Update question.py

question.py

@@ -66,9 +66,6 @@ def chat_with_doc(model, vector_store: SupabaseVectorStore, stats_db):
                 # print(st.session_state['max_tokens'])
                 endpoint_url = ("https://api-inference.huggingface.co/models/"+ model)
                 model_kwargs = {"temperature" : st.session_state['temperature'],
-                                "min_p" : 0.1,
-                                "top_p" : 0.9,
-                                "repetition_penalty" : 1.5,
                                 "max_new_tokens" : st.session_state['max_tokens'],
                                 "return_full_text" : False}
                 hf = HuggingFaceEndpoint(
@@ -77,7 +74,7 @@ def chat_with_doc(model, vector_store: SupabaseVectorStore, stats_db):
                     huggingfacehub_api_token=hf_api_key,
                     model_kwargs=model_kwargs
                 )
-                qa = ConversationalRetrievalChain.from_llm(hf, retriever=vector_store.as_retriever(search_kwargs={"score_threshold": 0.5, "k": 5,"filter": {"user": st.session_state["username"]}}), memory=memory, verbose=True, return_source_documents=True)
+                qa = ConversationalRetrievalChain.from_llm(hf, retriever=vector_store.as_retriever(search_kwargs={"score_threshold": 0.6, "k": 3,"filter": {"user": st.session_state["username"]}}), memory=memory, verbose=True, return_source_documents=True)
 
             st.session_state['chat_history'].append(("You", question))