Update app.py

app.py

@@ -48,7 +48,7 @@ def get_conversation_chain(vectorstore:FAISS) -> ConversationalRetrievalChain:
         #repo_id="TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF"
         model_kwargs={"temperature": 0.02, "max_length": 1048},
     )
-
+    llm.client.api_url = 'https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1'
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
     conversation_chain = ConversationalRetrievalChain.from_llm(
         llm=llm, retriever=vectorstore.as_retriever(), memory=memory