This commit is contained in:
Ian Arawjo 2023-05-10 13:02:15 -04:00
commit ed567ed0a4
2 changed files with 18 additions and 20 deletions

View File

@ -60,3 +60,8 @@ This script spins up two servers, the main one on port 8000 and a SocketIO serve
If you built the React app statically, go to `localhost:8000` in a web browser to view the app.
If you served the React app with hot reloading with `npm run start`, go to the server address you ran it on (usually `localhost:3000`).
## Contributing to ChainForge
If you have access to the main repository, we request that you add a branch `dev/<your_first_name>` and develop changes from there. When you are ready to push changes, say to addres an open Issue, make a Pull Request on the `main` repository and assign the main developer (Ian Arawjo) to it.

View File

@ -19,30 +19,23 @@ Taken together, these three features let you easily:
# Installation
To install, use `pip`. From the command line:
To get started, currently see the `CONTRIBUTOR_GUIDE.md`. Below are the planned installation steps (which are not yet active):
```
pip install chainforge
```
[TODO: Upload CF to PyPI]
[TODO: Create a command-line alias (?) so you can run `chainforge serve <react_port?> <py_port?>` and spin up both React and the Python backend automatically.]
To run simply, type:
```
chainforge serve
```
This spins up two local servers: a React server through npm, and a Python backend, powered by Flask. For more options, such as port numbers, type `chainforge --help`.
### Sharing prompt chains
All ChainForge node graphs are importable/exportable as JSON specs. You can freely share prompt chains you develop (alongside any custom analysis code), whether to the public or within your organization.
>
> To install, use `pip`. From the command line:
>
> ```
> pip install chainforge
> ```
> To run, type:
> ```
> chainforge serve
> ```
> This spins up two local servers: a React server through npm, and a Python backend, powered by Flask. For more options, such as port numbers, type `chainforge --help`.
## Example: Test LLM robustness to prompt injection
...
> ...
# Development