https://github.com/Qetesh/miniflux-ai
Miniflux with AI. Add AI summaries, translations, and AI news based on RSS content
https://github.com/Qetesh/miniflux-ai
ai llm miniflux miniflux-extension openai rss
Last synced: about 1 year ago
JSON representation
Miniflux with AI. Add AI summaries, translations, and AI news based on RSS content
- Host: GitHub
- URL: https://github.com/Qetesh/miniflux-ai
- Owner: Qetesh
- Created: 2024-08-12T16:36:22.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-04-12T19:53:05.000Z (about 1 year ago)
- Last Synced: 2025-04-12T20:26:35.890Z (about 1 year ago)
- Topics: ai, llm, miniflux, miniflux-extension, openai, rss
- Language: Python
- Homepage:
- Size: 40 KB
- Stars: 74
- Watchers: 1
- Forks: 9
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# miniflux-ai
Miniflux with AI
This project integrates with Miniflux to fetch RSS feed content via API or webhook. It then utilizes large language models (e.g., Ollama, ChatGPT, LLaMA, Gemini) to generate summaries, translations, and AI-driven news insights.
## Features
- **Miniflux Integration**: Seamlessly fetch unread entries from Miniflux or trigger via webhook.
- **LLM Processing**: Generate summaries, translations, etc. based on your chosen LLM agent.
- **AI News**: Use the LLM agent to generate AI morning and evening news from feed content.
- **Flexible Configuration**: Easily modify or add new agents via the `config.yml` file.
- **Markdown and HTML Support**: Outputs in Markdown or styled HTML blocks, depending on configuration.
summaries, translations
AI News
## Requirements
- Python 3.11+
- Dependencies: Install via `pip install -r requirements.txt`
- Miniflux API Key
- API Key compatible with OpenAI-compatible LLMs (e.g., Ollama for LLaMA 3.1)
## Configuration
The repository includes a template configuration file: `config.sample.yml`. Modify the `config.yml` to set up:
> If using a webhook, enter the URL in Settings > Integrations > Webhook > Webhook URL.
>
> If deploying in a container alongside Miniflux, use the following URL:
> http://miniflux_ai/api/miniflux-ai.
- **Miniflux**: Base URL and API key.
- **LLM**: Model settings, API key, and endpoint.Add timeout, max_workers parameters due to multithreading
- **AI News**: Schedule and prompts for daily news generation
- **Agents**: Define each agent's prompt, allow_list/deny_list filters, and output style（`style_block` parameter controls whether the output is formatted as a code block in Markdown）.
## Docker Setup
The project includes a `docker-compose.yml` file for easy deployment:
> If using webhook or AI news, it is recommended to use the same docker-compose.yml with miniflux and access it via container name.
```yaml
services:
miniflux_ai:
container_name: miniflux_ai
image: ghcr.io/qetesh/miniflux-ai:latest
restart: always
environment:
TZ: Asia/Shanghai
volumes:
- ./config.yml:/app/config.yml
```
Refer to `config.sample.*.yml`, create `config.yml`
To start the services:
```bash
docker-compose up -d
```
## Usage
1. Ensure `config.yml` is properly configured.
2. Run the script: `python main.py`
3. The script will fetch unread RSS entries, process them with the LLM, and update the content in Miniflux.
## Roadmap
- [x] Add daily summary(by title, Summary of existing AI)
- [x] Add Morning and Evening News（e.g. 9/24: AI Morning News, 9/24: AI Evening News）
- [x] Add timed summary
## FAQ
If the formatting of summary content is incorrect, add the following code in Settings > Custom CSS:
```
pre code {
white-space: pre-wrap;
word-wrap: break-word;
}
```
## Contributing
Feel free to fork this repository and submit pull requests. Contributions and issues are welcome!
## Star History
[](https://star-history.com/#Qetesh/miniflux-ai&Date)
## License
This project is licensed under the MIT License.