# Install
pip install glmocr

# Set API key (once)
export ZHIPU_API_KEY=sk-xxx
# or add to .env file in working directory:
echo "ZHIPU_API_KEY=sk-xxx" >> .env

# One-liner
import glmocr
result = glmocr.parse("document.pdf")
print(result.markdown_result)
print(result.to_dict())

# CLI — pass API key directly (no env setup needed)
glmocr parse image.png --api-key sk-xxx

# Or load from a specific .env file
glmocr parse image.png --env-file /path/to/.env

# Or rely on env var / auto-discovered .env (set once, then omit)
glmocr parse image.png
glmocr parse ./scans/ --output ./output/ --stdout

Constructor kwargs  >  os.environ  >  .env file  >  config.yaml  >  built-in defaults

import glmocr

# Single file → PipelineResult
result = glmocr.parse("invoice.png")

# Multiple files → list[PipelineResult]
results = glmocr.parse(["page1.png", "page2.png", "report.pdf"])

from glmocr import GlmOcr

parser = GlmOcr(api_key="sk-xxx")   # mode auto-set to "maas"
parser = GlmOcr(mode="maas")        # reads ZHIPU_API_KEY from env

# Always use as context manager or call .close()
with GlmOcr(api_key="sk-xxx") as parser:
    result = parser.parse("document.png")
    print(result.markdown_result)

parser.close()   # if not using `with`

result.markdown_result    # str — full document as Markdown
result.json_result        # list[list[dict]] — structured regions per page
result.original_images    # list[str] — absolute paths of input images

[
  [
    {
      "index": 0,
      "label": "title",
      "content": "Annual Report 2024",
      "bbox_2d": [100, 50, 900, 120]
    },
    {
      "index": 1,
      "label": "table",
      "content": "| Q1 | Q2 |\n|---|---|\n| 120 | 145 |",
      "bbox_2d": [100, 140, 900, 400]
    }
  ]
]

# Dict (JSON-serializable, for passing to other tools)
d = result.to_dict()
# Keys: json_result, markdown_result, original_images, usage (MaaS), data_info (MaaS)

# JSON string
json_str = result.to_json()                 # pretty-printed, ensure_ascii=False
json_str = result.to_json(indent=None)      # compact single line

# Save to disk: writes <stem>/<stem>.json + <stem>/<stem>.md + layout_vis/
result.save(output_dir="./output")
result.save(output_dir="./output", save_layout_visualization=False)

result = parser.parse("image.png")
d = result.to_dict()
if "error" in d:
    # Handle failure
    print("OCR failed:", d["error"])
else:
    print(d["markdown_result"])

# Parse a single file → saves to ./output/<stem>/
# MaaS mode is the default; ZHIPU_API_KEY must be set (or use --api-key)
glmocr parse image.png

# Pass API key directly without any env setup
glmocr parse image.png --api-key sk-xxx

# Parse a directory → saves each file to ./output/<stem>/
glmocr parse ./scans/

# Use self-hosted vLLM/SGLang instead of cloud
glmocr parse image.png --mode selfhosted

# Specify output directory
glmocr parse image.png --output ./results/

# Print Markdown + JSON to stdout (and still save to disk)
glmocr parse image.png --stdout

# Print to stdout ONLY — do not write any files
glmocr parse image.png --stdout --no-save

# JSON only (no Markdown output)
glmocr parse image.png --stdout --json-only

# Pipe JSON into jq for structured extraction
glmocr parse image.png --stdout --json-only --no-save | jq '.[0] | map(select(.label=="table"))'

# Skip layout visualization images (faster, smaller output)
glmocr parse image.png --no-layout-vis

# Parse and save only JSON + Markdown, skip layout vis
glmocr parse image.png --no-layout-vis --output ./results/

# All images in a folder
glmocr parse ./invoice_scans/ --output ./parsed/ --no-layout-vis

# With progress visible in logs
glmocr parse ./docs/ --output ./parsed/ --log-level INFO

glmocr parse image.png --log-level DEBUG

receive document path / URL
       │
       ▼
glmocr.parse(path)            ← single call, handles PDF/image
       │
       ▼
result.to_dict()              ← safe to pass as tool output
       │
       ├── markdown_result    → hand to LLM for reading / summarization
       └── json_result        → structured extraction (tables, formulas, regions by label)

result = glmocr.parse("report.png")
regions = result.json_result[0]  # first page

tables = [r for r in regions if r["label"] == "table"]
formulas = [r for r in regions if r["label"] == "formula"]
body_text = [r for r in regions if r["label"] == "text"]

with GlmOcr(api_key="sk-xxx") as parser:
    result = parser.parse("document.pdf")   # all pages in one PipelineResult
    for page_idx, page_regions in enumerate(result.json_result):
        print(f"Page {page_idx + 1}: {len(page_regions)} regions")
        for region in page_regions:
            print(f"  [{region['label']}] {region['content'][:60]}")

from glmocr.config import GlmOcrConfig

cfg = GlmOcrConfig.from_env(
    api_key="sk-xxx",
    mode="maas",
    timeout=600,
    log_level="DEBUG",
)

output_dir/
  <image_stem>/
    <image_stem>.json         ← structured regions
    <image_stem>.md           ← full Markdown (with cropped figure images)
    imgs/                     ← cropped figures referenced in Markdown
    layout_vis/               ← layout detection overlay images (if enabled)
      <image_stem>.jpg