tool calling agent (AzureChatOpenAI) is returning empty response sometimes.

[ajayjohn117]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

memory = ConversationBufferWindowMemory(k=3, return_messages=True, memory_key='memory', chat_memory=RedisChatMessageHistory(session_id=session_id))
    prompt = OpenAIFunctionsAgent.create_prompt(
        system_message=system_prompt,
        extra_prompt_messages=[MessagesPlaceholder(variable_name="memory")],
    )

    agent = create_openai_tools_agent(llm, tools, prompt)
    agent_executor = AgentExecutor(
        agent=agent,
        tools=tools,
        memory=memory,
        verbose=True,
        return_intermediate_steps=False,
        handle_parsing_errors=True
    )
    
    return agent_executor

Description

I have a long code, but the following is the part where i am initialising the tool calling agent. I have 4 tools that i am using.
Issue here i am facing is that most of the time the agent is working as intended. But sometimes i notice the agent is giving empty responses.

Following is the raw output

{
  "generations": [
    {
      "text": "",
      "generation_info": null,
      "type": "ChatGenerationChunk",
      "message": {
        "lc": 1,
        "type": "constructor",
        "id": [
          "langchain",
          "schema",
          "messages",
          "AIMessageChunk"
        ],
        "kwargs": {
          "content": "",
          "type": "AIMessageChunk",
          "id": "run-ae5e715f-a9f8-42a6-b58e-37b4149b6eb3",
          "tool_calls": [],
          "invalid_tool_calls": []
        }
      }
    }
  ],
  "llm_output": null,
  "run": null,
  "type": "LLMResult"
}

System Info

langchain==0.1.9
langchain-community==0.0.24
langchain-core==0.1.52
langchain-openai==0.1.5