Get the FREE Ultimate OpenClaw Setup Guide →

Mistral AI Automation

Scanned
npx machina-cli add skill ComposioHQ/awesome-claude-skills/mistral-ai-automation --openclaw
Files (1)
SKILL.md
4.9 KB

Mistral AI Automation

Automate your Mistral AI workflows -- upload files for fine-tuning, batch processing, and OCR, manage document libraries for RAG-enabled agents, list and retrieve files, track fine-tuning jobs, and integrate Mistral AI into cross-app data pipelines.

Toolkit docs: composio.dev/toolkits/mistral_ai


Setup

  1. Add the Composio MCP server to your client: https://rube.app/mcp
  2. Connect your Mistral AI account when prompted (API key authentication)
  3. Start using the workflows below

Core Workflows

1. Upload Files to Mistral AI

Use MISTRAL_AI_UPLOAD_FILE to upload files for fine-tuning, batch processing, or OCR.

Tool: MISTRAL_AI_UPLOAD_FILE
Inputs:
  - file: object (required)
    - name: string -- destination filename (e.g., "training_data.jsonl")
    - mimetype: string -- MIME type (e.g., "application/pdf", "application/jsonl")
    - s3key: string -- S3 key of a previously downloaded/stored file
  - purpose: "fine-tune" | "batch" | "ocr" (default "fine-tune")

Limits: Maximum file size is 512 MB. For fine-tuning, only .jsonl files are supported.

2. List and Retrieve Files

Use MISTRAL_AI_LIST_FILES to browse uploaded files with pagination, and MISTRAL_AI_RETRIEVE_FILE to get metadata for a specific file.

Tool: MISTRAL_AI_LIST_FILES
Inputs:
  - limit: integer (optional, min 1)
  - after: string (file ID cursor for next page)
  - order: "asc" | "desc" (default "desc")

Tool: MISTRAL_AI_RETRIEVE_FILE
Inputs:
  - file_id: string (required) -- UUID obtained from List Files

3. Create Document Libraries

Use MISTRAL_AI_CREATE_LIBRARY to group documents into libraries for use with RAG-enabled Mistral AI agents.

Tool: MISTRAL_AI_CREATE_LIBRARY
Inputs:
  - name: string (required) -- e.g., "Project Documents"
  - description: string (optional)

4. Upload Documents to a Library

Use MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT to add documents to a library for RAG retrieval by Mistral AI agents.

Tool: MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT
  - Requires library_id and file details
  - Call RUBE_GET_TOOL_SCHEMAS for full input schema before use

5. List Libraries and Download Files

Use MISTRAL_AI_LIST_LIBRARIES to discover available document libraries, and MISTRAL_AI_DOWNLOAD_FILE to retrieve file content.

Tool: MISTRAL_AI_LIST_LIBRARIES
  - Lists all document libraries with metadata (id, name, document counts)
  - Call RUBE_GET_TOOL_SCHEMAS for full input schema

Tool: MISTRAL_AI_DOWNLOAD_FILE
  - Downloads raw binary content of a previously uploaded file
  - Call RUBE_GET_TOOL_SCHEMAS for full input schema

6. Track Fine-Tuning Jobs

Use MISTRAL_AI_GET_FINE_TUNING_JOBS to list and filter fine-tuning jobs by model, status, and creation time.

Tool: MISTRAL_AI_GET_FINE_TUNING_JOBS
  - Supports filtering by model, status, creation time, and W&B integration
  - Call RUBE_GET_TOOL_SCHEMAS for full input schema

Known Pitfalls

PitfallDetail
Fine-tune file formatOnly .jsonl files are supported for fine-tuning uploads. Other formats will be rejected.
File size limitMaximum upload size is 512 MB per file.
File object structureMISTRAL_AI_UPLOAD_FILE requires an s3key referencing a previously stored file, not raw binary content. Use a download action first to stage files in S3.
Pagination cursorsMISTRAL_AI_LIST_FILES uses cursor-based pagination via the after parameter (file ID). Continue fetching until no more results are returned.
Library document processingUploaded library documents are processed asynchronously. They may not be immediately available for RAG queries after upload.
Schema referencesSeveral tools (MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT, MISTRAL_AI_LIST_LIBRARIES, MISTRAL_AI_GET_FINE_TUNING_JOBS, MISTRAL_AI_DOWNLOAD_FILE) require calling RUBE_GET_TOOL_SCHEMAS to load full input schemas before execution.

Quick Reference

Tool SlugDescription
MISTRAL_AI_UPLOAD_FILEUpload files for fine-tuning, batch processing, or OCR
MISTRAL_AI_LIST_FILESList uploaded files with pagination
MISTRAL_AI_RETRIEVE_FILEGet metadata for a specific file by ID
MISTRAL_AI_DOWNLOAD_FILEDownload content of an uploaded file
MISTRAL_AI_CREATE_LIBRARYCreate a document library for RAG
MISTRAL_AI_LIST_LIBRARIESList all document libraries with metadata
MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENTAdd a document to a library for RAG
MISTRAL_AI_GET_FINE_TUNING_JOBSList and filter fine-tuning jobs

Powered by Composio

Source

git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/mistral-ai-automation/SKILL.mdView on GitHub

Overview

Automate Mistral AI operations—from uploading files for fine-tuning, batch processing, and OCR to organizing libraries for RAG-enabled agents. Track fine-tuning jobs and build end-to-end data pipelines via the Composio MCP integration.

How This Skill Works

The skill orchestrates Mistral AI tasks through MCP-powered tools such as MISTRAL_AI_UPLOAD_FILE, MISTRAL_AI_LIST_FILES, MISTRAL_AI_CREATE_LIBRARY, MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT, and MISTRAL_AI_GET_FINE_TUNING_JOBS. You stage inputs by providing a file object (name, mimetype, s3key) and a purpose (fine-tune, batch, or ocr), then organize content into libraries for RAG-enabled agents and monitor tuning progress.

When to Use It

  • Upload a JSONL dataset to fine-tune a Mistral AI model (respecting the 512 MB limit).
  • Batch process or OCR large document sets and feed results into Mistral pipelines.
  • Create and populate document libraries for RAG-enabled agents.
  • List and retrieve file or library metadata to plan data workflows.
  • Track and filter ongoing fine-tuning jobs (model, status, creation time, W&B integration).

Quick Start

  1. Step 1: Set up MCP by adding the Composio MCP server (https://rube.app/mcp) and connect your Mistral AI account.
  2. Step 2: Upload a file with MISTRAL_AI_UPLOAD_FILE, providing a file object (name, mimetype, s3key) and a purpose (default fine-tune).
  3. Step 3: Create or list a library (MISTRAL_AI_CREATE_LIBRARY or MISTRAL_AI_LIST_LIBRARIES) and upload library documents as needed to build your RAG pipeline.

Best Practices

  • For fine-tuning, use only .jsonl files and keep each file within 512 MB.
  • Stage files in S3 and reference them with s3key in MISTRAL_AI_UPLOAD_FILE; do not upload raw binary content directly.
  • Use MISTRAL_AI_LIST_FILES with limit and after cursor to paginate through results.
  • Organize related documents into libraries with MISTRAL_AI_CREATE_LIBRARY and MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT for efficient RAG retrieval.
  • Consult RUBE_GET_TOOL_SCHEMAS for full input schemas when uploading library documents and monitor progress with MISTRAL_AI_GET_FINE_TUNING_JOBS (including W&B options).

Example Use Cases

  • A data science team uploads a 350 MB JSONL dataset to fine-tune a Mistral model and monitors the tuning status.
  • An enterprise creates a 'Product Docs' library, uploads manuals as library documents, and uses RAG-enabled agents to answer customer queries.
  • An operations team runs OCR on invoices, staging outputs via MISTRAL_AI_UPLOAD_FILE with purpose='ocr' and storing results in S3.
  • A knowledge base team lists libraries to audit content and downloads a file for backup or review.
  • A data ops workflow tracks fine-tuning jobs with filters for model and status, integrating with W&B for experiment tracking.

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers