feat: solution for 'Экзамен: RAG-агент с ChromaDB и веб-поиском'

This commit is contained in:
2026-06-30 00:39:05 +03:00
parent d6805973d6
commit c55f307e12
6 changed files with 226 additions and 26 deletions
+61
View File
@@ -0,0 +1,61 @@
import { Client } from "chromadb";
import { OpenAIEmbeddings } from "openai";
export class ChromaVectorStore {
constructor() {
const host = process.env.CHROMA_HOST || "localhost";
const port = process.env.CHROMA_PORT || "8000";
this.client = new Client({ path: `http://${host}:${port}` });
this.collectionName = "rag_collection";
this.collection = null;
}
async init() {
const collections = await this.client.getCollections();
const exists = collections.some((c) => c.name === this.collectionName);
if (!exists) {
this.collection = await this.client.createCollection({
name: this.collectionName,
metadata: { hnsw: { ef_construction: 128, M: 64 } },
});
} else {
this.collection = await this.client.getCollection({
name: this.collectionName,
});
}
}
async addDocuments(documents) {
if (!this.collection) await this.init();
const embeddings = await this._embedTexts(documents.map((d) => d.content));
const ids = documents.map((_, idx) => `doc_${Date.now()}_${idx}`);
await this.collection.add({
ids,
embeddings,
documents: documents.map((d) => d.content),
metadatas: documents.map((d) => d.metadata),
});
}
async query(queryText, topK = 5) {
if (!this.collection) await this.init();
const embedding = await this._embedTexts([queryText]);
const results = await this.collection.query({
queryEmbeddings: embedding,
nResults: topK,
});
return results.documents.map((doc, idx) => ({
content: doc,
score: results.distances[idx],
metadata: results.metadatas[idx],
}));
}
async _embedTexts(texts) {
const openai = new OpenAIEmbeddings({
apiKey: process.env.OPENAI_API_KEY,
});
const embeddings = await openai.embedTexts(texts);
return embeddings.data.map((d) => d.embedding);
}
}