https://chainforge.ai/docs/

[ ] [ ]
Skip to content
 
ChainForge Documentation
Introduction
( ) ( )
[                    ]
Initializing search

 
ianarawjo/ChainForge
 ChainForge Documentation
 
ianarawjo/ChainForge

  * [ ] Introduction Introduction Table of contents
      + How to Install
          o Install ChainForge locally
          o Or try out ChainForge online @ chainforge.ai/play
      + About Us
          o How to Cite
  * How to Install
  * [ ] Features Features
      + UI Overview
      + Nodes
      + Prompt Templating
      + Inspecting Responses
      + Evaluating Responses
      + Visualizing Results
      + Supported Models
  * [ ] Misc Misc
      + Release Notes
      + For Developers

Table of contents

  * How to Install
      + Install ChainForge locally
      + Or try out ChainForge online @ chainforge.ai/play
  * About Us
      + How to Cite

[?][?][?] ChainForge

prompt-inj-attack

ChainForge is an open-source visual programming environment for
prompt engineering, LLM evaluation and experimentation. With
ChainForge, you can evaluate the robustness of prompts and text
generation models with little to no coding required. Features
include:

  * Query multiple LLMs at once to test prompt ideas and variations
    quickly and effectively. Or query the same LLM at different
    settings.
  * Compare response quality across prompt permutations, across
    models, and across model settings to choose the best prompt and
    model for your use case.
  * Setup evaluation metrics with code or LLM-based scorers and
    automatically plot results across prompts, prompt parameters,
    models, or model settings.
  * Hold multiple conversations at once across template parameters
    and chat models. Template chat messages and inspect and evaluate
    outputs at each turn of a chat conversation.

ChainForge is in active development and is provided as an open beta
test.

How to Install

Install ChainForge locally

pip install chainforge 
chainforge serve

Open localhost:8000 in a Chrome, Firefox, Edge or Brave browser. For
more details on installation, such as setting API keys as environment
variables, see Getting Started.

Or try out ChainForge online @ chainforge.ai/play

The web version is limited, yet includes a magical feature called the
Share Button:

share-btn

With Share, you can send your LLM experiments to others as links.
Simply click Share to generate a unique weblink for your LLM
experiment and copy it to your clipboard. For instance, here's an
experiment that tries to get an LLM to reveal a secret key.

Note

ChainForge is compatible with Google Chrome and Mozilla Firefox. You
will need an API key for the LLM(s) you wish to use. We do not store
your API keys --not in a cookie, localStorage, or server. Because of
this, you must set your API keys every time you load ChainForge. If
you prefer not to worry about it, we recommend installing ChainForge
locally and setting your API keys as environment variables.

About Us

ChainForge is created by Ian Arawjo, a postdoctoral scholar at
Harvard in the Glassman Lab of the Harvard HCI group. Collaborators
include PhD students Priyan Vaithilingam and Chelse Swoopes and
faculty members Elena Glassman and Martin Wattenberg.

How to Cite

If you use ChainForge for research purposes, or build upon the source
code, we ask that you cite this project in any related publications.
The BibTeX you can use for now is:

@misc{Arawjo_2023,
  author = {Arawjo, Ian and Vaithilingam, Priyan and Swoopes, Chelse and Wattenberg, Martin and Glassman, Elena},
  title = {ChainForge},
  year = {2023},
  howpublished = {\url{https://www.chainforge.ai/}}
}


Copyright (c) 2023 Ian Arawjo
Made with Material for MkDocs