Error with custom component

[DreF174]

I am creating a flow where the model is passed a prompt for it to generate code. The code is then executed to make sure it works and passed to another model for further refining. I am trying to create a custom component as an LLM runner for this. I am trying to pass the runner the LLM, prompt and tool for code execution however I keep getting this error:

" Error building node CustomComponent(ID:CustomComponent-dNNcg): 1 validation error for LLMChain
tool
extra fields not permitted (type=value_error.extra) "

This is the code I am using:

from langflow import CustomComponent

from langchain.llms.base import BaseLLM
from langchain.chains import LLMChain
from langchain import PromptTemplate
from langchain.schema import Document
from langchain.tools import Tool

class YourComponent(CustomComponent):
   display_name: str = "LLM Runner"
   description: str = "Build and run a chain with no free parameters"

def build(self, llm: BaseLLM, prompt: PromptTemplate, Tool:List[Tool]) -> Document:
    chain = LLMChain(llm=llm, prompt=prompt)
    result = chain.run({"":""})
    return Document(page_content=str(result))

Does anyone know anything about this issue or any advice on how I can get the flow I want to work?

[dosubot[bot]]

🤖

Hello @DreF174!

Nice to meet you, I'm Dosu, a friendly bot designed to help out with bug solving, answering questions, and guiding contributors in the right direction. While we wait for a human maintainer, I'm here to assist you as best as I can. Let's work together to sort out your issue.

The error you're encountering typically arises when you're trying to pass extra fields to a function or method that doesn't expect them. In your case, you're trying to pass the LLM, prompt, and tool for code execution to the build method of your custom component, but this method only expects a single parameter param.

To resolve this issue, you need to modify the build method of your custom component to accept these additional parameters. Here is how you can do it:

from langflow import CustomComponent
from langflow.field_typing import Data


class Component(CustomComponent):
    documentation: str = "http://docs.langflow.org/components/custom"

    def build_config(self):
        return {"param": {"display_name": "Parameter"},
                "llm": {"display_name": "LLM"},
                "prompt": {"display_name": "Prompt"},
                "tool": {"display_name": "Tool"}}

    def build(self, param: Data, llm: Data, prompt: Data, tool: Data) -> Data:
        # Your code here
        return param

In the build_config method, I added the additional parameters llm, prompt, and tool to the configuration. Then, I modified the build method to accept these additional parameters. Now, you should be able to pass the LLM, prompt, and tool for code execution to your custom component without encountering the "extra fields not permitted" error.

You can find more information about the structure and parameters of a custom component in the langflow codebase in the CustomComponent.py file.

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

-Dosu

Sources

• src/backend/langflow/components/custom_components/CustomComponent.py
• src/backend/langflow/interface/custom/custom_component/custom_component.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.

[Cristhianzl]

Hi! 👋

We are using other channels as our official means of communication with users. We apologize for the delayed response.
For faster assistance, please direct your questions to our Discord channel or open a GitHub issue, as we are much more active on these platforms.

Langflow Discord Server

Thank you for your understanding.

Best regards,
The Langflow Team