Решение готово к публикации: update vectorstore.py

vectorstore.py

@@ -2,7 +2,6 @@ from pathlib import Path
 from uuid import uuid4
 
 from langchain_chroma import Chroma, Settings
-
 from langchain_ollama import OllamaEmbeddings
 from langchain_core.documents import Document
 from langchain_text_splitters import RecursiveCharacterTextSplitter
@@ -14,12 +13,17 @@ OLLAMA_BASE_URL = "http://127.0.0.1:11434"
 
 
 def create_vectorstore(persist_directory: str = CHROMA_DIR):
+    """Return a Chroma collection configured for the local knowledge base.
+
+    The collection is persisted in ``persist_directory`` and named
+    ``COLLECTION_NAME``.
+    """
     client = Chroma(Settings(persist_directory=persist_directory))
     collection = client.get_or_create_collection(name=COLLECTION_NAME)
     return collection
 
 
-def load_documents(directory: str, vectorstore: Chroma) -> int:
+def load_documents(directory: str, collection) -> int:
     splitter = RecursiveCharacterTextSplitter(
         chunk_size=1000,
         chunk_overlap=200,
@@ -48,5 +52,10 @@ def load_documents(directory: str, vectorstore: Chroma) -> int:
     ids = [str(uuid4()) for _ in chunks]
     embeddings = OllamaEmbeddings(model=EMBED_MODEL, base_url=OLLAMA_BASE_URL)
     vectors = embeddings.embed_documents([doc.page_content for doc in chunks])
-    vectorstore.add(ids=ids, documents=[doc.page_content for doc in chunks], embeddings=vectors, metadatas=[doc.metadata for doc in chunks])
+    collection.add(
+        ids=ids,
+        documents=[doc.page_content for doc in chunks],
+        embeddings=vectors,
+        metadatas=[doc.metadata for doc in chunks],
+    )
     return len(chunks)