Mandala
Tools

Mistral Parser

Extract text from PDF documents

Usage Instructions

Integrate Mistral Parse into the workflow. Can extract text from uploaded PDF documents, or from a URL.

Tools

mistral_parser

Parse PDF documents using Mistral OCR API

Input

ParameterTypeRequiredDescription
filePathstringYesURL to a PDF document to be processed
resultTypestringNoType of parsed result (markdown, text, or json). Defaults to markdown.
pagesarrayNoSpecific pages to process (array of page numbers, starting from 0)
apiKeystringNoMistral API key (MISTRAL_API_KEY) - required unless provider is azure-mistral
providerstringNoOCR provider to use: "mistral" (default) or "azure-mistral"
azureEndpointstringNoFull Azure OCR endpoint URL - required when provider is azure-mistral
azureApiKeystringNoAzure AI Foundry API key - required when provider is azure-mistral
azureModelNamestringNoAzure OCR deployment name - required when provider is azure-mistral

Output

ParameterTypeDescription
successbooleanWhether the PDF was parsed successfully
contentstringExtracted content in the requested format (markdown, text, or JSON)
metadataobjectProcessing metadata including jobId, fileType, pageCount, and usage info

Notes

  • Category: tools
  • Type: mistral_parse
Mistral Parser