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
OCR Processor | Mistral Docs
3+ hour, 12+ min 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…...
Speech Generation | Mistral Docs
2+ day, 11+ hour ago (150+ words) Speech Generation Mistral AI Documentation Generate speech from text using a saved voice ( voice_id ) or a one-off reference audio clip ( ref_audio ). Generate speech using a previously saved voice ( voice_id ) identifier. - Language match: the voice prompt should be in the same language as the…...
Sampling | Mistral Docs
2+ day, 11+ hour ago (157+ words) Here, we will discuss the sampling settings that influence the output of Large Language Models (LLMs). This guide covers parameters such as Temperature, N, Top P, Presence Penalty, and Frequency Penalty, and explains how to adjust them. Whether you aim…...
Code Embeddings | Mistral Docs
2+ day, 11+ hour ago (465+ words) Embeddings are at the core of multiple enterprise use cases, such as retrieval systems, clustering, code analytics, classification, and a variety of search applications. With code embedings, you can embed code databases and repositories, and power coding assistants with state-of-the-art…...
GPTQ - Mistral AI Cookbook
2+ week, 6+ day ago (166+ words) GPTQ is a quantization format optimized for GPU inference. It makes use of a calibration dataset to improve its quantizations. Let's do a short demo and quantize Mistral 7B. First, we install auto-gptq. It will allow us to easily quantize and…...
Concept Deep Dive: Quantization - Mistral AI Cookbook
2+ week, 6+ day ago (575+ words) When we want to run an LLM, also called Inference, we need to load the entire model, including all of its parameters, to perform the necessary computations. This requirement scales linearly with RAM/VRAM, meaning that larger models necessitate more…...
Getting started with Mistral AI API - Mistral AI Cookbook
2+ week, 6+ day ago (207+ words) Getting started with Mistral AI API Mistral AI Documentation - 🐫 CAMEL Role-Playing Scraper for Report & Knowledge Graph Generation - 🐫 Using CAMEL to Do Graph RAG with Mistral Models - 🛰️ Finetuning Pixtral on a satellite imagery dataset 🛰️ - 00 — Concepts: a visual tour of the Mistral…...
Search Toolkit | Mistral Docs
2+ mon, 2+ week ago (180+ words) LLMs are not trained on your private data. To ground their answers in your documents you need a retrieval pipeline that ingests, indexes, and searches your content. Search Toolkit gives you every building block to assemble that pipeline. Ingestion transforms…...
Install and setup | Mistral Docs
2+ mon, 2+ week ago (239+ words) Install the Vibe CLI, run vibe in your project, and complete the setup prompt. On a different surface? This page covers the CLI specifically. If you'd rather work inside your editor or against a remote repo, jump to VS Code…...
Generate images | Mistral Docs
2+ mon, 2+ week ago (257+ words) Work can generate and edit images directly in the chat interface. Describe what you need in plain language and get visuals you can use for presentations, product mockups, marketing materials, and more. Work uses Black Forest Labs models for image…...