deepdata/deepflow/docs/FAQ.md

FAQ

Table of Contents

• Where's the name DeepFlow come from?
• Which models does DeepFlow support?
• How do I view complete model output?
• How do I enable debug logging?
• How do I troubleshoot issues?

Where's the name DeepFlow come from?

DeepFlow is short for Deep Exploration and Efficient Research Flow. It is named after the deer, which is a symbol of gentleness and elegance. We hope DeepFlow can bring a gentle and elegant deep research experience to you.

Which models does DeepFlow support?

Please refer to the Configuration Guide for more details.

How do I view complete model output?

If you want to see the complete model output, including system prompts, tool calls, and LLM responses:

1. Enable debug logging by setting DEBUG=True in your .env file

2. Enable LangChain verbose logging by adding these to your .env:

   LANGCHAIN_VERBOSE=true
   LANGCHAIN_DEBUG=true
   

3. Use LangSmith tracing for visual debugging (recommended for production):

   LANGSMITH_TRACING=true
   LANGSMITH_API_KEY="your-api-key"
   LANGSMITH_PROJECT="your-project-name"
   

For detailed instructions, see the Debugging Guide.

How do I enable debug logging?

To enable debug logging:

1. Open your .env file
2. Set DEBUG=True
3. Restart your application

For Docker Compose:

docker compose restart

For development:

uv run main.py

You'll now see detailed logs including:

• System prompts sent to LLMs
• Model responses
• Tool execution details
• Workflow state transitions

See the Debugging Guide for more options.

How do I troubleshoot issues?

When encountering issues:

1. Check the logs: Enable debug logging as described above
2. Review configuration: Ensure your .env and conf.yaml are correct
3. Check existing issues: Search GitHub Issues for similar problems
4. Enable verbose logging: Use LANGCHAIN_VERBOSE=true for detailed output
5. Use LangSmith: For visual debugging, enable LangSmith tracing

For Docker-specific issues:

# View logs
docker compose logs -f

# Check container status
docker compose ps

# Restart services
docker compose restart

For more detailed troubleshooting steps, see the Debugging Guide.