Metadata-Version: 2.5
Name: langchain-chartquery
Version: 0.1.0
Summary: LangChain tools for ChartQuery: turn data into charts, descriptions into diagrams, and text into QR codes, as image links.
Project-URL: Homepage, https://www.chartquery.com
Project-URL: Documentation, https://github.com/chartquery/langchain-chartquery#readme
Project-URL: Repository, https://github.com/chartquery/langchain-chartquery
Project-URL: Issues, https://github.com/chartquery/langchain-chartquery/issues
Author-email: ChartQuery <contact@chartquery.com>
License-Expression: MIT
License-File: LICENSE
Keywords: agents,chartjs,chartquery,charts,data-visualization,diagrams,langchain,mermaid,qrcode,tools
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Internet :: WWW/HTTP
Classifier: Typing :: Typed
Requires-Python: >=3.10
Requires-Dist: httpx<1,>=0.27
Requires-Dist: langchain-core<2,>=0.3.15
Provides-Extra: test
Requires-Dist: langchain-tests>=0.3.5; extra == 'test'
Requires-Dist: pytest-asyncio>=0.24; extra == 'test'
Requires-Dist: pytest>=8.3; extra == 'test'
Requires-Dist: ruff<1,>=0.8; extra == 'test'
Description-Content-Type: text/markdown

# langchain-chartquery

[LangChain](https://www.langchain.com) integration for [ChartQuery](https://www.chartquery.com): turn data into charts, descriptions into diagrams, and text into QR codes, as image links.

## Installation

```bash
pip install -U langchain-chartquery
export CHARTQUERY_API_KEY="your-api-key"
```

Get an API key at [app.chartquery.com](https://app.chartquery.com).

## Tools

| Class | Tool name | What it does |
| --- | --- | --- |
| `ChartQueryChart` | `chartquery_chart` | Render a Chart.js chart through ChartQuery and return links to the image. |
| `ChartQueryChartFromPrompt` | `chartquery_chart_from_prompt` | Build a chart from a plain-words description through ChartQuery. |
| `ChartQueryDiagram` | `chartquery_diagram` | Render a diagram from its source through ChartQuery. |
| `ChartQueryQRCode` | `chartquery_qr_code` | Generate a QR code through ChartQuery. |

Each tool takes `api_key` (defaults to `CHARTQUERY_API_KEY`), `base_url` and `timeout`, plus the settings shown in its docstring. Errors (invalid key, no credits, rate limit, timeout) come back to the model as a `ToolException` message, without the API key. Every tool has an async version.

```python
from langchain_chartquery import ChartQueryChart

tool = ChartQueryChart()
print(tool.invoke({"chart_config": '{"type": "bar", "data": {"labels": ["a"]}}'}))
```

### In an agent

```python
from langchain.agents import create_agent
from langchain_chartquery import ChartQueryChart, ChartQueryChartFromPrompt, ChartQueryDiagram

agent = create_agent("openai:gpt-4.1-mini", tools=[ChartQueryChart(), ChartQueryChartFromPrompt(), ChartQueryDiagram()])
result = agent.invoke({"messages": [{"role": "user", "content": "..."}]})
```

## Development

```bash
pip install -e ".[test]"
pytest tests/unit_tests
```

## License

MIT
