Full flow of report generation
1. Subject input: Specify the research topic via command line parameters, such aspython main.py --topic "量子计算应用"
2. masterplan::
- System automatically generates proposal outlines (customizable JSON structure)
- Support for manual restructuring of chapters
3. information retrieval::
- Multi-round web search via the Tavily API
- Automatic de-emphasis and assessment of information quality
- Generate targeted sub-problems to deepen research
4. Content generation::
- Integrate information into Markdown format reports
- Automatic addition of titles, sections and references
- Option to generate matching images/audio
Advanced Control
You can adjust the search depth (-max_search_depth), specify the output language, etc. via parameters. Typical tasks take 5-10 minutes, depending on the complexity of the topic.
This answer comes from the articleTogether Open Deep Research: Generating Indexed Deep Research ReportsThe
English 
简体中文 
日本語 
Deutsch 
Português do Brasil