rework: ChromaDB - update vector_store.py

vector_store.py

@@ -1,18 +1,16 @@
-"""Векторное хранилище Qdrant + эмбеддинги Ollama."""
+"""Векторное хранилище ChromaDB + эмбеддинги Ollama."""
 from __future__ import annotations
 
 import os
 from pathlib import Path
 
+from langchain_chroma import Chroma
 from langchain_core.documents import Document
 from langchain_ollama import OllamaEmbeddings
-from langchain_qdrant import QdrantVectorStore
 from langchain_text_splitters import RecursiveCharacterTextSplitter
-from qdrant_client import QdrantClient
-from qdrant_client.http.models import Distance, VectorParams
 
 COLLECTION_NAME = "knowledge_base"
-QDRANT_PATH = os.getenv("QDRANT_PATH", "./qdrant_data")
+CHROMA_PATH = os.getenv("CHROMA_PATH", "./chroma_data")
 OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
 EMBED_MODEL = os.getenv("OLLAMA_EMBED_MODEL", "nomic-embed-text")
 
@@ -24,29 +22,12 @@ def get_embeddings() -> OllamaEmbeddings:
     )
 
 
-def get_qdrant_client() -> QdrantClient:
-    Path(QDRANT_PATH).mkdir(parents=True, exist_ok=True)
-    return QdrantClient(path=QDRANT_PATH)
-
-
-def _ensure_collection(client: QdrantClient, embeddings: OllamaEmbeddings) -> None:
-    if client.collection_exists(COLLECTION_NAME):
-        return
-    vector_size = len(embeddings.embed_query("dimension probe"))
-    client.create_collection(
+def get_vector_store() -> Chroma:
+    Path(CHROMA_PATH).mkdir(parents=True, exist_ok=True)
+    return Chroma(
         collection_name=COLLECTION_NAME,
-        vectors_config=VectorParams(size=vector_size, distance=Distance.COSINE),
-    )
-
-
-def get_vector_store() -> QdrantVectorStore:
-    client = get_qdrant_client()
-    embeddings = get_embeddings()
-    _ensure_collection(client, embeddings)
-    return QdrantVectorStore(
-        client=client,
-        collection_name=COLLECTION_NAME,
-        embedding=embeddings,
+        embedding_function=get_embeddings(),
+        persist_directory=CHROMA_PATH,
     )