MistralOCR

pip install chonkie[mistral]

from chonkie import MistralOCR

# Default initialization (uses MISTRAL_API_KEY env var)
ocr = MistralOCR()

# Custom model and explicit API key
ocr = MistralOCR(model="mistral-ocr-2505", api_key="sk-...")

from chonkie import MistralOCR

ocr = MistralOCR()

# Single file
doc = ocr.process("research_paper.pdf")
print(doc.content)
print(f"Source: {doc.metadata['filename']}")

# Multiple files
docs = ocr.process_batch(["page1.png", "page2.png"])

# Async
import asyncio
doc = asyncio.run(ocr.aprocess("document.pdf"))

from chonkie import Pipeline

# Process a PDF with OCR and chunk it
doc = (Pipeline()
    .fetch_from("file", path="document.pdf")
    .process_with("mistral")
    .chunk_with("recursive", chunk_size=512)
    .run())

print(f"Extracted {len(doc.chunks)} chunks from PDF")

from chonkie import Pipeline

docs = (Pipeline()
    .fetch_from("file", dir="./scanned_docs", ext=[".pdf", ".png"])
    .process_with("mistral")
    .chunk_with("recursive", chunk_size=1024)
    .refine_with("overlap", context_size=100)
    .store_in("qdrant", collection_name="scanned_documents")
    .run())

print(f"Ingested {len(docs)} documents")

from chonkie import Pipeline

doc = (Pipeline()
    .fetch_from("file", path="textbook_chapter.pdf")
    .process_with("mistral")
    .chunk_with("semantic", threshold=0.8, chunk_size=1024)
    .refine_with("embedding", model="text-embedding-3-small")
    .export_with("json", file="textbook_chunks.json")
    .run())

from chonkie import MistralOCR, RecursiveChunker

# Step 1: Extract text from PDF
ocr = MistralOCR()
doc = ocr.process("report.pdf")

# Step 2: Chunk the extracted content
chunker = RecursiveChunker(chunk_size=512)
chunks = chunker.chunk(doc.content)

# Step 3: Store chunks in the document
doc.chunks = chunks

print(f"Document: {doc.metadata['filename']}")
print(f"  Content: {len(doc.content)} characters")
print(f"  Chunks: {len(doc.chunks)}")