Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

A handy custom component for combining chains #18

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

victorpicaud
Copy link

DynamicSequentialChainComponent for Langflow

Introduction

This document introduces the DynamicSequentialChainComponent, a versatile custom component for Langflow. It facilitates the integration of multiple LLMChain instances within a flow, enhancing flexibility and user interaction.

Features

  • Dynamic Chain Integration: Combines multiple LLMChain instances seamlessly.
  • Variable Sharing Across Chains: Enables sharing of variables between different chains in a flow.
  • Customizable Inputs and Outputs: Users can specify input and output variables for each chain, allowing for tailored data processing.
  • Interactive Variable Definition: Variables can be dynamically defined in the chat window, rather than being pre-defined in the flow. This allows for more interactive and adaptable user experiences.

Use Cases

Ideal for scenarios requiring sequential data processing and context preservation across different chains. It's particularly useful where user interaction and real-time variable definition are important.

How It Works

The component takes lists of chains, input variables, and output variables, constructing a SequentialChain. This chain processes data through each LLMChain, using the provided variables, which can be dynamically defined during user interaction.

Conclusion

The DynamicSequentialChainComponent provides a simple, yet powerful way to build flexible and interactive flows in Langflow, enhancing both the design and user experience.

@victorpicaud
Copy link
Author

victorpicaud commented Dec 29, 2023

@ langflow team, I love your tool so I have created for my team (we all use langflow) this component that is described above,
It could be a standart in some way, I could not manage to integrate it with LELC yet
NB: This is the component json and not the flow, If it is interesting for you I can provide a flow example (but i need to build one, I only have production flow right now)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

1 participant