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
pip install mistralai-workflows
Quick Start
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/getting-started/introduction
Examples
The SDK includes comprehensive examples in the mistralai/workflows/examples directory. You can run all examples with a single command:
# Run all example workflows in a single worker
python -m mistralai_workflow_tests.examples.all_workflows_worker
License
Apache License 2.0 - see LICENSE for details.
4 maintainers
Release files for mistralai-workflows 3.15.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| mistralai_workflows-3.15.0.tar.gz | 587.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mistralai_workflows-3.15.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.1 MB
Release files / mistralai_workflows-3.15.0.tar.gz
| Download URL | mistralai_workflows-3.15.0.tar.gz |
|---|---|
| Size | 587.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9393fa7ca47ff5496498e476041195d3e916de5ab9248b98d14eb8b8d0e87278
|
|
BLAKE2b-256 checksum How to use checksums |
83a03f22295f72c1bd9c91f65e9999e8a4e4ec41279d5025d487313c2253606e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 14, 2026.
Transparency logRelease files / mistralai_workflows-3.15.0-py3-none-any.whl
| Download URL | mistralai_workflows-3.15.0-py3-none-any.whl |
|---|---|
| Size | 468.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0d3759cedd93aa5fe05576ac140ea6300578aea32751415619b826cc05ac7b27
|
|
BLAKE2b-256 checksum How to use checksums |
b79630eb4b82df54ba38cc5099f11b8421f24516e7a4e53cf2c05d146c38bd17
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 14, 2026.
Transparency log
