Удалить vector_store.py

vector_store.py

@@ -1,64 +0,0 @@
-"""
-Vector store implementation using ChromaDB.
-
-Provides methods to add documents and perform similarity search.
-"""
-import os
-from pathlib import Path
-from typing import List, Dict
-
-from chromadb import Client as ChromadbClient
-from chromadb.config import Settings
-from langchain_text_splitters import RecursiveCharacterTextSplitter
-from langchain_ollama import OllamaEmbeddings
-
-# Ensure persistent directory exists
-CHROMA_DIR = Path("./chroma_db")
-CHROMA_DIR.mkdir(parents=True, exist_ok=True)
-
-# Embedding model via Ollama
-embeddings = OllamaEmbeddings(model="nomic-embed-text")
-
-# Chroma client with persistence
-client = ChromadbClient(Settings(persist_directory=str(CHROMA_DIR)))
-collection_name = "knowledge"
-if collection_name not in client.list_collections():
-    client.create_collection(name=collection_name)
-col = client.get_or_create_collection(name=collection_name)
-
-# Chunker from chunker.py
-from chunker import chunker
-
-class VectorStore:
-    def add_documents(self, docs: List[str], metadatas: List[Dict]):
-        """Add documents to the collection.
-
-        Parameters
-        ----------
-        docs: list of raw text strings.
-        metadatas: list of metadata dicts corresponding to each doc.
-        """
-        # Split into chunks and embed
-        all_chunks = []
-        all_metadatas = []
-        for doc, meta in zip(docs, metadatas):
-            chunks = chunker.split_text(doc)
-            all_chunks.extend(chunks)
-            all_metadatas.extend([meta] * len(chunks))
-
-        # Generate embeddings via Ollama
-        embeds = embeddings.embed_documents(all_chunks)
-        ids = [f"chunk_{i}" for i in range(len(all_chunks))]
-        col.add(ids=ids, documents=all_chunks, metadatas=all_metadatas, embeddings=embeds)
-
-    def similarity_search(self, query: str, k: int = 5) -> List[Dict]:
-        """Return top-k similar chunks with metadata."""
-        results = col.query(
-            query_texts=[query],
-            n_results=k,
-            include=['documents', 'metadatas'],
-        )
-        # results is dict with keys documents, metadatas
-        docs = results["documents"][0]
-        metas = results["metadatas"][0]
-        return [{"content": d, "metadata": m} for d, m in zip(docs, metas)]