diff --git a/vector_store.py b/vector_store.py
deleted file mode 100644
index 5e734d8..0000000
--- a/vector_store.py
+++ /dev/null
@@ -1,65 +0,0 @@
-"""Векторное хранилище Qdrant + эмбеддинги Ollama."""
-from __future__ import annotations
-
-import os
-
-from langchain_qdrant import QdrantVectorStore
-from langchain_core.documents import Document
-from langchain_ollama import OllamaEmbeddings
-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")
-OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
-EMBED_MODEL = os.getenv("OLLAMA_EMBED_MODEL", "nomic-embed-text")
-
-
-def get_embeddings() -> OllamaEmbeddings:
-    return OllamaEmbeddings(
-        model=EMBED_MODEL,
-        base_url=OLLAMA_BASE_URL,
-    )
-
-
-def get_vector_store() -> QdrantVectorStore:
-    client = QdrantClient(path=QDRANT_PATH)
-    collections = client.get_collections().collections
-    if not any(col.name == COLLECTION_NAME for col in collections):
-        client.create_collection(
-            collection_name=COLLECTION_NAME,
-            vectors_config=VectorParams(size=768, distance=Distance.COSINE),
-        )
-    return QdrantVectorStore(
-        client=client,
-        collection_name=COLLECTION_NAME,
-        embedding=get_embeddings(),
-    )
-
-
-def chunk_document(content: str, title: str) -> list[Document]:
-    splitter = RecursiveCharacterTextSplitter(
-        chunk_size=500,
-        chunk_overlap=100,
-    )
-    documents = splitter.create_documents(
-        texts=[content],
-        metadatas=[{"title": title}],
-    )
-    for index, doc in enumerate(documents):
-        doc.metadata["chunk_index"] = index
-        doc.metadata["source"] = title
-    return documents
-
-
-def add_document_to_store(content: str, title: str) -> int:
-    store = get_vector_store()
-    chunks = chunk_document(content, title)
-    store.add_documents(chunks)
-    return len(chunks)
-
-
-def search_store(query: str, max_results: int = 4) -> list[tuple[Document, float]]:
-    store = get_vector_store()
-    return store.similarity_search_with_score(query, k=max_results)