Add support for streaming with chains

[aiswaryasankar]

Would be great to support streaming for Langchain chains - e.g.

streaming_handler = kwargs.get('streaming_handler')

    model = ChatOpenAI(
        model='gpt-3.5-turbo',
        temperature=0.0,
        verbose=True,
        streaming=True,  # Pass `streaming=True` to make sure the client receives the data.
        callback_manager=CallbackManager(
            [streaming_handler]
        ),
    )
    qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever)

[Deepankar Mahapatro]

This is now supported by passing the callback manager to the chains as well.

langchain-serve/lcserve/apps/autogpt/helper.py

Lines 120 to 125 in 24da78d

 chain = LLMChain( 
     llm=llm, 
     prompt=prompt, 
     verbose=True, 
     callback_manager=llm.callback_manager, 
 )