Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 27 additions & 13 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -169,29 +169,43 @@ agent = A1() # Everything uses gpt-4, 1200s timeout

For detailed configuration options, see the **[Configuration Guide](docs/configuration.md)**.

### PDF Generation

## Running Tests
Generate PDF reports of execution traces:

Biomni uses Python's built-in unittest framework.
```python
from biomni.agent import A1

# Initialize agent
agent = A1(path='./data', llm='claude-sonnet-4-20250514')

- Run all tests in the tests/ folder (recommended):
# Run your task
agent.go("Your biomedical task here")

```bash
python3 -m unittest discover -s tests -p 'test_*.py' -q
# Save conversation history as PDF
agent.save_conversation_history("my_analysis_results.pdf")
```

- Run only the glycoengineering tests:
**PDF Generation Dependencies:**

For optimal PDF generation, install one of these packages:

```bash
python3 -m unittest -q tests/test_glycoengineering.py
```
# Option 1: WeasyPrint (recommended for best layout control)
pip install weasyprint

Notes:
- The top-level package import may require optional dependencies (e.g., pandas). The commands above restrict discovery to the tests/ folder to avoid importing the entire biomni package during discovery.
- Ensure you are in your Biomni environment before running tests:
# Option 2: markdown2pdf (Rust-based, fast and reliable)
# macOS:
brew install theiskaa/tap/markdown2pdf

```bash
conda activate biomni_e1
# Windows/Linux (using Cargo):
cargo install markdown2pdf

# Or download prebuilt binaries from:
# https://github.com/theiskaa/markdown2pdf/releases/latest

# Option 3: Pandoc (pip installation)
pip install pandoc
```

## MCP (Model Context Protocol) Support
Expand Down
Loading