Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Using prompts in chat completions | Mistral Docs
3+ day, 14+ hour ago (120+ words) The Prompt Registry lets you store, version, and manage prompts centrally in Studio. This guide shows how to retrieve a stored prompt and use it as the system message in a chat completion. Fetch the prompt by name or ID,…...
Policy-based content moderation with Shieldstral - Mistral AI Cookbook
4+ day, 17+ hour ago (470+ words) Shieldstral is self-hosted only—no Mistral API endpoint is available. This cookbook runs the model locally with Transformers or vLLM. Supply natural-language policies at inference time—no fixed categories, no retraining. The model answers a yes/no question about whether…...
Search Toolkit | Mistral Docs
4+ day, 17+ hour ago (207+ words) Search Toolkit is a Python framework for building information retrieval (IR) systems. It provides components for ingestion, retrieval, and evaluation. It works across backends, and every component can be swapped. LLMs are not trained on your private data. To ground…...
Manage schema | Mistral Docs
4+ day, 17+ hour ago (186+ words) Manage your Vespa application schemas through Python migrations. For the concepts behind schemas, fields, and ranking, see Anatomy of a Vespa application. Use migrations to define and modify your schemas. Migrations are Python files under vespa_app/migrations/ that are append-only, ordered…...
Libraries | Mistral Docs
4+ day, 17+ hour ago (377+ words) Libraries are persistent knowledge bases that you can fill with documents and connect to your agents for built-in retrieval-augmented generation (RAG). Upload PDFs, papers, or any document, and your agents can search through them on demand. This page covers how…...
Build a custom MCP server for Vibe - Mistral AI Cookbook
4+ day, 17+ hour ago (531+ words) Build a tic-tac-toe MCP server powered by Mistral, deploy it to Hugging Face Spaces, and connect it to Vibe to play directly from the chat interface. The following table outlines the five steps in this cookbook: The architecture follows a…...
Changelog | Mistral Docs
1+ week, 4+ day ago (84+ words) Find out about all the latest changes to our tool. You may filter by date and type of release. We released moderation API and batch API. MODEL RELEASED API UPDATED We introduced three new parameters: API UPDATED We downscaled the…...
OCR Processor | Mistral Docs
1+ week, 4+ day ago (312+ words) Use the Document AI OCR processor to extract text and structured content from PDF documents and images. The mistral-ocr-latest alias points to our latest OCR model. For endpoint details, see the OCR API reference. Table formatting as well as header…...
Regional inference | Mistral Docs
1+ week, 4+ day ago (422+ words) Mistral offers regional inference as an optional service through dedicated API endpoints. It supports processing inference requests by systems located within a chosen geography: currently the European Union or the United States. Use regional inference when you have data location…...
Build a Quickstart Generator with Connectors and Web Search (TypeScript) - Mistral AI Cookbook
1+ week, 5+ day ago (614+ words) You want to learn Polars, the fast DataFrame library for Python. You could read the docs, skim blog posts, and piece together a quickstart yourself — or you could let Mistral do it for you, with access to the right tools....