Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mmz-001/knowledge_gpt
Accurate answers and instant citations for your documents.
https://github.com/mmz-001/knowledge_gpt
Last synced: 2 months ago
JSON representation
Accurate answers and instant citations for your documents.
- Host: GitHub
- URL: https://github.com/mmz-001/knowledge_gpt
- Owner: mmz-001
- License: mit
- Created: 2023-01-31T06:17:33.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-01-03T08:50:48.000Z (6 months ago)
- Last Synced: 2024-01-29T00:22:15.199Z (5 months ago)
- Language: Python
- Homepage: https://knowledgegpt.streamlit.app/
- Size: 1.53 MB
- Stars: 1,443
- Watchers: 18
- Forks: 534
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-langchain - Knowledge GPT - 001/knowledge_gpt?style=social) (Open Source Projects / Knowledge Management)
- awesome-ChatGPT-repositories - knowledge_gpt - Accurate answers and instant citations for your documents. (NLP)
- my-awesome - mmz-001/knowledge_gpt - Accurate answers and instant citations for your documents. (Python)
- my-awesome-stars - mmz-001/knowledge_gpt - Accurate answers and instant citations for your documents. (Python)
- awesome-stars - mmz-001/knowledge_gpt - Accurate answers and instant citations for your documents. (Python)
- awesome-stars - knowledge_gpt - 001 | 1549 | (Python)
- jimsghstars - mmz-001/knowledge_gpt - Accurate answers and instant citations for your documents. (Python)
- awesome-stars - knowledge_gpt - 001 | 1448 | (Python)
- awesome-langchain-zh - Knowledge GPT - 001/knowledge_gpt?style=social): 为你的文档提供准确的答案和即时引用。 (开源项目 / 知识管理)
README
📖KnowledgeGPT
[](https://twitter.com/mm_sasmitha)
**Accurate answers and instant citations for your documents.**
Upload your documents and get answers to your questions, with citations from the text.
[Demo](https://twitter.com/mm_sasmitha/status/1620999984085884930)
## Installation
Follow the instructions below to run the Streamlit server locally.
### Pre-requisites
Make sure you have Python ≥3.10 installed.
### Steps
1. Clone the repository
```bash
git clone https://github.com/mmz-001/knowledge_gpt
cd knowledge_gpt
```
2. Install dependencies with [Poetry](https://python-poetry.org/) and activate virtual environment
```bash
poetry install
poetry shell
```
3. (Optional) Avoid adding the OpenAI API every time you run the server by adding it to environment variables.
- Make a copy of `.env.example` named `.env`
- Add your API key to the `.env` file
> **Note:** Make sure you have a paid OpenAI API key for faster completions and to avoid hitting rate limits.
4. Run the Streamlit server
```bash
cd knowledge_gpt
streamlit run main.py
```
## Build with Docker
Run the following commands to build and run the Docker image.
```bash
cd knowledge_gpt
docker build -t knowledge_gpt .
docker run -p 8501:8501 knowledge_gpt
```
Open http://localhost:8501 in your browser to access the app.
## Customization
You can increase the max upload file size by changing `maxUploadSize` in `.streamlit/config.toml`.
Currently, the max upload size is 25MB for the hosted version.
## Tech Stack
- User Interface - [Streamlit](https://streamlit.io/)
- LLM Tooling - [Langchain](https://github.com/hwchase17/langchain)
## Roadmap
- Add support for more formats (e.g. webpages, PPTX, etc.)
- Highlight relevant phrases in citations
- Support scanned documents with OCR
- More customization options (e.g. chain type, chunk size, etc.)
- Visual PDF viewer
- Support for Local LLMs
## Contributing
All contributions are welcome!
## Contributors
Big thanks to the following people for their contributions!
## License
Distributed under the MIT License. See [LICENSE](https://github.com/mmz-001/knowledge_gpt/blob/main/LICENSE) for more information.
## Star History
[](https://star-history.com/#mmz-001/knowledge_gpt&Date)