mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-16 16:52:34 +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.
223 lines
6.9 KiB
TypeScript
223 lines
6.9 KiB
TypeScript
// SPDX-License-Identifier: Apache-2.0
|
|
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
|
|
|
import { expect, test } from "@jest/globals";
|
|
|
|
test("complete vector_search", async () => {
|
|
// --8<-- [start:vector_search_body]
|
|
const lancedb = await import("@lancedb/lancedb");
|
|
const { mkdtemp, rm } = await import("node:fs/promises");
|
|
const { tmpdir } = await import("node:os");
|
|
const { join } = await import("node:path");
|
|
const uri = await mkdtemp(join(tmpdir(), "lancedb-search-"));
|
|
try {
|
|
const db = await lancedb.connect(uri);
|
|
const table = await db.createTable("documents", [
|
|
{
|
|
id: 1,
|
|
text: "A puppy playing in the park",
|
|
category: "animals",
|
|
vector: [1.0, 0.0],
|
|
},
|
|
{
|
|
id: 2,
|
|
text: "A dog resting at home",
|
|
category: "animals",
|
|
vector: [0.9, 0.1],
|
|
},
|
|
{
|
|
id: 3,
|
|
text: "A guide to growing tomatoes",
|
|
category: "gardening",
|
|
vector: [0.0, 1.0],
|
|
},
|
|
]);
|
|
const rows = await table
|
|
.vectorSearch([1.0, 0.0])
|
|
.distanceType("l2")
|
|
.select(["id", "text", "_distance"])
|
|
.limit(2)
|
|
.toArray();
|
|
console.log(rows);
|
|
// --8<-- [end:vector_search_body]
|
|
expect(rows.map((row) => row.id)).toEqual([1, 2]);
|
|
expect(rows[0]._distance).toBe(0);
|
|
// --8<-- [start:vector_search_tail]
|
|
} finally {
|
|
await rm(uri, { recursive: true, force: true });
|
|
}
|
|
// --8<-- [end:vector_search_tail]
|
|
});
|
|
|
|
test("complete text_search", async () => {
|
|
// --8<-- [start:text_search_body]
|
|
const lancedb = await import("@lancedb/lancedb");
|
|
const { mkdtemp, rm } = await import("node:fs/promises");
|
|
const { tmpdir } = await import("node:os");
|
|
const { join } = await import("node:path");
|
|
const uri = await mkdtemp(join(tmpdir(), "lancedb-search-"));
|
|
try {
|
|
const db = await lancedb.connect(uri);
|
|
const table = await db.createTable("documents", [
|
|
{ id: 1, text: "A puppy playing in the park", category: "animals" },
|
|
{ id: 2, text: "A dog resting at home", category: "animals" },
|
|
{ id: 3, text: "A guide to growing tomatoes", category: "gardening" },
|
|
]);
|
|
await table.createIndex("text", { config: lancedb.Index.fts() });
|
|
const rows = await table
|
|
.query()
|
|
.fullTextSearch("puppy", { columns: ["text"] })
|
|
.select(["id", "text", "_score"])
|
|
.limit(2)
|
|
.toArray();
|
|
console.log(rows);
|
|
// --8<-- [end:text_search_body]
|
|
expect(rows.map((row) => row.id)).toEqual([1]);
|
|
expect(rows[0]._score).toBeGreaterThan(0);
|
|
// --8<-- [start:text_search_tail]
|
|
} finally {
|
|
await rm(uri, { recursive: true, force: true });
|
|
}
|
|
// --8<-- [end:text_search_tail]
|
|
});
|
|
|
|
test("complete hybrid_search", async () => {
|
|
// --8<-- [start:hybrid_search_body]
|
|
const lancedb = await import("@lancedb/lancedb");
|
|
const { mkdtemp, rm } = await import("node:fs/promises");
|
|
const { tmpdir } = await import("node:os");
|
|
const { join } = await import("node:path");
|
|
const uri = await mkdtemp(join(tmpdir(), "lancedb-search-"));
|
|
try {
|
|
const db = await lancedb.connect(uri);
|
|
const table = await db.createTable("documents", [
|
|
{
|
|
id: 1,
|
|
text: "A puppy playing in the park",
|
|
category: "animals",
|
|
vector: [1.0, 0.0],
|
|
},
|
|
{
|
|
id: 2,
|
|
text: "A dog resting at home",
|
|
category: "animals",
|
|
vector: [0.9, 0.1],
|
|
},
|
|
{
|
|
id: 3,
|
|
text: "A guide to growing tomatoes",
|
|
category: "gardening",
|
|
vector: [0.0, 1.0],
|
|
},
|
|
]);
|
|
await table.createIndex("text", { config: lancedb.Index.fts() });
|
|
const reranker = await lancedb.rerankers.RRFReranker.create();
|
|
const rows = await table
|
|
.vectorSearch([1.0, 0.0])
|
|
.fullTextSearch("puppy", { columns: ["text"] })
|
|
.rerank(reranker)
|
|
.limit(2)
|
|
.toArray();
|
|
console.log(rows);
|
|
// --8<-- [end:hybrid_search_body]
|
|
expect(rows.map((row) => row.id)).toEqual([1, 2]);
|
|
expect(rows[0]._relevance_score).toBeGreaterThan(rows[1]._relevance_score);
|
|
// --8<-- [start:hybrid_search_tail]
|
|
} finally {
|
|
await rm(uri, { recursive: true, force: true });
|
|
}
|
|
// --8<-- [end:hybrid_search_tail]
|
|
});
|
|
|
|
test("complete filter_search", async () => {
|
|
// --8<-- [start:filter_search_body]
|
|
const lancedb = await import("@lancedb/lancedb");
|
|
const { mkdtemp, rm } = await import("node:fs/promises");
|
|
const { tmpdir } = await import("node:os");
|
|
const { join } = await import("node:path");
|
|
const uri = await mkdtemp(join(tmpdir(), "lancedb-search-"));
|
|
try {
|
|
const db = await lancedb.connect(uri);
|
|
const table = await db.createTable("documents", [
|
|
{
|
|
id: 1,
|
|
text: "A puppy playing in the park",
|
|
category: "animals",
|
|
vector: [1.0, 0.0],
|
|
},
|
|
{
|
|
id: 2,
|
|
text: "A dog resting at home",
|
|
category: "animals",
|
|
vector: [0.9, 0.1],
|
|
},
|
|
{
|
|
id: 3,
|
|
text: "A guide to growing tomatoes",
|
|
category: "gardening",
|
|
vector: [0.0, 1.0],
|
|
},
|
|
]);
|
|
const rows = await table
|
|
.vectorSearch([0.0, 1.0])
|
|
.where("category = 'animals'")
|
|
.select(["id", "text", "category", "_distance"])
|
|
.limit(2)
|
|
.toArray();
|
|
console.log(rows);
|
|
// --8<-- [end:filter_search_body]
|
|
expect(rows.map((row) => row.id).sort()).toEqual([1, 2]);
|
|
expect(rows.every((row) => row.category === "animals")).toBe(true);
|
|
// --8<-- [start:filter_search_tail]
|
|
} finally {
|
|
await rm(uri, { recursive: true, force: true });
|
|
}
|
|
// --8<-- [end:filter_search_tail]
|
|
});
|
|
|
|
test("complete query_plan", async () => {
|
|
// --8<-- [start:query_plan_body]
|
|
const lancedb = await import("@lancedb/lancedb");
|
|
const { mkdtemp, rm } = await import("node:fs/promises");
|
|
const { tmpdir } = await import("node:os");
|
|
const { join } = await import("node:path");
|
|
const uri = await mkdtemp(join(tmpdir(), "lancedb-search-"));
|
|
try {
|
|
const db = await lancedb.connect(uri);
|
|
const table = await db.createTable("documents", [
|
|
{
|
|
id: 1,
|
|
text: "A puppy playing in the park",
|
|
category: "animals",
|
|
vector: [1.0, 0.0],
|
|
},
|
|
{
|
|
id: 2,
|
|
text: "A dog resting at home",
|
|
category: "animals",
|
|
vector: [0.9, 0.1],
|
|
},
|
|
{
|
|
id: 3,
|
|
text: "A guide to growing tomatoes",
|
|
category: "gardening",
|
|
vector: [0.0, 1.0],
|
|
},
|
|
]);
|
|
const query = table
|
|
.vectorSearch([1.0, 0.0])
|
|
.select(["id", "text", "_distance"])
|
|
.limit(2);
|
|
console.log("Plan:", await query.explainPlan());
|
|
console.log("Measured execution:", await query.analyzePlan());
|
|
const rows = await query.toArray();
|
|
console.log(rows);
|
|
// --8<-- [end:query_plan_body]
|
|
expect(rows.map((row) => row.id)).toEqual([1, 2]);
|
|
// --8<-- [start:query_plan_tail]
|
|
} finally {
|
|
await rm(uri, { recursive: true, force: true });
|
|
}
|
|
// --8<-- [end:query_plan_tail]
|
|
});
|