Unable to stream Ollama

[aadityamundhalia]

I am trying to stream the response in streamlit but I get the full response instead of the streamed one. can someone point me to right direction:

chat_model = ChatOllama(
                base_url=ollamaPath,
                model=modelName,
                temperature=temperature,
                verbose=True,
                callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])),
            )

qa = RetrievalQA.from_chain_type(
                chat_model,
                chain_type="stuff",
                retriever=vectorstore.as_retriever(),
                chain_type_kwargs={"prompt": promptRepository.basicPrompt()},
            )

qa({"query": prompt})['result']

any help be much appreciated.

[kaushalpowar]

I faced the same issue. In my case it was because of st.write(response), write st.markdown(response) instead

[aadityamundhalia]

thanks,, let me try that