admin-valentin/openai-agents-python
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update visualization.md

Browse source
This commit is contained in:
Rohan Mehta 2025-03-25 13:34:45 -04:00 committed by GitHub
parent 698fd69eb4
commit 6be9b2a222
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
docs/visualization.md
View file

@ -4,10 +4,10 @@ Agent visualization allows you to generate a structured graphical representation
## Installation
The visualization functionality relies on the **Graphviz** package. To use it, ensure you have Graphviz installed and add it as a dependency in `pyproject.toml`. Alternatively, install it directly via pip:
Install the optional `viz` dependency group:
```bash
pip install openai-agents[viz]
pip install "openai-agents[viz]"
```
## Generating a Graph
@ -83,24 +83,4 @@ draw_graph(triage_agent, filename="agent_graph.png")
This will generate `agent_graph.png` in the working directory.
## Testing the Visualization
The visualization functionality includes test coverage to ensure correctness. Tests are located in `tests/test_visualizations.py` and verify:
- Node and edge correctness in `get_main_graph()`.
- Proper agent and tool representation in `get_all_nodes()`.
- Accurate relationship mapping in `get_all_edges()`.
- Graph rendering functionality in `draw_graph()`.
Run tests using:
```bash
pytest tests/test_visualizations.py
```
## Conclusion
Agent visualization provides a powerful way to **understand, debug, and communicate** how agents interact within an application. By leveraging **Graphviz**, you can generate intuitive visual representations of complex agent structures effortlessly.
For further details on agent functionality, see the [Agents documentation](agents.md).