Hi there! I've been using the ContextRetrieverOpenAIAgent.from_tools_and_retriever context agent. I noticed that it's not managing the number of tokens effectively, and as a result, it often exceeds the limit. Shouldn't this context agent inherently control the number of tokens?

Hey guys! I'm using the create_llama_chat_agent and I'm wondering, how can I set the system prompt in this case?

Hey guys! Should this example: https://gpt-index.readthedocs.io/en/latest/examples/chat_engine/chat_engine_openai.html, be compatible with version 0.7.6?