Mistral AI Automation
Automate Mistral AI operations -- manage files and libraries, upload documents for fine-tuning, batch processing, and OCR, track fine-tuning jobs, and build RAG pipelines via the Composio MCP integration.
What this skill does
# 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](https://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
| Pitfall | Detail |
|---------|--------|
| Fine-tune file format | Only `.jsonl` files are supported for fine-tuning uploads. Other formats will be rejected. |
| File size limit | Maximum upload size is 512 MB per file. |
| File object structure | `MISTRAL_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 cursors | `MISTRAL_AI_LIST_FILES` uses cursor-based pagination via the `after` parameter (file ID). Continue fetching until no more results are returned. |
| Library document processing | Uploaded library documents are processed asynchronously. They may not be immediately available for RAG queries after upload. |
| Schema references | Several 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 Slug | Description |
|-----------|-------------|
| `MISTRAL_AI_UPLOAD_FILE` | Upload files for fine-tuning, batch processing, or OCR |
| `MISTRAL_AI_LIST_FILES` | List uploaded files with pagination |
| `MISTRAL_AI_RETRIEVE_FILE` | Get metadata for a specific file by ID |
| `MISTRAL_AI_DOWNLOAD_FILE` | Download content of an uploaded file |
| `MISTRAL_AI_CREATE_LIBRARY` | Create a document library for RAG |
| `MISTRAL_AI_LIST_LIBRARIES` | List all document libraries with metadata |
| `MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT` | Add a document to a library for RAG |
| `MISTRAL_AI_GET_FINE_TUNING_JOBS` | List and filter fine-tuning jobs |
---
*Powered by [Composio](https://composio.dev)*
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.