Update app.py

app.py

@@ -27,10 +27,17 @@ embeddings = HuggingFaceEmbeddings()
 db = FAISS.load_local('db_full', embeddings)
 mp_docs = {}
 
-def retrieve_thoughts(query, n):
+def retrieve_thoughts(query, n, yt = False):
 
     # print(db.similarity_search_with_score(query = query, k = k, fetch_k = k*10))
-    docs_with_score = db.similarity_search_with_score(query = query, k = len(db.index_to_docstore_id.values()), fetch_k = len(db.index_to_docstore_id.values()))
+    #filter = {'Product Name': prod}
+    if yt:
+        docs_with_score = db.similarity_search_with_score(query = query, filter = {'categories': None},k = len(db.index_to_docstore_id.values()), fetch_k = len(db.index_to_docstore_id.values()))
+    else:
+        # Make it include only news + people or just create a whole new db with articles having their common key, and yt/podcasts having their own.
+        
+        docs_with_score = db.similarity_search_with_score(query = query, k = len(db.index_to_docstore_id.values()), fetch_k = len(db.index_to_docstore_id.values()))
+    
     df = pd.DataFrame([dict(doc[0])['metadata'] for doc in docs_with_score], )
     df = pd.concat((df, pd.DataFrame([dict(doc[0])['page_content'] for doc in docs_with_score], columns = ['page_content'])), axis = 1)
     df = pd.concat((df, pd.DataFrame([doc[1] for doc in docs_with_score], columns = ['score'])), axis = 1)
@@ -78,7 +85,7 @@ def qa_retrieve_art(query,):
     return {'Reference': reference}
 
 
-def qa_retriev_yt(query,):
+def qa_retrieve_yt(query,):
 
     docs = ""