🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Python agentai-societiesartificial-intelligencecommunicative-aicooperative-aideep-learninglarge-language-modelsmulti-agent-systemsnatural-language-processing
fix: update README with minor refinements (#135)
Bo Liud4adeaf0090b
diff --git a/README.md b/README.mdindex 33b18ea7c..2b6eb91b1 100644--- a/README.md+++ b/README.md@@ -2,7 +2,14 @@<a href="https://huggingface.co/camel-ai"><img src="https://huggingface.co/datasets/huggingface/brand-assets/resolve/main/hf-logo-with-title.png" alt="Hugging Face" width="100"/></a># CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society-## [[Project Website]](https://www.camel-ai.org/) [[Preprint]](https://ghli.org/camel.pdf)+<p align="center">+ <a href="https://github.com/camel-ai/camel#installation">Installation</a> |+ <a href="https://camel-ai.github.io/camel/">Documentation</a> |+ <a href="https://github.com/camel-ai/camel/tree/HEAD/examples">Examples</a> |+ <a href="https://arxiv.org/abs/2303.17760">Paper</a> |+ <a href="https://github.com/camel-ai/camel#citation">Citation</a> |+ <a href="https://www.camel-ai.org/">CAMEL-AI</a>+</p><p align="center"><img src='./misc/logo.png' width=800>@@ -22,34 +29,67 @@ We provide a [-## Environment Setup+## InstallationInstall `CAMEL` from source with conda:```-# create a conda virtual environment+# Create a conda virtual environmentconda create --name camel python=3.10-# activate camel conda environment++# Activate camel conda environmentconda activate camel-# install pre-commmit within camel env-pip install pre-commit-# clone github repo++# Clone github repogit clone -b v0.1.0 https://github.com/camel-ai/camel.git-# change directory into project directory++# Change directory into project directorycd camel-# install camel from source-pre-commit install++# Install camel from sourcepip install -e .++# Install pre-commmit within camel env (only needed for opening pull requests)+pip install pre-commit+pre-commit install```## ExampleYou can find a list of tasks for different set of assistant and user role pairs [here](https://drive.google.com/file/d/194PPaSTBR07m-PzjS-Ty6KlPLdFIPQDd/view?usp=share_link)-Run the `role_playing.py` script.-```-# export your OpenAI API key+Run the `role_playing.py` script++First, you need to add your OpenAI API key to system environment variables. The method to do this depends on your operating system and the shell you're using.++**For Bash shell (Linux, macOS, Git Bash on Windows):**++```bash+# Export your OpenAI API keyexport OPENAI_API_KEY=<insert your OpenAI API key>+```++**For Windows Command Prompt:**++```cmd+REM export your OpenAI API key+set OPENAI_API_KEY=<insert your OpenAI API key>+```++**For Windows PowerShell:**++```powershell+# Export your OpenAI API key+$env:OPENAI_API_KEY="<insert your OpenAI API key>"+```++Replace `<insert your OpenAI API key>` with your actual OpenAI API key in each case. Make sure there are no spaces around the `=` sign.++After setting the OpenAI API key, you can run the script:++```bash# You can change the role pair and initial prompt in role_playing.pypython examples/ai_society/role_playing.py```+Please note that the environment variable is session-specific. If you open a new terminal window or tab, you will need to set the API key again in that new session.+## Data (Hosted on Hugging Face)| Dataset | Chat format | Instruction format | Chat format (translated) || -- | -- | -- | -- |@@ -75,17 +115,19 @@ python examples/ai_society/role_playing.py## Citation```-@misc{camel,- author = {Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, Bernard Ghanem},- title = {CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society},- year = {2023},- journal={arXiv preprint},+@misc{li2023camel,+ title={CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society},+ author={Guohao Li and Hasan Abed Al Kader Hammoud and Hani Itani and Dmitrii Khizbullin and Bernard Ghanem},+ year={2023},+ eprint={2303.17760},+ archivePrefix={arXiv},+ primaryClass={cs.AI}}```## AcknowledgementSpecial thanks to [Nomic AI](https://home.nomic.ai/) for giving us extended access to their data set exploration tool (Atlas).-We would also like to thank Haya Hammoud for designing the logo of our project.+We would also like to thank Haya Hammoud for designing the logo of our project.## License@@ -96,4 +138,4 @@ The source code is licensed under Apache 2.0.The datasets are licensed under CC BY NC 4.0, which permits only non-commercial usage. It is advised that any models trained using the dataset should not be utilized for anything other than research purposes.## Contact-For more information please contact [Guohao Li](https://ghli.org/), [Hasan Abed Al Kader Hammoud](https://cemse.kaust.edu.sa/ece/people/person/hasan-abed-al-kader-hammoud), [Hani Itani](https://github.com/HaniItani).+For more information please contact [email protected].