Update rss_processor.py

rss_processor.py

@@ -1,6 +1,6 @@
 import os
 import feedparser
-from langchain.vectorstores import Chroma
+from chromadb import Client, Documents
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.docstore.document import Document
 import logging
@@ -163,14 +163,11 @@ def process_and_store_articles(articles):
     if not os.path.exists(LOCAL_DB_DIR):
         os.makedirs(LOCAL_DB_DIR)
     
-    vector_db = Chroma(
-        persist_directory=LOCAL_DB_DIR,
-        embedding_function=get_embedding_model(),
-        collection_name=COLLECTION_NAME
-    )
+    client = Client(persist_directory=LOCAL_DB_DIR)
+    collection = client.get_or_create_collection(name=COLLECTION_NAME)
     
     try:
-        existing_ids = set(vector_db.get(include=[])["ids"])
+        existing_ids = set(collection.get(include=[])["ids"])
         logger.info(f"Loaded {len(existing_ids)} existing document IDs from {LOCAL_DB_DIR}.")
     except Exception as e:
         logger.info(f"No existing DB found or error loading IDs: {e}. Starting fresh.")
@@ -201,9 +198,16 @@ def process_and_store_articles(articles):
     
     if docs_to_add:
         try:
-            vector_db.add_documents(documents=docs_to_add, ids=ids_to_add)
-            vector_db._client.persist()
-            logger.info(f"Added {len(docs_to_add)} new articles to DB. Total in DB: {vector_db._collection.count()}")
+            embeddings = get_embedding_model()
+            for doc, doc_id in zip(docs_to_add, ids_to_add):
+                collection.add(
+                    documents=[doc.page_content],
+                    metadatas=[doc.metadata],
+                    ids=[doc_id],
+                    embeddings=[embeddings.embed_query(doc.page_content)]
+                )
+            client.persist()
+            logger.info(f"Added {len(docs_to_add)} new articles to DB. Total in DB: {collection.count()}")
         except Exception as e:
             logger.error(f"Error storing articles: {e}")