n distanceType: \"hamming\",\n }),\n});\n\nconst query = Array(32)\n .fill(1)\n .map(() => Math.floor(Math.random() * 255));\nconst results = await tbl.query().nearestTo(query).limit(10).toArray();\n";
|
|
|
|
export const TsBruteForceSearch = "const tbl = await db.openTable(\"my_vectors\");\n\nconst results1 = await tbl.search(Array(128).fill(1.2)).limit(3).toArray();\n";
|
|
|
|
export const TsBypassVectorIndex = "await table\n .query()\n .nearestTo(embedding)\n .bypassVectorIndex()\n .limit(5)\n .toArray();\n";
|
|
|
|
export const TsDistanceRange = "const results3 = await (\n tbl.search(Array(128).fill(1.2)) as lancedb.VectorQuery\n)\n .distanceType(\"cosine\")\n .distanceRange(0.1, 0.2)\n .limit(10)\n .toArray();\n";
|
|
|
|
export const TsExactVsApproximate = "// Indexed ANN search without refinement (fast, approximate `_distance`)\nconst fastResults = await (table.search(embedding) as lancedb.VectorQuery)\n .limit(10)\n .toArray();\n\n// Recompute distances on full vectors for reranked candidates\nconst exactDistanceResults = await (\n table.search(embedding) as lancedb.VectorQuery\n)\n .limit(10)\n .refineFactor(1)\n .toArray();\n\n// Rerank a larger candidate set for better recall (higher latency)\nconst higherRecallResults = await (\n table.search(embedding) as lancedb.VectorQuery\n)\n .limit(10)\n .refineFactor(20)\n .toArray();\n";
|
|
|
|
export const TsFastSearch = "await table\n .query()\n .nearestTo(embedding)\n .fastSearch()\n .limit(5)\n .toArray();\n";
|
|
|
|
export const TsImport = "import * as lancedb from \"@lancedb/lancedb\";\n";
|
|
|
|
export const TsImportBinUtil = "import { Field, FixedSizeList, Int32, Schema, Uint8 } from \"apache-arrow\";\n";
|
|
|
|
export const TsIndexNestedColumn = "await table.createIndex(\"image.embedding\");\n";
|
|
|
|
export const TsIngestBinaryData = "const schema = new Schema([\n new Field(\"id\", new Int32(), true),\n new Field(\"vec\", new FixedSizeList(32, new Field(\"item\", new Uint8()))),\n]);\nconst data = lancedb.makeArrowTable(\n Array(1_000)\n .fill(0)\n .map((_, i) => ({\n // the 256 bits would be store in 32 bytes,\n // if your data is already in this format, you can skip the packBits step\n id: i,\n vec: lancedb.packBits(Array(256).fill(i % 2)),\n })),\n { schema: schema },\n);\n\nconst tbl = await db.createTable(\"binary_table\", data);\nawait tbl.createIndex(\"vec\", {\n config: lancedb.Index.ivfFlat({\n numPartitions: 10,\n distanceType: \"hamming\",\n }),\n});\n";
|
|
|
|
export const TsSearch1 = "const db = await lancedb.connect(databaseDir);\nconst tbl = await db.openTable(\"my_vectors\");\n\nconst results1 = await tbl.search(Array(128).fill(1.2)).limit(10).toArray();\n";
|
|
|
|
export const TsSearch2 = "const results2 = await (\n tbl.search(Array(128).fill(1.2)) as lancedb.VectorQuery\n)\n .distanceType(\"cosine\")\n .limit(10)\n .toArray();\n";
|
|
|
|
export const TsSearchBinaryData = "const query = Array(32)\n .fill(1)\n .map(() => Math.floor(Math.random() * 255));\nconst results = await tbl.query().nearestTo(query).limit(10).toArrow();\n";
|
|
|
|
export const TsSelectVectorColumn = "const table = await db.openTable(\"nested\");\n\n// Inferred: LanceDB finds the single nested vector leaf automatically.\nawait table.query().nearestTo([0.0, 1.0]).limit(1).toArray();\n\n// Explicit: required when more than one vector column matches.\nawait table\n .query()\n .nearestTo([0.0, 1.0])\n .column(\"image.embedding\")\n .limit(1)\n .toArray();\n";
|
|
|
|
export const TsVectorSearchPostfilter = "const vectorResultsWithPostFilter = await (\n table.search(queryEmbed) as lancedb.VectorQuery\n)\n .where(\"label > 2\")\n .postfilter()\n .select([\"text\", \"keywords\", \"label\"])\n .limit(5)\n .toArray();\n\nconsole.log(\"Vector search results with post-filter:\");\nconsole.log(vectorResultsWithPostFilter);\n";
|
|
|
|
export const TsVectorSearchPrefilter = "// Generate a sample 768-dimension embedding vector (typical for BERT-based models)\n// In real applications, you would get this from an embedding model\nconst dimensions = 768;\nconst queryEmbed = Array.from(\n { length: dimensions },\n () => Math.random() * 2 - 1,\n);\n\n// Open table and perform search\nconst tableName = \"lancedb-enterprise-quickstart\";\nconst table = await db.openTable(tableName);\n\n// Vector search with filters (pre-filtering is the default)\nconst vectorResults = await table\n .search(queryEmbed)\n .where(\"label > 2\")\n .select([\"text\", \"keywords\", \"label\"])\n .limit(5)\n .toArray();\n\nconsole.log(\"Search results (with pre-filtering):\");\nconsole.log(vectorResults);\n";
|
|
|
|
export const RsBatchSearch = "// Search multiple query vectors in one call. Each result row carries a\n// `query_index` mapping it back to the query it matched.\nlet mut results = table\n .vector_search(&query_1)?\n .add_query_vector(&query_2)?\n .limit(5)\n .execute()\n .await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsBinarySearch = "// Binary vectors use `hamming` distance over the packed uint8 bytes.\nlet query: Arc<dyn Array> = Arc::new(UInt8Array::from(vec![1u8; NUM_BYTES as usize]));\nlet mut results = tbl\n .vector_search(query)?\n .distance_type(DistanceType::Hamming)\n .limit(10)\n .execute()\n .await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsBruteForceSearch = "// A plain vector search returns the top-k closest rows.\nlet mut results = table.vector_search(&query_vector)?.limit(3).execute().await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsBypassVectorIndex = "// Force an exhaustive (flat) scan for exact, ground-truth results.\nlet mut results = table\n .vector_search(&query_vector)?\n .bypass_vector_index()\n .limit(5)\n .execute()\n .await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsConfigureDistanceMetric = "// Use the same distance metric the index was trained with.\nlet mut results = table\n .vector_search(&query_vector)?\n .distance_type(DistanceType::Cosine)\n .limit(10)\n .execute()\n .await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsExactVsApproximate = "// Approximate ANN search (fast, distances may come from the index representation)\nlet mut fast_results = table.vector_search(&query_vector)?.limit(10).execute().await?;\nwhile let Some(batch) = fast_results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n\n// Rerank a larger candidate set on full vectors for better recall\nlet mut refined_results = table\n .vector_search(&query_vector)?\n .limit(10)\n .refine_factor(20)\n .execute()\n .await?;\nwhile let Some(batch) = refined_results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsFastSearch = "// Skip unindexed data for lower latency.\nlet mut results = table\n .vector_search(&query_vector)?\n .fast_search()\n .limit(5)\n .execute()\n .await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsSearchDistanceRange = "// Only return rows whose distance falls within [0.1, 0.5).\nlet mut results = table\n .vector_search(&query_vector)?\n .distance_range(Some(0.1), Some(0.5))\n .execute()\n .await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsVectorSearchPostfilter = "// Apply the filter after vector search by calling postfilter().\nlet mut results = table\n .vector_search(&query_vector)?\n .only_if(\"id > 100\")\n .postfilter()\n .select(Select::columns(&[\"id\"]))\n .limit(5)\n .execute()\n .await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|
|
export const RsVectorSearchPrefilter = "// Prefiltering is the default: the filter is applied before vector search.\nlet mut results = table\n .vector_search(&query_vector)?\n .only_if(\"id > 100\")\n .select(Select::columns(&[\"id\"]))\n .limit(5)\n .execute()\n .await?;\nwhile let Some(batch) = results.try_next().await? {\n println!(\"{:?}\", batch);\n}\n";
|
|
|