AI directory search
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
7 matches for "ocr"
Mistral models docs · Beginner to advanced
Official material for comparing current Mistral families such as Devstral, Magistral, Voxtral, OCR, and newer Small and Medium models across coding, reasoning, and multimodal use cases.
Topics
Mistral models, Open models, Model selection, Agents, Coding, Reasoning, Multimodal AI
Model docs · Cohere · Intermediate
You need Cohere's August 27, 2026 document-parsing model for turning PDFs, slides, forms, tables, and images into structured Markdown before embedding, reranking, or agent retrieval.
cohere, parse, document ai, rag, ocr
Model docs · Mistral AI · Beginner to advanced
You need to compare current Mistral families such as Devstral, Magistral, Voxtral, OCR, and general-purpose models.
mistral, open models, commercial models, model selection, coding
Guide · DeepSeek · Intermediate
You need the operational guide for image inputs, token usage, supported formats, and multimodal prompting after the August 21, 2026 launch of `deepseek-v4-flash-vision-exp`.
deepseek, vision, multimodal, agents, ocr
Guide · Mistral AI · Intermediate
You want Mistral's current document-AI path for OCR, PDF extraction, and downstream RAG or automation workflows instead of treating OCR as a separate stack.
mistral, ocr, document ai, multimodal, extraction
Model docs · Mistral AI · Intermediate
You want the current OCR 4.1 model page before building document parsing, block-level extraction, or PDF-to-RAG workflows on older Mistral OCR assumptions.
mistral, ocr, document ai, bounding boxes, confidence scores
Model docs · Cohere · Intermediate
You want Cohere's current multimodal Command model for chart reading, document OCR, and image-grounded enterprise workflows instead of assuming Command is text-only.
cohere, command a vision, vision, documents, ocr