From mistral-ocr
Extracts text from images and PDFs using Mistral OCR API via curl. Converts scanned documents to Markdown, JSON, or plain text without external dependencies. Use for OCR and digitization tasks.
npx claudepluginhub parlamento-ai/parlamento-ai --plugin parlamento-ai-researchThis skill is limited to using the following tools:
Extract text from images and PDFs using Mistral's dedicated OCR API. No external dependencies required.
Converts PDF files to Markdown using opendataloader-pdf, extracting text, tables, headings, lists, and images in correct reading order. For PDF parsing, document extraction, and AI/LLM/RAG data preparation.
Parses complex PDFs and document images into Markdown and JSON using PaddleOCR API, preserving tables, formulas, charts, diagrams, and multi-column layouts.
Converts PDF files to markdown using local GLM-OCR via Ollama. Renders each page to image, runs OCR, assembles clean text output. Use for extracting text from PDFs.
Share bugs, ideas, or general feedback.
Extract text from images and PDFs using Mistral's dedicated OCR API. No external dependencies required.
This skill requires a Mistral API key. If you don't have one, follow the guide in reference/getting-started.md.
The user must provide their Mistral API key. Ask for it if not available.
Option 1 (Recommended for AI agents): User provides key directly in message:
"Use this Mistral key: aBc123XyZ..."
"Convert this PDF to markdown, my API key is aBc123XyZ..."
Option 2: Environment variable $MISTRAL_API_KEY
Option 3: Claude Code settings (~/.claude/settings.json)
If no key is available, guide the user to get one at console.mistral.ai.
Use the dedicated OCR endpoint for all document processing:
POST https://api.mistral.ai/v1/ocr
Model: mistral-ocr-latest
curl -s "https://api.mistral.ai/v1/ocr" \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral-ocr-latest",
"document": {
"type": "document_url",
"document_url": "https://example.com/document.pdf"
}
}'
Works with JPG, PNG, WEBP, GIF:
curl -s "https://api.mistral.ai/v1/ocr" \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral-ocr-latest",
"document": {
"type": "image_url",
"image_url": "https://example.com/image.jpg"
}
}'
For local PDFs or images, encode as base64 and use a data URL.
ALWAYS use curl (works on all platforms including Windows via Git Bash):
# For local PDF
BASE64=$(base64 -w0 document.pdf)
curl -s "https://api.mistral.ai/v1/ocr" \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral-ocr-latest",
"document": {
"type": "document_url",
"document_url": "data:application/pdf;base64,'"$BASE64"'"
}
}'
# For local images (PNG, JPG, etc.)
BASE64=$(base64 -w0 image.png)
curl -s "https://api.mistral.ai/v1/ocr" \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral-ocr-latest",
"document": {
"type": "image_url",
"image_url": "data:image/png;base64,'"$BASE64"'"
}
}'
MIME types:
data:application/pdf;base64,...data:image/png;base64,...data:image/jpeg;base64,...data:image/webp;base64,...For invoices, forms, tables - ask for JSON in a follow-up or use Document AI annotations.
The API returns markdown directly:
{
"pages": [
{
"index": 0,
"markdown": "# Document Title\n\nExtracted content here...",
"images": [],
"tables": [],
"dimensions": {"dpi": 200, "height": 842, "width": 595}
}
],
"model": "mistral-ocr-latest",
"usage_info": {"pages_processed": 1, "doc_size_bytes": 12345}
}
# Cross-platform temp directory
TMPDIR="${TMPDIR:-${TEMP:-/tmp}}"
# Step 1: Encode file to base64
base64 -w0 "document.pdf" > "$TMPDIR/b64.txt"
# Step 2: Create JSON request file
echo '{"model":"mistral-ocr-latest","document":{"type":"document_url","document_url":"data:application/pdf;base64,'$(cat "$TMPDIR/b64.txt")'"}}' > "$TMPDIR/request.json"
# Step 3: Call API with -d @file (use actual key, not variable)
curl -s "https://api.mistral.ai/v1/ocr" \
-H "Authorization: Bearer YOUR_API_KEY_HERE" \
-H "Content-Type: application/json" \
-d @"$TMPDIR/request.json" > "$TMPDIR/response.json"
# Step 4: Extract markdown with node (NOT jq - not available on all systems)
node -e "const fs=require('fs'); const r=JSON.parse(fs.readFileSync('$TMPDIR/response.json')); console.log(r.pages.map(p=>p.markdown).join('\n\n---\n\n'))"
-d @file for request body (handles large files)${TMPDIR:-${TEMP:-/tmp}} for temp files (works on all systems)When the user says:
| User Request | Action |
|---|---|
| "Convert this PDF to markdown" | OCR the PDF, save as .md file |
| "Extract text from this image" | OCR the image, return text |
| "Give me a .md of this document" | OCR and save as .md file |
| "What does this PDF say?" | OCR and summarize content |
| "OCR this receipt" | Extract text, optionally structure as JSON |
| Error | Cause | Solution |
|---|---|---|
| 401 Unauthorized | Invalid API key | Verify key, guide to getting-started.md |
| 400 Bad Request | Invalid document | Check format and URL accessibility |
| 3310 File fetch error | URL not accessible | Use base64 for local files |
| Rate limit | Too many requests | Wait and retry |
| Format | Support |
|---|---|
| ✅ Direct (no conversion) | |
| PNG | ✅ Direct |
| JPG/JPEG | ✅ Direct |
| WEBP | ✅ Direct |
| GIF | ✅ Direct |
No external dependencies required! Unlike other OCR solutions, Mistral OCR handles PDFs directly without needing pdftoppm, ImageMagick, or any other tools.
As of 2025, Mistral OCR pricing:
Check current rates at mistral.ai/pricing
Skill by Parlamento AI