Ocr And Documents

PDF & Document Extraction

For DOCX: use python-docx when available (parses actual document structure, far better than OCR). If dependencies are unavailable or you only need paragraphs/tables, a dependency-free fallback is to unzip the .docx and parse word/document.xml plus headers/footers/comments with xml.etree.ElementTree; preserve paragraph/table order roughly and save the extracted .txt beside the source for traceability. For PPTX: see the powerpoint skill (uses python-pptx with full slide/notes support). This skill covers PDFs and scanned documents.

Step 1: Remote URL Available?

If the document has a URL, always try web_extract first:

web_extract(urls=["https://arxiv.org/pdf/2402.03300"])
web_extract(urls=["https://example.com/report.pdf"])

This handles PDF-to-markdown conversion via Firecrawl with no local dependencies.

Only use local extraction when: the file is local, web_extract fails, or you need batch processing.

Step 2: Choose Local Extractor

Decision: Use pymupdf unless you need OCR, equations, forms, or complex layout analysis.

If the user needs marker capabilities but the system lacks ~5GB free disk:

"This document needs OCR/advanced extraction (marker-pdf), which requires ~5GB for PyTorch and models. Your system has [X]GB free. Options: free up space, provide a URL so I can use web_extract, or I can try pymupdf which works for text-based PDFs but not scanned documents or equations."

pymupdf (lightweight)

pip install pymupdf pymupdf4llm

Via helper script:

python scripts/extract_pymupdf.py document.pdf              # Plain text
python scripts/extract_pymupdf.py document.pdf --markdown    # Markdown
python scripts/extract_pymupdf.py document.pdf --tables      # Tables
python scripts/extract_pymupdf.py document.pdf --images out/ # Extract images
python scripts/extract_pymupdf.py document.pdf --metadata    # Title, author, pages
python scripts/extract_pymupdf.py document.pdf --pages 0-4   # Specific pages

Inline:

python3 -c "
import pymupdf
doc = pymupdf.open('document.pdf')
for page in doc:
    print(page.get_text())
"

marker-pdf (high-quality OCR)

# Check disk space first
python scripts/extract_marker.py --check

pip install marker-pdf

Via helper script:

python scripts/extract_marker.py document.pdf                # Markdown
python scripts/extract_marker.py document.pdf --json         # JSON with metadata
python scripts/extract_marker.py document.pdf --output_dir out/  # Save images
python scripts/extract_marker.py scanned.pdf                 # Scanned PDF (OCR)
python scripts/extract_marker.py document.pdf --use_llm      # LLM-boosted accuracy

CLI (installed with marker-pdf):

marker_single document.pdf --output_dir ./output
marker /path/to/folder --workers 4    # Batch

Arxiv Papers

# Abstract only (fast)
web_extract(urls=["https://arxiv.org/abs/2402.03300"])

# Full paper
web_extract(urls=["https://arxiv.org/pdf/2402.03300"])

# Search
web_search(query="arxiv GRPO reinforcement learning 2026")

Split, Merge & Search

pymupdf handles these natively — use execute_code or inline Python:

# Split: extract pages 1-5 to a new PDF
import pymupdf
doc = pymupdf.open("report.pdf")
new = pymupdf.open()
for i in range(5):
    new.insert_pdf(doc, from_page=i, to_page=i)
new.save("pages_1-5.pdf")

# Merge multiple PDFs
import pymupdf
result = pymupdf.open()
for path in ["a.pdf", "b.pdf", "c.pdf"]:
    result.insert_pdf(pymupdf.open(path))
result.save("merged.pdf")

# Search for text across all pages
import pymupdf
doc = pymupdf.open("report.pdf")
for i, page in enumerate(doc):
    results = page.search_for("revenue")
    if results:
        print(f"Page {i+1}: {len(results)} match(es)")
        print(page.get_text("text"))

No extra dependencies needed — pymupdf covers split, merge, search, and text extraction in one package.

RAG / Knowledge-Base PDF Pipelines

When investigating a project-specific "PDF to index/database" flow, do not stop at the extractor. Trace the whole path:

1. Upload/API entrypoint: multipart endpoint, accepted extensions, where files are saved.
2. Parser service: text extraction, page rendering, OCR/layout/table models, fallbacks.
3. Config: parser roots, model weight paths, feature flags, device, vector/DB toggles.
4. Storage artifacts: chunks JSON, metadata JSON, extracted images/tables/crops.
5. Indexer: PostgreSQL/SQLite tables, vector DB upsert, local fallback store.
6. Retrieval layer: source priority, vector-to-JSON fallback, asset links in results.

Be precise about model roles. Layout detectors such as DocLayout-YOLO and table detectors such as Table Transformer can support PDF understanding by finding/cropping figures and tables, but they are not full OCR engines unless text recognition from page pixels is explicitly implemented. A text-based PDF pipeline may still rely on PyMuPDF/PyPDF2/pdfplumber for actual text chunks.

Reference: references/ai-travel-pdf-indexing.md documents the AI_TRAVEL/agri-model-platform-nwafu PDF upload → enhanced parsing → JSON/Postgres/Chroma indexing flow and the DocLayout-YOLO/Table Transformer distinction.

Notes

• web_extract is always first choice for URLs
• pymupdf is the safe default — instant, no models, works everywhere
• marker-pdf is for OCR, scanned docs, equations, complex layouts — install only when needed
• Both helper scripts accept --help for full usage
• marker-pdf downloads 2.5GB of models to `/.cache/huggingface/` on first use
• For Word docs: pip install python-docx (better than OCR — parses actual structure)
• For PowerPoint: see the powerpoint skill (uses python-pptx)