Files
ekzamen-rag-agent-s-chromad…/src/vectorStore.js
T

58 lines
1.6 KiB
JavaScript

import { ChromaClient } from 'chromadb';
import { OpenAIEmbeddings } from 'langchain/embeddings/openai';
const chroma = new ChromaClient({
host: process.env.CHROMA_HOST || 'localhost',
port: parseInt(process.env.CHROMA_PORT, 10) || 8000,
});
const embeddings = new OpenAIEmbeddings({
openAIApiKey: process.env.OPENAI_API_KEY,
});
const COLLECTION_NAME = 'rag_collection';
/**
* Ensure the collection exists in ChromaDB.
*/
async function ensureCollection() {
const collections = await chroma.listCollections();
if (!collections.includes(COLLECTION_NAME)) {
await chroma.createCollection({ name: COLLECTION_NAME });
}
}
/**
* Add an array of documents to the vector store.
* @param {string[]} docs
*/
export async function addDocuments(docs) {
await ensureCollection();
const ids = docs.map((_, idx) => `doc-${Date.now()}-${idx}`);
const embeddingsResult = await embeddings.embedDocuments(docs);
await chroma.add({
collection_name: COLLECTION_NAME,
ids,
documents: docs,
embeddings: embeddingsResult,
});
}
/**
* Query the vector store for the most relevant documents.
* @param {string} queryText
* @param {number} nResults
* @returns {Promise<{documents: string[]}>}
*/
export async function query(queryText, nResults = 3) {
await ensureCollection();
const embedding = await embeddings.embedQuery(queryText);
const results = await chroma.query({
collection_name: COLLECTION_NAME,
query_embeddings: [embedding],
n_results: nResults,
});
// ChromaDB returns an array of objects; extract documents
const docs = results.documents || [];
return { documents: docs };
}