Metadata-Version: 2.4
Name: mistralai-workflows-plugins-mistralai
Version: 2.0.0
Summary: Mistral AI plugin for Mistral Workflows - Provides native Mistral AI integration
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,plugin,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: <3.13,>=3.12
Requires-Dist: aiocache>=0.12.3
Requires-Dist: authlib>=1.3.0
Requires-Dist: griffe>=1.0.0
Requires-Dist: mcp>=1.12.4
Requires-Dist: mistralai-workflows<2.1.0,>=2.0.0b1
Requires-Dist: mistralai>=1.8.1
Requires-Dist: structlog<26,>=24
Description-Content-Type: text/markdown

# Mistral Workflows - Mistral AI Plugin

Native Mistral AI integration for Mistral Workflows.

## Overview

This plugin provides Mistral AI-specific activities and models for building AI workflows with the Mistral AI API.

## Features

- **Mistral AI Activities**: Pre-built activities for chat completions, embeddings, and more
- **Streaming Support**: Native streaming for chat responses
- **Model Definitions**: Type-safe model configurations
- **Agent Runtime**: Build and run autonomous AI agents
- **Session Management**: Stateful agent sessions with context persistence
- **MCP Support**: Model Context Protocol integration for tool use
- **Tool Execution**: Built-in tool calling and execution framework

## Installation

```bash
pip install mistralai-workflows[mistralai]
```

Or install directly:

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

## Quick Start

```python
import mistralai_workflows as workflows
import mistralai_workflows.plugins.mistralai as workflows_mistralai


@workflows.workflow.define(name="chat-workflow")
class ChatWorkflow:
    @workflows.workflow.entrypoint
    async def run(self, prompt: str) -> str:
        response = await workflows_mistralai.mistralai_chat_stream(
            workflows_mistralai.ChatCompletionRequest(
                model="mistral-medium-latest",
                messages=[workflows_mistralai.UserMessage(content=prompt)],
            )
        )
        return response.content
```

## Documentation

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

## Examples

Run examples with:

```bash
python -m mistralai_workflows.examples.assist.workflow_multi_turn_chat
python -m mistralai_workflows.examples.assist.workflow_insurance_claims
python -m mistralai_workflows.examples.assist.workflow_local_session_streaming
python -m mistralai_workflows.examples.assist.workflow_travel_agent_streaming
python -m mistralai_workflows.examples.assist.workflow_with_agent
python -m mistralai_workflows.examples.assist.workflow_extract_markdown
python -m mistralai_workflows.examples.assist.workflow_embeddings
```

## License

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