LiteParse

pip install chonkie[liteparse]

from chonkie import LiteParse

# Default initialization
chef = LiteParse()

# Custom configuration
chef = LiteParse(
    ocr_enabled=True,
    ocr_language="eng",
    dpi=300,
    max_pages=100,
    target_pages="1-10",
    num_workers=8,
)

from chonkie import LiteParse

chef = LiteParse()

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

# Multiple files
docs = chef.process_batch(["report.pdf", "slides.pptx", "data.xlsx"])

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

from chonkie import Pipeline

# Process a PDF locally and chunk it
doc = (Pipeline()
    .fetch_from("file", path="document.pdf")
    .process_with("liteparse")
    .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="./documents", ext=[".pdf", ".docx", ".pptx"])
    .process_with("liteparse")
    .chunk_with("recursive", chunk_size=1024)
    .refine_with("overlap", context_size=100)
    .store_in("qdrant", collection_name="local_documents")
    .run())

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

from chonkie import LiteParse

chef = LiteParse(target_pages="1-5,10,15-20", dpi=300)
doc = chef.process("large_report.pdf")
print(f"Extracted {len(doc.content)} characters from selected pages")

from chonkie import LiteParse, RecursiveChunker

# Step 1: Extract text from PDF
chef = LiteParse()
doc = chef.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)}")