mirror of
https://github.com/camel-ai/owl.git
synced 2026-03-22 14:07:17 +08:00
initial update
This commit is contained in:
45
README.md
Normal file
45
README.md
Normal file
@@ -0,0 +1,45 @@
|
||||
# DeepSwarm
|
||||
|
||||
## Overview
|
||||
|
||||
DeepSwarm is a multi-agent framework based from [camel](https://github.com/camel-ai/camel/). It achieved open-source state-of-the-art performance on the [GAIA](https://huggingface.co/datasets/gaia-benchmark/GAIA) benchmark.
|
||||
|
||||
## Quickstart
|
||||
|
||||
It is recommended to run the code in linux environment.
|
||||
To get started, follow these steps:
|
||||
|
||||
1. **Clone the Github repository:**
|
||||
|
||||
```bash
|
||||
$ git clone xxx
|
||||
```
|
||||
|
||||
2. **Set up Python Environment:**
|
||||
|
||||
```bash
|
||||
$ conda create -n deepswarm python=3.11
|
||||
$ conda activate deepswarm
|
||||
```
|
||||
|
||||
3. **Install Dependencies:**
|
||||
|
||||
```bash
|
||||
$ pip install -r requirements.txt
|
||||
```
|
||||
|
||||
4. **Set API Keys:** We use `dotenv` to manage API keys. Please copy and check the `.env.example` file to `.env` and fill in the necessary API keys.
|
||||
|
||||
5. **Run the Demo Code:**
|
||||
|
||||
```bash
|
||||
$ python run.py
|
||||
```
|
||||
|
||||
## Reproduce the Results in GAIA
|
||||
|
||||
We have provided a script to reproduce the results in GAIA. You can check the `run_gaia_roleplaying.py` file and run the following command:
|
||||
|
||||
```bash
|
||||
$ python run_gaia_roleplaying.py
|
||||
```
|
||||
Reference in New Issue
Block a user