Whether chat_engine can call stream_complete()?

[cxycxm]

Question Validation

• I have searched both the documentation and discord for an answer.

Question

Whether chat_engine can call stream_complete()?

[dosubot]

Hey there, @cxycxm! 🚀 Good to see you back with another intriguing question. Just diving into the depths to fetch your answer. Hang tight!

[logan-markewich]

the method you are looking for is chat_engine.stream_chat()

response = chat_engine.stream_chat("Hello!")
for token response.response_gen:
  print(token, end="", flush=True)

[dosubot]

To directly address your question, chat_engine does not have a method named stream_complete(). Instead, as highlighted by the maintainer, you should use chat_engine.stream_chat() to handle streaming chat responses. Here's a quick recap on how to use it:

response = chat_engine.stream_chat("Hello!")
for token in response.response_gen:
  print(token, end="", flush=True)

This approach allows you to process and print each token received from the chat engine in real-time. If you have any more questions or need further clarification, feel free to ask!

Details

Sources

• llama-index-legacy/llama_index/legacy/chat_engine/simple.py
• llama-index-legacy/llama_index/legacy/chat_engine/context.py
• llama-index-core/llama_index/core/chat_engine/context.py
• llama-index-core/llama_index/core/chat_engine/simple.py

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[cxycxm]

but i need stream_complete()，my purpose is to complete the conversation

[logan-markewich]

That's not how it works with chat engines sadly. Completion only makes sense if you have a single string, not a an alternating chat history.

You can prompt it with a chat history and take the llms response as a completion of the previous message if you want