# UniLLM: Unified Large Language Model Interface
[](https://opensource.org/licenses/MIT)
[](https://pypi.org/project/unillm/)
[](https://github.com/fuzihaofzh/unillm)
[](https://unillm.readthedocs.io/en/latest/?badge=latest)
UniLLM is a versatile Python library and command-line tool designed to provide unified access to various large language models such as [ChatGPT](https://openai.com/chatgpt), [Llama2](https://llama.meta.com/), [Mistral](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2), [Claude](https://www.anthropic.com/), [MistralAI](https://mistral.ai/), [RAG](https://www.llamaindex.ai/), [Llama3](https://llama.meta.com/), and [CommandRPlus](https://cohere.ai/). This library simplifies the integration of these models into your projects or allows for direct interaction via the command line.
## Features
- Unified API for interacting with multiple language models.
- Support for both API and local models.
- Extensible framework allowing the addition of more models in the future.
- Command-line tool for easy interaction with models.
- Configuration via YAML file for API keys.
## Installation
Install UniLLM using pip:
```bash
pip install unillm
```
## Configuration
Configure your API keys for the models by creating a `.unillm.yaml` file in your home directory:
```yaml
chatgpt: YOUR_CHATGPT_API_KEY
claude: YOUR_CLAUDE_API_KEY
mistralai: YOUR_MISTRALAI_API_KEY
# Add other model API keys as needed
```
## Supported Models
| Model | Support API | Support Local |
|---------------|:-----------:|:-------------:|
| ChatGPT | ✅ | |
| Llama2 | | ✅ |
| Mistral | ✅ | ✅ |
| Claude | ✅ | |
| MistralAI | ✅ | |
| RAG | ✅ | ✅ |
| Llama3 | | ✅ |
| CommandRPlus | | ✅ |
## Usage
### As a Python Library
Interact with language models seamlessly in your Python projects:
```python
from unillm import UniLLM
# Initialize Llama with specific settings
model = UniLLM('Llama2', peft_path="path_to_peft_model", max_new_tokens=1024)
# Generate a response
response = model.generate_response("How can AI help humans?")
print(response)
```
### As a Command-Line Tool
Start the CLI by running:
```bash
unillm
```
Follow the prompts to select a model and enter your queries. For example:
```bash
Please choose a model by number (default is 1):
1: ChatGPT
2: Llama2
...
👨Please Ask a Question: What are the latest AI trends?
🤖 (ChatGPT): AI trends include...
```
To exit, type `exit`.
## Contributing
We welcome contributions! If you have suggestions or enhancements, fork the repository, create a feature branch, and submit a pull request.
## License
This project is licensed under the MIT License - see the LICENSE file for details.
Raw data
{
"_id": null,
"home_page": "https://github.com/fuzihaofzh/unillm",
"name": "unillm",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "language models AI NLP ChatGPT Llama Mistral Claude MistralAI RAG",
"author": "Your Name",
"author_email": "your.email@example.com",
"download_url": "https://files.pythonhosted.org/packages/9a/80/ac0dfbffbab7eb315427f387e59611d971182168f7e9d96740c5c3a41f82/unillm-0.0.8.tar.gz",
"platform": null,
"description": "# UniLLM: Unified Large Language Model Interface\n\n[](https://opensource.org/licenses/MIT)\n[](https://pypi.org/project/unillm/)\n[](https://github.com/fuzihaofzh/unillm)\n[](https://unillm.readthedocs.io/en/latest/?badge=latest)\n\nUniLLM is a versatile Python library and command-line tool designed to provide unified access to various large language models such as [ChatGPT](https://openai.com/chatgpt), [Llama2](https://llama.meta.com/), [Mistral](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2), [Claude](https://www.anthropic.com/), [MistralAI](https://mistral.ai/), [RAG](https://www.llamaindex.ai/), [Llama3](https://llama.meta.com/), and [CommandRPlus](https://cohere.ai/). This library simplifies the integration of these models into your projects or allows for direct interaction via the command line.\n\n## Features\n\n- Unified API for interacting with multiple language models.\n- Support for both API and local models.\n- Extensible framework allowing the addition of more models in the future.\n- Command-line tool for easy interaction with models.\n- Configuration via YAML file for API keys.\n\n## Installation\n\nInstall UniLLM using pip:\n\n```bash\npip install unillm\n```\n\n## Configuration\n\nConfigure your API keys for the models by creating a `.unillm.yaml` file in your home directory:\n\n```yaml\nchatgpt: YOUR_CHATGPT_API_KEY\nclaude: YOUR_CLAUDE_API_KEY\nmistralai: YOUR_MISTRALAI_API_KEY\n# Add other model API keys as needed\n```\n\n## Supported Models\n\n| Model | Support API | Support Local |\n|---------------|:-----------:|:-------------:|\n| ChatGPT | \u2705 | |\n| Llama2 | | \u2705 |\n| Mistral | \u2705 | \u2705 |\n| Claude | \u2705 | |\n| MistralAI | \u2705 | |\n| RAG | \u2705 | \u2705 |\n| Llama3 | | \u2705 |\n| CommandRPlus | | \u2705 |\n\n## Usage\n\n### As a Python Library\n\nInteract with language models seamlessly in your Python projects:\n\n```python\nfrom unillm import UniLLM\n\n# Initialize Llama with specific settings\nmodel = UniLLM('Llama2', peft_path=\"path_to_peft_model\", max_new_tokens=1024)\n\n# Generate a response\nresponse = model.generate_response(\"How can AI help humans?\")\nprint(response)\n```\n\n### As a Command-Line Tool\n\nStart the CLI by running:\n\n```bash\nunillm\n```\n\nFollow the prompts to select a model and enter your queries. For example:\n\n```bash\nPlease choose a model by number (default is 1):\n1: ChatGPT\n2: Llama2\n...\n\n\ud83d\udc68Please Ask a Question: What are the latest AI trends?\n\ud83e\udd16 (ChatGPT): AI trends include...\n```\n\nTo exit, type `exit`.\n\n## Contributing\n\nWe welcome contributions! If you have suggestions or enhancements, fork the repository, create a feature branch, and submit a pull request.\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Unified Large Language Model Interface for ChatGPT, LLaMA, Mistral, Claude, and RAG",
"version": "0.0.8",
"project_urls": {
"Homepage": "https://github.com/fuzihaofzh/unillm"
},
"split_keywords": [
"language",
"models",
"ai",
"nlp",
"chatgpt",
"llama",
"mistral",
"claude",
"mistralai",
"rag"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "70eb83935e6978bdadce05f9d5da23c489ddf9d8cf5a682e8792403296580b30",
"md5": "b74ab0330c3149c04f05da817f6cd359",
"sha256": "e7000324536030ebb42b7ac9fa587b5cd3ad920d56febfb8ecebf2f5e456469b"
},
"downloads": -1,
"filename": "unillm-0.0.8-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b74ab0330c3149c04f05da817f6cd359",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 8844,
"upload_time": "2024-04-19T08:07:22",
"upload_time_iso_8601": "2024-04-19T08:07:22.339547Z",
"url": "https://files.pythonhosted.org/packages/70/eb/83935e6978bdadce05f9d5da23c489ddf9d8cf5a682e8792403296580b30/unillm-0.0.8-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "9a80ac0dfbffbab7eb315427f387e59611d971182168f7e9d96740c5c3a41f82",
"md5": "d0299a5fd70b053aa28540fb68eac779",
"sha256": "051e13b12f23c1f135277cdb01089bdd86169268ac12bb07eee80c4cb9ce01b0"
},
"downloads": -1,
"filename": "unillm-0.0.8.tar.gz",
"has_sig": false,
"md5_digest": "d0299a5fd70b053aa28540fb68eac779",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 10396,
"upload_time": "2024-04-19T08:07:23",
"upload_time_iso_8601": "2024-04-19T08:07:23.608699Z",
"url": "https://files.pythonhosted.org/packages/9a/80/ac0dfbffbab7eb315427f387e59611d971182168f7e9d96740c5c3a41f82/unillm-0.0.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-19 08:07:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "fuzihaofzh",
"github_project": "unillm",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "openai",
"specs": []
},
{
"name": "torch",
"specs": []
},
{
"name": "transformers",
"specs": []
},
{
"name": "yaml",
"specs": []
},
{
"name": "peft",
"specs": []
},
{
"name": "anthropic",
"specs": []
},
{
"name": "mistralai",
"specs": []
},
{
"name": "llama_index",
"specs": []
},
{
"name": "fire",
"specs": []
}
],
"lcname": "unillm"
}
JSON
