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
- Le Chat UI: Conversational UI components for Le Chat (canvas, assistant messages, UI components)
Installation
pip install mistralai-workflows[mistralai]
Or install directly:
pip install mistralai-workflows-plugins-mistralai
Quick Start
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.mistral.ai/workflows/getting-started/introduction
Examples
Run examples with:
python -m mistralai_workflow_tests.examples.assist.workflow_multi_turn_chat
python -m mistralai_workflow_tests.examples.assist.workflow_insurance_claims
python -m mistralai_workflow_tests.examples.assist.workflow_local_session_streaming
python -m mistralai_workflow_tests.examples.assist.workflow_travel_agent_streaming
python -m mistralai_workflow_tests.examples.assist.workflow_with_agent
python -m mistralai_workflow_tests.examples.assist.workflow_extract_markdown
python -m mistralai_workflow_tests.examples.assist.workflow_embeddings
License
Apache License 2.0 - see LICENSE for details.
Metadata
Release files for mistralai-workflows-plugins-mistralai 3.12.0
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_plugins_mistralai-3.12.0.tar.gz | 115.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mistralai_workflows_plugins_mistralai-3.12.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 182.2 kB
Release files / mistralai_workflows_plugins_mistralai-3.12.0.tar.gz
| Download URL | mistralai_workflows_plugins_mistralai-3.12.0.tar.gz |
|---|---|
| Size | 115.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
be945a3e44145abdcc35f4e097dfe645e2819ab1012f11bfe40ab58f5901b5c3
|
|
BLAKE2b-256 checksum How to use checksums |
47a78ec21c79640ca2e62314e92007147a008187eb82ba0cd1c17854fe8f3b17
|
| 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 Aug 28, 2026.
Transparency logRelease files / mistralai_workflows_plugins_mistralai-3.12.0-py3-none-any.whl
| Download URL | mistralai_workflows_plugins_mistralai-3.12.0-py3-none-any.whl |
|---|---|
| Size | 67.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d6b93b94cb5eb8ad70dbaba76ff8ca17d700df09fe93391443175571b4011dfe
|
|
BLAKE2b-256 checksum How to use checksums |
bff63d86dea85634e61dbdfee6608bab6fbcf6f8516dc783197c2ff3738342f3
|
| 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 Aug 28, 2026.
Transparency log