Does anyone created agent with tool which takes "dataframe" and "user_input" as input variables in langchain?

[bmshambu]

Issue you'd like to raise.

Does anyone created agent with tool which takes "dataframe" and "user_input" as input variables in langchain?
I do not want use dataframe agent which is there already in langchain. As I need pass further instruction in the prompt template.

Suggestion:

No response

[dosubot]

🤖

Hello,

Yes, it is indeed possible to create an agent in LangChain that accepts both a "dataframe" and "user_input" as input variables. You can achieve this by modifying the create_prompt method in the StructuredChatAgent class to include "dataframe" and "user_input" in the input_variables list. Here's how you can do it:

@classmethod
def create_prompt(
    cls,
    tools: Sequence[BaseTool],
    prefix: str = PREFIX,
    suffix: str = SUFFIX,
    human_message_template: str = HUMAN_MESSAGE_TEMPLATE,
    format_instructions: str = FORMAT_INSTRUCTIONS,
    input_variables: Optional[List[str]] = None,
    memory_prompts: Optional[List[BasePromptTemplate]] = None,
) -> BasePromptTemplate:
    # ... existing code ...

    if input_variables is None:
        input_variables = ["dataframe", "user_input", "agent_scratchpad"]

    # ... existing code ...

In the above code, we have modified the input_variables list to include "dataframe" and "user_input". This will allow the agent to accept both a dataframe and user input as input variables.

You can find the StructuredChatAgent class in the LangChain codebase at libs/langchain/langchain/agents/structured_chat/base.py.

Please note that this modification will affect all instances of StructuredChatAgent that do not provide their own input_variables list. If you want to limit this change to a specific agent, you can subclass StructuredChatAgent and override the create_prompt method in your subclass.

I hope this helps! If you have any further questions, feel free to ask.

Best regards,
Dosu

Sources

• libs/langchain/langchain/agents/structured_chat/base.py

---

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.

If you want to continue the conversation, start your reply with @dosu-bot.

[bmshambu]

I have requirement like this I need generate insights from the data frame table where i create two tools
one tool takes df and user input in case user wants to generate insights on Area. i will configure area related prompt inside the tool.
And one more tool takes df and user input in case user user wants to generate insights on Serviceline. i will configure area related prompt inside the tool.

[dosubot]

Hi, @bmshambu! I'm Dosu, and I'm here to help the LangChain team manage our backlog. I wanted to let you know that we are marking this issue as stale.

From what I understand, you were asking if anyone has created an agent in LangChain that takes a dataframe and user input as input variables. There hasn't been any response or suggestion provided yet, but I have given a helpful response. I explained how to modify the create_prompt method in the StructuredChatAgent class to include the desired input variables. You, as the original author, have also provided additional details about your specific requirements.

If this issue is still relevant to the latest version of the LangChain repository, please let us know by commenting on this issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.

Thank you for your understanding and contribution to the LangChain project! If you have any further questions or need assistance, feel free to reach out.