Repository files navigation

A toy project reimplementingopen_deep_research withpydantic-ai. All code logic and prompts are from the original project - I'm just playing around and learning

⚠️ This is just for fun and learning! If you need something reliable, please use the original project.

This project usesuv as the package manager. Simply run:

uv sync

1. You'll need these API keys:

   • Tavily API key (required for web search)
   • Choose at least one of these:
     • OpenAI API key (if using OpenAI as provider)
     • Anthropic API key (if using Anthropic as provider)

2. Copy.env.example to.env, configure your settings:

# RequiredTAVILY_API_KEY=your-tavily-key# Choose your providers and fill corresponding API keysPLANNER_PROVIDER=openai# or anthropicWRITER_PROVIDER=anthropic# or openai# If using OpenAIOPENAI_API_KEY=sk-xxxOPENAI_BASE_URL=# optional, default is official API# If using AnthropicANTHROPIC_API_KEY=xxxANTHROPIC_BASE_URL=# optional# Optional settingsPLANNER_MODEL=o3-mini# model for planningWRITER_MODEL=claude-3.5-sonnet# model for writingNUMBER_OF_QUERIES=3# searches per sectionMAX_SEARCH_DEPTH=2# max research iterationsMAX_RETRIES=3# API call retriesREPORT_STRUCTURE=# custom report template

3. Run it:

python cli.py"your topic"

Here's what happens when you run it:

All operations are logged tologfire, where you can track the execution flow:

The logs show:

• Search queries generation
• Web search operations
• Section writing progress
• Model API calls

Well... pretty much everything 😂

• Quality is totally unpredictable
• Error handling is minimal
• Code is messy
• Test coverage? What's that?

Huge thanks toopen_deep_research! This is just a learning exercise based on their amazing work.

MIT (do whatever you want, but don't blame me if it breaks 😉)