Use a custom embedding function

After you create and register a custom embedding function, you can use it when you create or retrieve a collection.

Here is an example:

import { SeekdbClient } from "seekdb";

const client = new SeekdbClient({
  host: "127.0.0.1",
  port: 2881,
  user: "root",
  password: "",
  database: "test",
});

// Create a collection with a custom embedding function
const ef = new MyCustomEmbeddingFunction();

const collection = await client.createCollection({
  name: "my_collection",
  configuration: {
    dimension: 384,
    distance: "cosine"
  },
  embeddingFunction: ef
});

// Retrieve a collection with a custom embedding function
const collection = await client.getCollection({
  name: "my_collection",
  embeddingFunction: ef
});

// Use the collection - documents will be automatically embedded
await collection.add({
  ids: ["doc1", "doc2"],
  documents: ["Document 1", "Document 2"],  // Vectors are automatically generated
  metadatas: [{ tag: "A" }, { tag: "B" }]
});

// Text-based query - query vector is automatically generated
const results = await collection.query({
  queryTexts: "My query",
  nResults: 10
});

Related operations

If you want to use other built-in functions or custom functions, you can refer to the following documentation to create and use custom functions:

• Default embedding functions
• Create a custom embedding function