mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-01-10 23:58:06 -05:00
Updated the forge readme
This commit is contained in:
@@ -16,51 +16,6 @@ Ever dreamt of becoming the genius behind an AI agent? Dive into the *Forge*, wh
|
||||
|
||||
### 🚀 **Get Started!**
|
||||
|
||||
Intial setup:
|
||||
1. **[Fork the Project](https://github.com/Significant-Gravitas/Auto-GPT)**
|
||||
2. Clone your repo
|
||||
3. run `create_new_agent.sh name` changing name to the name you want to give your agent
|
||||
4. `cd autogpts/name` where name is the name you entered above
|
||||
5. Install [Poetry](https://python-poetry.org/docs/#installation) if you haven't already
|
||||
6. Run `poetry install` to install the project dependencies
|
||||
7. Activate the virtual environment with `poetry shell`
|
||||
Please follow the quickstart guide:
|
||||
|
||||
---
|
||||
|
||||
### 🏃♂️ **Running Your Agent**
|
||||
|
||||
|
||||
1. Make sure you're in the poetry shell. If not, activate it with `poetry shell`.
|
||||
2. Copy the example environment file with `cp .env.example .env`.
|
||||
3. Open the `.env` file and add your OpenAI API key. You can get it from [OpenAI API](https://platform.openai.com/docs/developer-quickstart/).
|
||||
4. Run your agent with `./run`. This command runs the server and watches for changes.
|
||||
|
||||
### 📊 **Benchmarking**
|
||||
|
||||
|
||||
To run the benchmark, use the `agbenchmark` command. Here are some options you can use with this command:
|
||||
|
||||
- `--backend`: If it's being run from the cli
|
||||
- `-c, --category TEXT`: Specific category to run
|
||||
- `-s, --skip-category TEXT`: Skips preventing the tests from this category from running
|
||||
- `--test TEXT`: Specific test to run
|
||||
- `--maintain`: Runs only regression tests
|
||||
- `--improve`: Run only non-regression tests
|
||||
- `--explore`: Only attempt challenges that have never been beaten
|
||||
- `--mock`: Run with mock
|
||||
- `--no_dep`: Run without dependencies
|
||||
- `--nc`: Run without cutoff
|
||||
- `--keep-answers`: Keep answers
|
||||
- `--cutoff TEXT`: Set or override tests cutoff (seconds)
|
||||
- `--help`: Show this message and exit.
|
||||
|
||||
For example, if you want to run a specific test, you can use the `--test` option like this:
|
||||
`agbenchmark --test your_test_name`
|
||||
|
||||
If you want to run the benchmark without dependencies, you can use the `--no_dep` option like this:
|
||||
`agbenchmark --no_dep`
|
||||
|
||||
You can combine multiple options as well. For example, to run a specific test without dependencies, you can do:
|
||||
`agbenchmark --test your_test_name --no_dep`
|
||||
|
||||
Remember to replace `your_test_name` with the name of the test you want to run.
|
||||
[**Quick Start Guide**](../../QUICKSTART.md)
|
||||
|
||||
Reference in New Issue
Block a user