Lexoid Python

from dotenv import load_dotenv

# Loads .env from the current dir (or a parent) into os.environ if the file
# exists; a no-op that returns False when no .env is found. Existing env vars
# are not overwritten unless override=True is passed.
load_dotenv()

from lexoid.api import parse
result = parse("document.pdf", parser_type="LLM_PARSE", model="gpt-4o")

{
    "raw": str,                  # full markdown
    "segments": [                # one dict per page / section; may be empty
        # bboxes is included only when return_bboxes=True
        {"metadata": {"page": int}, "content": str, "bboxes": [(text, [x0, top, x1, bottom]), ...]},
        ...
    ],
    "title": str,
    "url": str,                  # input URL or "" if input was a local file
    "parent_title": str,         # parent doc title when recursive; "" otherwise
    "recursive_docs": [...],     # empty unless depth > 1
    # --- optional keys below ---
    "token_usage": {"input": int, "output": int, "total": int, "llm_page_count": int},
        # zeros under STATIC_PARSE-only; ABSENT on the HTML/recursive-URL path
        # (URL input that isn't a file-typed URL and as_pdf is not set)
    "parsers_used": [str, ...],  # ABSENT on the HTML/recursive-URL path (same condition)
    "token_cost": {...},         # only when api_cost_mapping is supplied
    "pdf_path": str,             # only when as_pdf=True; file is removed unless save_dir is also set
}

from lexoid.api import parse

result = parse("document.pdf")
markdown = result["raw"]
for seg in result["segments"]:
    print(seg["metadata"]["page"], seg["content"][:80])

# Native-text PDFs — fastest, no API key
parse("document.pdf", parser_type="STATIC_PARSE", framework="pdfplumber")

# Scanned PDFs / images — local OCR, no API key
parse("scanned.pdf", parser_type="STATIC_PARSE", framework="paddleocr")

# LLM parsing
parse("document.pdf", parser_type="LLM_PARSE", model="gpt-4o")
parse("document.pdf", parser_type="LLM_PARSE", model="gemini-2.5-pro")
parse("document.pdf", parser_type="LLM_PARSE", model="claude-3-5-sonnet-20241022")

# Speed (default): static if no images, LLM otherwise
parse("doc.pdf", parser_type="AUTO", router_priority="speed")

# Accuracy: prefers LLM, except PDFs with hidden hyperlinks
parse("doc.pdf", parser_type="AUTO", router_priority="accuracy")

# Cost: tries PaddleOCR first; LLM fallback if extracted text is too short
parse("doc.pdf", parser_type="AUTO", router_priority="cost", character_threshold=100)

# ML-based LLM auto-selection (uses lexoid/core/llm_selector.py)
parse("doc.pdf", parser_type="AUTO", autoselect_llm=True)

# Ollama — Lexoid forces max_processes=1 for Ollama
parse("doc.pdf", parser_type="LLM_PARSE",
      api_provider="ollama", model="gemma4:latest", max_processes=1)

# SmolDocling / granite-docling
parse("doc.pdf", parser_type="LLM_PARSE",
      api_provider="local", model="ds4sd/SmolDocling-256M-preview")

# PaddleOCR-VL
parse("doc.pdf", parser_type="LLM_PARSE",
      api_provider="local", model="PaddlePaddle/PaddleOCR-VL")

from lexoid.api import parse_with_schema
from pydantic import BaseModel

class Invoice(BaseModel):
    invoice_number: str
    total: float

# Per-page extraction. `pages` is a list with one entry per page;
# each entry is whatever JSON the model returned for that page.
pages = parse_with_schema("invoice.pdf", schema=Invoice, model="gpt-4o-mini")
# e.g., pages[0] -> {"invoice_number": "...", "total": ...}
#       pages[0][0] -> first record if the model returned a list per page

# Single instance for the whole document — returns a one-element list.
[full] = parse_with_schema("contract.pdf", schema=Invoice,
                           model="gpt-4o", fill_single_schema=True)

# Dict schema with example data + alternate keys (improves match)
pages = parse_with_schema(
    "invoice.pdf",
    schema={"invoice_number": "string", "total": "number"},
    example_schema={"invoice_number": "INV-001", "total": 199.95},
    alternate_keys={"invoice_number": ["Invoice #", "Invoice No."]},
)

# Dataclass schemas also work
from dataclasses import dataclass
@dataclass
class Receipt:
    merchant: str
    amount: float

parse_with_schema("receipt.pdf", schema=Receipt)