Metadata-Version: 2.4
Name: mistralai-workflows
Version: 3.0.0a3
Summary: Mistral Workflows - Build reliable AI workflows with Python
Project-URL: Homepage, https://mistral.ai
Project-URL: Documentation, https://docs-internal-frameworks.mistral.ai/workflows
Author-email: Mistral AI <support@mistral.ai>
License: Apache-2.0
License-File: LICENSE
Keywords: ai,llm,mistral,orchestration,temporal,workflows
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: <3.15,>=3.12
Requires-Dist: asynciolimiter<2.0.0,>=1.2.0
Requires-Dist: cryptography<47.0.0,>=41.0.0
Requires-Dist: httpx<1.0.0,>=0.27.0
Requires-Dist: jsonpatch<2.0.0,>=1.33
Requires-Dist: mistralai==2.2.0rc3
Requires-Dist: opentelemetry-api<2.0.0,>=1.30.0
Requires-Dist: opentelemetry-exporter-otlp-proto-http<2.0.0,>=1.30.0
Requires-Dist: opentelemetry-instrumentation-asyncio<0.70b0,>=0.60b1
Requires-Dist: opentelemetry-instrumentation-fastapi<0.70b0,>=0.60b1
Requires-Dist: opentelemetry-instrumentation-httpx<0.70b0,>=0.60b1
Requires-Dist: opentelemetry-sdk<2.0.0,>=1.30.0
Requires-Dist: orjson<4.0.0,>=3.10.15
Requires-Dist: pydantic-settings<3.0.0,>=2.7.1
Requires-Dist: pydantic<3.0.0,>=2.12.0
Requires-Dist: structlog<26,>=24
Requires-Dist: temporalio<1.23.0,>=1.18.1
Requires-Dist: tenacity<10.0.0,>=9.1.2
Provides-Extra: all
Requires-Dist: aioboto3<13.0.0,>=12.4.0; extra == 'all'
Requires-Dist: aiocache<1.0.0,>=0.12.3; extra == 'all'
Requires-Dist: azure-storage-blob[aio]<13.0.0,>=12.28.0; extra == 'all'
Requires-Dist: gcloud-aio-storage<10.0.0,>=9.3.0; extra == 'all'
Requires-Dist: mcp<2.0.0,>=1.12.4; extra == 'all'
Requires-Dist: mistralai-workflows-plugins-mistralai<4.0.0,>=3.0.0a1; extra == 'all'
Requires-Dist: mistralai-workflows-plugins-webhook<4.0.0,>=3.0.0a1; extra == 'all'
Requires-Dist: opentelemetry-instrumentation-aiohttp-client<0.70b0,>=0.60b1; extra == 'all'
Provides-Extra: all-plugins
Requires-Dist: aiocache<1.0.0,>=0.12.3; extra == 'all-plugins'
Requires-Dist: mcp<2.0.0,>=1.12.4; extra == 'all-plugins'
Requires-Dist: mistralai-workflows-plugins-mistralai<4.0.0,>=3.0.0a1; extra == 'all-plugins'
Requires-Dist: mistralai-workflows-plugins-webhook<4.0.0,>=3.0.0a1; extra == 'all-plugins'
Provides-Extra: azure
Requires-Dist: azure-storage-blob[aio]<13.0.0,>=12.28.0; extra == 'azure'
Provides-Extra: gcs
Requires-Dist: gcloud-aio-storage<10.0.0,>=9.3.0; extra == 'gcs'
Requires-Dist: opentelemetry-instrumentation-aiohttp-client<0.70b0,>=0.60b1; extra == 'gcs'
Provides-Extra: mistralai
Requires-Dist: aiocache<1.0.0,>=0.12.3; extra == 'mistralai'
Requires-Dist: mcp<2.0.0,>=1.12.4; extra == 'mistralai'
Requires-Dist: mistralai-workflows-plugins-mistralai<4.0.0,>=3.0.0a1; extra == 'mistralai'
Provides-Extra: s3
Requires-Dist: aioboto3<13.0.0,>=12.4.0; extra == 's3'
Provides-Extra: storage
Requires-Dist: aioboto3<13.0.0,>=12.4.0; extra == 'storage'
Requires-Dist: azure-storage-blob[aio]<13.0.0,>=12.28.0; extra == 'storage'
Requires-Dist: gcloud-aio-storage<10.0.0,>=9.3.0; extra == 'storage'
Requires-Dist: opentelemetry-instrumentation-aiohttp-client<0.70b0,>=0.60b1; extra == 'storage'
Provides-Extra: webhook
Requires-Dist: mistralai-workflows-plugins-webhook<4.0.0,>=3.0.0a1; extra == 'webhook'
Description-Content-Type: text/markdown

# Mistral Workflows

Build reliable, production-grade AI workflows with Python.

## Overview

Mistral Workflows is a Python SDK for building AI-powered workflows with built-in reliability, observability, and scalability. It provides fault tolerance, durability, and exactly-once execution guarantees.

## Features

- **Simple Python API**: Define workflows using Python decorators
- **Built-in Reliability**: Automatic retries, timeouts, and error handling
- **Distributed Execution**: Scale workflows across multiple workers
- **LLM Integration**: Native support for Mistral AI and other LLM providers
- **Observability**: Distributed tracing, structured logging, and event streaming
- **Type Safety**: Full type hints and Pydantic validation

## Installation

```bash
pip install mistralai-workflows
```

## Quick Start

```python
from datetime import timedelta

from mistralai.workflows import workflow, activity

@activity
async def get_weather(city: str) -> str:
    # Your activity implementation
    return f"Weather in {city}: Sunny"

@workflow.define
class WeatherWorkflow:
    @workflow.run
    async def run(self, city: str) -> str:
        weather = await workflow.execute_activity(
            get_weather,
            city,
            start_to_close_timeout=timedelta(seconds=10),
        )
        return weather
```

## Documentation

For full documentation, visit [docs.mistral.ai/workflows](https://docs.mistral.ai/workflows)

## Examples

The SDK includes comprehensive examples in the `mistralai/workflows/examples` directory. You can run all examples with a single command:

```bash
# Run all example workflows in a single worker
python -m mistralai.workflows.examples.all_workflows_worker
```

## License

Apache License 2.0 - see [LICENSE](LICENSE) for details.
