Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Wannabeasmartguy/RAGENT
Probably one of the lightest native RAG + Agent apps out there，experience the power of Agent-powered models and Agent-driven knowledge bases in one click, without complex configuration.
https://github.com/Wannabeasmartguy/RAGENT
agent autogen azure groq langchian llamafile llm local-development ollama openai rag
Last synced: 12 days ago
JSON representation
Probably one of the lightest native RAG + Agent apps out there，experience the power of Agent-powered models and Agent-driven knowledge bases in one click, without complex configuration.
- Host: GitHub
- URL: https://github.com/Wannabeasmartguy/RAGENT
- Owner: Wannabeasmartguy
- License: gpl-3.0
- Created: 2024-04-21T06:42:24.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-10-23T08:31:15.000Z (3 months ago)
- Last Synced: 2024-10-23T13:37:28.442Z (3 months ago)
- Topics: agent, autogen, azure, groq, langchian, llamafile, llm, local-development, ollama, openai, rag
- Language: Python
- Homepage:
- Size: 1.61 MB
- Stars: 8
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# RAGenT
**English** | [中文文档](./docs/README_zh.md) | [日本語](./docs/README_ja.md)
Probably one of the lightest native RAG + Agent apps out there，experience the power of Agent-powered models and Agent-driven knowledge bases in one click, without complex configuration.
## Features
Chat and Agent interactions:
- [x] 💭 Simple, easy-to-use chat box interface.
- [x] 🌏️ Language options (Simplified Chinese, English)
- [x] 🔧 Inference support for multiple (local) model sources (Azure OpenAI, Groq, ollama, llamafile)
- [x] Native Function Call (OpenAI, Azure OpenAI, OpenAI Like, Ollama)
- [x] 🤖 Multiple Agent modes on-premises
- [x] 🖥️ Local storage of dialog data and management
- [x] Multiple export formats(Markdown, HTML)
- [x] Multiple themes(HTML)
Knowledgebase:
- [x] **Native implementation** of Retrieval Augmentation Generation (RAG), lightweight and efficient
- [x] Optional embedding models (Hugging Face/OpenAI)
- [x] Easy-to-use knowledge base management
- [x] Hybrid search, reranking, and specified file retrieval
> If you like this project, please star it, it's the biggest encouragement for me!
## More details
### General
#### Voice to text input:
#### Export
Support export format, theme selection and export range control:
Currently supported themes:
| Default | Glassmorphism |
| :-----: | :-----------: |
| 
| 
|
### RAG Chat
Set up the model (sidebar) and view detailed references:
Configure RAG ：
### Function Call
Function calls are supported on both `Chat` and `AgentChat` pages, but are implemented differently.
#### Chat Page
The Function Calls on this page are native and work for all OpenAI Compatible models, but require the model itself to support Function calls.
> You can also customize the function you want to call, please refer to [toolkits.py](tools/toolkits.py) for writing rules.
#### AgentChat Page
> **Note**: Due to AutoGen v0.4 is completely rewritten, the AgentChat Page will be updated in the future version and now is only supported for testing with AutoGen v0.2. If you want to use the AgentChat Page, please use `python startup.py` to start the application rather than `streamlit run RAGenT.py`.
Relying on the AutoGen framework for implementation (testing), please refer to the documentation of [AutoGen](https://github.com/microsoft/autogen) for model compatibility.
Function call can significantly enhance the capabilities of LLM and currently supports OpenAI, Azure OpenAI, Groq, and local models.（[by LiteLLM + Ollama](https://microsoft.github.io/autogen/docs/topics/non-openai-models/local-litellm-ollama#using-litellmollama-with-autogen)）。
> You can also customize the function you want to call, please note that AutoGen's function writing is **different** from the native function calling writing rules, please refer to the [Official Documentation](https://microsoft.github.io/autogen/docs/tutorial/tool-use/) and this project's [tools.py](llm/aoai/tools/tools.py).
## Quick start
### Git
0. Use `git clone https://github.com/Wannabeasmartguy/RAGenT.git` to pull the code;
Then open your runtime environment in **command prompt (CMD)** and use `pip install -r requirements.txt` to install the runtime dependencies.
1. Configure the model dependencies: Modify the `.env_sample` file to `.env` and fill in the following:
- `LANGUAGE`: Support `English` and `简体中文`, defualt is `English`;
- `OPENAI_API_KEY` : If you are using an OpenAI model, fill in the api key here;
- `AZURE_OAI_KEY` : If you are using an Azure OpenAI model, fill in the api key here;
- `AZURE_OAI_ENDPOINT` : If you are using an OpenAI model, fill in the end_point here;
- `API_VERSION`: If you are using an Azure OpenAI model, fill in the api version here;
- `API_TYPE`: if you are using an Azure OpenAI model, fill in the api type here;
- `GROQ_API_KEY` : if you are using Groq as the model source, fill in the api key here;
- `COZE_ACCESS_TOKEN`: if you need to use the created Coze Bot, fill in the access token here;
> If you are using Llamafile, please set the endpoint within the application after starting the Llamafile model.
2. launch the application:
Run: Run `streamlit run RAGenT.py` on the command line can start it.
If you want to use the AgentChat page, please use `python startup.py` to start the application rather than `streamlit run RAGenT.py`.
## Route
- [x] Chat history and configuration local persistence
- [x] Chat history local persistence
- [x] Configuration local persistence
- [ ] Increase the number of preset Agents
- [ ] Mixed retrieval, reordering and specified file retrieval
- [ ] 📚️Agent-driven Knowledge Base