PDF ──> pdfmux router ──> best extractor per page ──> audit ──> re-extract failures ──> Markdown / JSON / chunks
            |
            ├─ PyMuPDF         (digital text, 0.01s/page)
            ├─ OpenDataLoader  (complex layouts, 0.05s/page)
            ├─ RapidOCR        (scanned pages, CPU-only)
            ├─ Docling         (tables, 97.9% TEDS)
            ├─ Surya           (heavy OCR fallback)
            ├─ Marker          (academic papers, neural)
            ├─ Mistral OCR     ($0.002/page, 96.6% tables)
            └─ YOUR LLM        (Gemini / Gemma 3 / Claude / GPT-4o / Ollama / Mistral — BYOK via YAML)

pip install pdfmux

pip install "pdfmux[ocr]"             # ⭐ recommended — RapidOCR for scanned pages (~200MB, CPU)

pip install "pdfmux[tables]"          # Docling — table-heavy docs (~500MB)
pip install "pdfmux[opendataloader]"  # OpenDataLoader — complex layouts (Java 11+)
pip install "pdfmux[marker]"          # Marker — neural extraction for academic papers
pip install "pdfmux[llm]"             # Gemini fallback (default LLM)
pip install "pdfmux[llm-claude]"      # Claude (Sonnet / Opus)
pip install "pdfmux[llm-openai]"      # GPT-4o family
pip install "pdfmux[llm-ollama]"      # Ollama (any local model)
pip install "pdfmux[llm-mistral]"     # Mistral OCR API ($0.002/page)
pip install "pdfmux[llm-all]"         # all LLM providers (incl. Gemma via Gemini key)
pip install "pdfmux[watch]"           # `pdfmux watch <dir>` auto-convert on change
pip install "pdfmux[all]"             # everything

# zero config — just works
pdfmux convert invoice.pdf
# invoice.pdf -> invoice.md (2 pages, 95% confidence, via pymupdf4llm)

# RAG-ready chunks with token limits
pdfmux convert report.pdf --chunk --max-tokens 500

# cost-aware extraction with budget cap
pdfmux convert report.pdf --mode economy --budget 0.50

# schema-guided structured extraction (5 built-in presets)
pdfmux convert invoice.pdf --schema invoice

# BYOK any LLM for hardest pages
pdfmux convert scan.pdf --llm-provider claude

# use a built-in or saved profile (invoices, receipts, papers, contracts, bulk-rag)
pdfmux convert invoice.pdf --profile invoices

# predict cost before running anything
pdfmux estimate big-report.pdf --llm-provider gemini

# stream pages as NDJSON as they finish (great for long documents)
pdfmux stream report.pdf --quality high

# auto-convert any new PDFs that land in a folder
pdfmux watch ./inbox/ -o ./output/

# diff two extractions side-by-side
pdfmux diff old.pdf new.pdf

# batch a directory — writes manifest.json with per-doc confidence
pdfmux convert ./docs/ -o ./output/

# CI mode: fail the run if any document is below 0.20 confidence
pdfmux convert ./docs/ -o ./output/ --strict --min-confidence 0.20

# pre-flight a directory: which extras do you actually need for THIS batch?
pdfmux doctor --check ./docs/

# results are cached by file hash — re-runs are instant; bypass with --no-cache
pdfmux convert report.pdf --no-cache
pdfmux convert report.pdf --clear-cache

import pdfmux
from pathlib import Path

# Batch extract — yields (path, result) tuples as each PDF completes.
pdfs = list(Path("./inbox").glob("*.pdf"))
for path, result in pdfmux.batch_extract(pdfs, quality="standard"):
    if isinstance(result, Exception):
        print(f"FAILED {path.name}: {result}")
        continue
    if result.confidence < 0.50:
        print(f"REVIEW {path.name} ({result.confidence:.2f})")
    else:
        print(f"OK     {path.name} ({result.confidence:.2f})")

# Single-file helpers.
text   = pdfmux.extract_text("report.pdf")             # markdown string
data   = pdfmux.extract_json("report.pdf")             # locked schema dict
chunks = pdfmux.chunk("report.pdf", max_tokens=500)    # RAG-ready chunks

# Certify pdfmux's own extraction of a document
pdfmux verify --source report.pdf --engine pdfmux

# Certify ANOTHER engine's output (JSON / Markdown / text)
pdfmux verify --source report.pdf --extracted reducto.json --engine-name reducto

# Batch a whole directory — the "M pages silently dropped across N docs" report
pdfmux verify --source ./pdfs/ --extracted ./engine-outputs/ -o certification.json

# CI gate: exit non-zero unless the overall verdict is PASS
pdfmux verify --source report.pdf --extracted out.json --strict

pdfmux verify — report.pdf · engine: reducto
  FAIL   confidence 71% · coverage 68%
  reducto: FAIL; 3 page(s) SILENTLY DROPPED (pages 7, 12, 31); overall
  confidence 71%, coverage 68% across 40 page(s).

❌ 3 page(s) SILENTLY DROPPED: 7, 12, 31

from pdfmux import verify_extraction, verify_batch

# Single document → a CertificationManifest
manifest = verify_extraction("report.pdf", "reducto.json", engine="reducto")
print(manifest.verdict)        # "PASS" | "REVIEW" | "FAIL"
print(manifest.silent_drops)   # e.g. (7, 12, 31)  — 1-indexed page numbers
print(manifest.coverage)       # 0.0–1.0

# Many documents → a BatchCertification ("M pages dropped across N docs")
batch = verify_batch([("a.pdf", "a.json"), ("b.pdf", "b.json")], engine="llamaparse")
print(batch.total_silent_drops, "pages dropped across", batch.doc_count, "docs")

pdfmux verify-manifest manifest.json      # free, MIT, offline — no account

                           ┌─────────────────────────────┐
                           │     Segment Detector         │
                           │  text / tables / images /    │
                           │  formulas / headers per page │
                           └─────────────┬───────────────┘
                                         │
                    ┌────────────────────────────────────────┐
                    │            Router Engine                │
                    │                                        │
                    │   economy ── balanced ── premium        │
                    │   (minimize $)  (default)  (max quality)│
                    │   budget caps: --budget 0.50            │
                    └────────────────────┬───────────────────┘
                                         │
          ┌──────────┬──────────┬────────┴────────┬──────────┐
          │          │          │                  │          │
     PyMuPDF   OpenData    RapidOCR           Docling     LLM
     digital   Loader      scanned            tables    (BYOK)
     0.01s/pg  complex     CPU-only           97.9%    any provider
               layouts                        TEDS
          │          │          │                  │          │
          └──────────┴──────────┴────────┬────────┴──────────┘
                                         │
                    ┌────────────────────────────────────────┐
                    │           Quality Auditor               │
                    │                                        │
                    │   4-signal dynamic confidence scoring   │
                    │   per-page: good / bad / empty          │
                    │   if bad -> re-extract with next backend│
                    └────────────────────┬───────────────────┘
                                         │
                    ┌────────────────────────────────────────┐
                    │           Output Pipeline               │
                    │                                        │
                    │   heading injection (font-size analysis)│
                    │   table extraction + normalization      │
                    │   text cleanup + merge                  │
                    │   confidence score (honest, not inflated)│
                    └────────────────────────────────────────┘

pdfmux convert <file-or-dir> [options]

Options:
  -o, --output PATH          Output file or directory
  -f, --format FORMAT        markdown | json | csv | llm (default: markdown)
  -q, --quality QUALITY      fast | standard | high (default: standard)
  -s, --schema SCHEMA        JSON schema file or preset (invoice, receipt, contract, resume, paper)
  --chunk                    Output RAG-ready chunks
  --max-tokens N             Max tokens per chunk (default: 500)
  --mode MODE                economy | balanced | premium (default: balanced)
  --budget AMOUNT            Max spend per document in USD
  --llm-provider PROVIDER    LLM backend: gemini | claude | openai | ollama
  --confidence               Include confidence score in output
  --stdout                   Print to stdout instead of file

pdfmux serve              # stdio mode (Claude Desktop, Cursor)
pdfmux serve --http 8080  # HTTP mode

pdfmux doctor
# ┌──────────────────┬─────────────┬─────────┬──────────────────────────────────┐
# │ Extractor        │ Status      │ Version │ Install                          │
# ├──────────────────┼─────────────┼─────────┼──────────────────────────────────┤
# │ PyMuPDF          │ installed   │ 1.25.3  │                                  │
# │ OpenDataLoader   │ installed   │ 0.3.1   │                                  │
# │ RapidOCR         │ installed   │ 3.0.6   │                                  │
# │ Docling          │ missing     │ --      │ pip install pdfmux[tables]       │
# │ Surya            │ missing     │ --      │ pip install pdfmux[ocr-heavy]    │
# │ LLM (Gemini)     │ configured  │ --      │ GEMINI_API_KEY set               │
# └──────────────────┴─────────────┴─────────┴──────────────────────────────────┘

pdfmux benchmark report.pdf
# ┌──────────────────┬────────┬────────────┬─────────────┬──────────────────────┐
# │ Extractor        │   Time │ Confidence │      Output │ Status               │
# ├──────────────────┼────────┼────────────┼─────────────┼──────────────────────┤
# │ PyMuPDF          │  0.02s │        95% │ 3,241 chars │ all pages good       │
# │ Multi-pass       │  0.03s │        95% │ 3,241 chars │ all pages good       │
# │ RapidOCR         │  4.20s │        88% │ 2,891 chars │ ok                   │
# │ OpenDataLoader   │  0.12s │        97% │ 3,310 chars │ best                 │
# └──────────────────┴────────┴────────────┴─────────────┴──────────────────────┘

pdfmux estimate report.pdf --quality high --llm-provider gemini
# Pages       : 47
# Extractors  : pymupdf4llm + gemini-2.5-flash on 9 pages
# Estimated   : $0.0234
# Cache hit?  : no  (first run for this file)

pdfmux stream long.pdf --quality high
# {"event":"classified","page_count":312,"plan":"pymupdf+gemini-fallback"}
# {"event":"page","page_num":0,"confidence":0.97,"chars":1842}
# {"event":"page","page_num":1,"confidence":0.92,"chars":1611,"ocr":true}
# ...
# {"event":"complete","confidence":0.94,"cost_usd":0.0712}

pdfmux watch ./inbox/ -o ./output/ --profile bulk-rag

pdfmux diff a.pdf b.pdf --quality standard

pdfmux profiles list
# invoices    quality=standard, schema=invoice, format=json
# receipts    quality=fast,     schema=receipt, format=json
# papers      quality=high,     chunk=true, max_tokens=500
# contracts   quality=high,     schema=contract
# bulk-rag    quality=standard, format=llm, chunk=true

pdfmux profiles show invoices
pdfmux profiles save my-default --quality high --format llm --chunk
pdfmux profiles delete my-default

# use a profile when converting
pdfmux convert file.pdf --profile invoices

import pdfmux

text = pdfmux.extract_text("report.pdf")                    # -> str (markdown)
text = pdfmux.extract_text("report.pdf", quality="fast")    # PyMuPDF only, instant
text = pdfmux.extract_text("report.pdf", quality="high")    # LLM-assisted

data = pdfmux.extract_json("report.pdf")
# data["page_count"]   -> 12
# data["confidence"]   -> 0.91
# data["ocr_pages"]    -> [2, 5, 8]
# data["pages"][0]["key_values"]  -> [{"key": "Date", "value": "2026-02-28"}]
# data["pages"][0]["tables"]      -> [{"headers": [...], "rows": [...]}]

chunks = pdfmux.chunk("report.pdf", max_tokens=500)
for c in chunks:
    print(f"{c['title']}: {c['tokens']} tokens (pages {c['page_start']}-{c['page_end']})")

data = pdfmux.extract_json("invoice.pdf", schema="invoice")
# Uses built-in invoice preset: extracts date, vendor, line items, totals
# Also accepts a path to a custom JSON Schema file

from pdfmux.extractors import get_extractor

ext = get_extractor("fast")
for page in ext.extract("large-500-pages.pdf"):  # Iterator[PageResult]
    process(page.text)  # constant memory, even on 500-page PDFs

from pdfmux import (
    # Enums
    Quality,              # FAST, STANDARD, HIGH
    OutputFormat,         # MARKDOWN, JSON, CSV, LLM
    PageQuality,          # GOOD, BAD, EMPTY

    # Data objects (frozen dataclasses)
    PageResult,           # page: text, page_num, confidence, quality, extractor
    DocumentResult,       # document: pages, source, confidence, extractor_used
    Chunk,                # chunk: title, text, page_start, page_end, tokens

    # Errors
    PdfmuxError,          # base -- catch this for all pdfmux errors
    FileError,            # file not found, unreadable, not a PDF
    ExtractionError,      # extraction failed
    ExtractorNotAvailable,# requested backend not installed
    FormatError,          # invalid output format
    AuditError,           # audit could not complete
)

pip install langchain-pdfmux

from langchain_pdfmux import PDFMuxLoader

loader = PDFMuxLoader("report.pdf", quality="standard")
docs = loader.load()  # -> list[Document] with confidence metadata

pip install llama-index-readers-pdfmux

from llama_index.readers.pdfmux import PDFMuxReader

reader = PDFMuxReader(quality="standard")
docs = reader.load_data("report.pdf")  # -> list[Document]

{
  "mcpServers": {
    "pdfmux": {
      "command": "npx",
      "args": ["-y", "pdfmux-mcp"]
    }
  }
}

claude mcp add pdfmux -- npx -y pdfmux-mcp

# ~/.pdfmux/llm.yaml
provider: claude          # gemini | claude | openai | ollama | any OpenAI-compatible
model: claude-sonnet-4-20250514
api_key: ${ANTHROPIC_API_KEY}
base_url: https://api.anthropic.com  # optional, for custom endpoints
max_cost_per_page: 0.02   # budget cap

# Default install — already includes python-bidi for RTL reordering
pip install pdfmux

# Recommended for Arabic-heavy docs — adds Gemma vision OCR
# (Gemma speaks the OpenAI protocol, so it needs the openai SDK)
pip install "pdfmux[llm-openai]"

# One credential covers Gemma + Gemini (same Google endpoint)
export GEMINI_API_KEY=...

from pdfmux.arabic import (
    is_arabic_text,
    is_rtl_dominant,
    fix_bidi_order,
    normalize_arabic,
)

text = "مرحبا بالعالم"
assert is_arabic_text(text)
assert is_rtl_dominant(text)

# Fix glyph order from PyMuPDF / OCR engines
visual = fix_bidi_order(text)

# Canonicalize for indexing — strip Tatweel, unify Alef variants, drop diacritics
indexable = normalize_arabic("أَحْمَدْ")  # → "احمد"

pdfmux convert big-report.pdf            # first run: 14.2s
pdfmux convert big-report.pdf            # cache hit: 0.05s
pdfmux convert big-report.pdf --no-cache # bypass cache (still writes back)
pdfmux convert big-report.pdf --clear-cache  # purge and re-run

Page 4: 32% confidence. 0 chars extracted from image-heavy page.
  -> Install pdfmux[ocr] for RapidOCR support on 6 image-heavy pages.

git clone https://github.com/NameetP/pdfmux.git
cd pdfmux
python3.12 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

pytest              # 659 tests
ruff check src/ tests/
ruff format src/ tests/