glmocr-sdk

Q: How do I install glmocr-sdk?

Run npx skills add https://modelscope.cn --skill glmocr-sdk in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/glmocr-sdk/ (personal) or .claude/skills/glmocr-sdk/ (project).

by modelscope.cnMedia & Creative

Trigger when: (1) User wants to extract text, tables, formulas, or structured data from images/PDFs/scanned documents, (2) User mentions "OCR", "文字识别", "文档解析", (3) User has a document (screenshot, scanned page, invoice, paper, whiteboard photo) and needs its content in structured form, (4) User asks to parse, digitize, or extract content from a visual document. Invokes the GLM-OCR SDK (pip install glmocr) to parse documents via Zhipu's cloud API. No GPU required. Returns structured JSON (regions with labels + bounding boxes) and Markdown. Agent can operate entirely via CLI — no YAML files needed. NOT for: real-time camera feeds, audio transcription, or non-document images (photos, illustrations).

Installs: 334
Last 24h: —
Trending rank: —
Security: Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://modelscope.cn --skill glmocr-sdk

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads glmocr-sdk automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

OpenClaw Skill: glmocr

Parses documents (images, PDFs, scans) via the GLM-OCR SDK.

📌 On-demand: This skill requires only ZHIPU_API_KEY in the environment. No YAML config files or GPU needed.

⚡ Quick Start

# 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

Configuration Priority

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

Agents override everything via constructor kwargs or env vars — no YAML editing needed.

Key Environment Variables

Variable	Description	Example
`ZHIPU_API_KEY`	API key (required for MaaS)	`sk-abc123`
`GLMOCR_MODEL`	Model name	`glm-ocr`
`GLMOCR_TIMEOUT`	Request timeout (seconds)	`600`
`GLMOCR_ENABLE_LAYOUT`	Layout detection on/off	`true`
`GLMOCR_LOG_LEVEL`	`DEBUG` / `INFO` / `WARNING` / `ERROR`	`INFO`

Python API

Convenience function (single call)

import glmocr

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

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

Class-based (multiple calls / resource reuse)

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`

Constructor Parameters

Parameter	Type	Description
`api_key`	`str`	API key. Providing this auto-enables MaaS mode.
`api_url`	`str`	Override MaaS endpoint URL
`model`	`str`	Model name override
`timeout`	`int`	Request timeout in seconds (default: 600)
`enable_layout`	`bool`	Enable layout detection
`log_level`	`str`	Logging level

Working with `PipelineResult`

Fields

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

`json_result` structure

List of pages → list of regions per page:

[
  [
    {
      "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]
    }
  ]
]

Bounding boxes (bbox_2d): [x1, y1, x2, y2] normalised to 0–1000 scale.

Region labels: title, text, table, figure, formula, header, footer, page_number, reference, seal

Serialization

# 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)

Error Handling

The SDK does not raise on MaaS errors — check to_dict() for an "error" key:

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"])

CLI Reference

Agent-preferred interface: use the CLI for most operations. Set ZHIPU_API_KEY in env once, then invoke as needed.

Supported input formats: .jpg, .jpeg, .png, .bmp, .gif, .webp, .pdf

Basic usage

# 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/

Read results in the terminal (agent-friendly)

# 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"))'

Save control

# 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/

Batch processing

# 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

Debugging

glmocr parse image.png --log-level DEBUG

Full flag reference

Flag	Default	Description
`--api-key / -k`	env var	API key for MaaS mode (overrides `ZHIPU_API_KEY`)
`--mode`	`maas`	`maas` (cloud, default) or `selfhosted` (local GPU)
`--env-file`	auto	Path to `.env` file (default: auto-discover from cwd)
`--output / -o`	`./output`	Output directory
`--stdout`	off	Print JSON + Markdown to stdout
`--no-save`	off	Skip writing files (use with `--stdout`)
`--json-only`	off	stdout JSON only, no Markdown
`--no-layout-vis`	off	Skip layout visualization images
`--config / -c`	none	Path to YAML config override
`--log-level`	`INFO`	`DEBUG` / `INFO` / `WARNING` / `ERROR`

Typical Agent Workflow

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)

Filter 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"]

Multi-page PDF → iterate pages

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]}")

Programmatic config (no env vars)

from glmocr.config import GlmOcrConfig

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

Output Directory Layout

After result.save(output_dir):

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

Common Pitfalls

ZHIPU_API_KEY not set: SDK defaults to MaaS mode. Without a key, parse() will fail with a clear error message and quick-fix instructions. Set via export ZHIPU_API_KEY=sk-xxx, add to a .env file, or pass --api-key sk-xxx to the CLI.
Large PDFs: Default timeout is 600s. For very long documents increase with timeout=1200.
result.json_result is a string: Happens when the model returns malformed JSON. The SDK preserves the raw string — parse or log it manually.

FAQ

What does the glmocr-sdk skill do?

How do I install glmocr-sdk?

Run npx skills add https://modelscope.cn --skill glmocr-sdk in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/glmocr-sdk/ (personal) or .claude/skills/glmocr-sdk/ (project).

Which AI agents can use glmocr-sdk?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is glmocr-sdk safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains glmocr-sdk?

It is published by modelscope.cn in modelscope.cn. It has 334 recorded installs.

More from modelscope.cn

View all →

skill-creator

modelscope.cn

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

AI & Agents2.5K installs

frontend-design

modelscope.cn

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Frontend & Design2K installs

pptx-generator

modelscope.cn

Generate, edit, and read PowerPoint presentations. Create from scratch with PptxGenJS (cover, TOC, content, section divider, summary slides), edit existing PPTX via XML workflows, or extract text with markitdown. Triggers: PPT, PPTX, PowerPoint, presentation, slide, deck, slides.

Docs & Writing1.6K installs

minimax-docx

modelscope.cn

Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say "write a report", "draft a proposal", "make a contract", "fill in this form", "reformat to match this template", or any task whose final output is a .docx file. Even if the user doesn't mention "docx" explicitly, if the task implies a printable/formal document, use this skill.

Docs & Writing1.6K installs

minimax-pdf

modelscope.cn

Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the form", "fill out this PDF", "complete the form fields", "write values into PDF", "what fields does this PDF have". REFORMAT (apply design to an existing doc): "reformat this document", "apply our style", "convert this Markdown/text to PDF", "make this doc look good", "re-style this PDF". This skill uses a token-based design system: color, typography, and spacing are derived from the document type and flow through every page. The output is print-ready. Prefer this skill when appearance matters, not just when any PDF output is needed.

Docs & Writing1.5K installs

minimax-xlsx

modelscope.cn

Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Use when the user asks to create, build, modify, analyze, read, validate, or format any Excel spreadsheet, financial model, pivot table, or tabular data file. Covers: creating new xlsx from scratch, reading and analyzing existing files, editing existing xlsx with zero format loss, formula recalculation and validation, and applying professional financial formatting standards. Triggers on 'spreadsheet', 'Excel', '.xlsx', '.csv', 'pivot table', 'financial model', 'formula', or any request to produce tabular data in Excel format.

Data & Databases1.5K installs

Popular media & creative skills

View category →

hyperframes

heygen-com/hyperframes

Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.

Media & Creative1.2M installs

media-use

heygen-com/hyperframes

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.

Media & Creative1.1M installs

hyperframes-registry

heygen-com/hyperframes

About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.

Media & Creative1M installs

hyperframes-creative

heygen-com/hyperframes

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.

Media & Creative916.5K installs

ai-video-generation

101-skills/superpowers

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

Media & Creative881.5K installs

ai-image-generation

101-skills/superpowers

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

Media & Creative880.3K installs

glmocr-sdk

Install

Install

Describe the task

Review the result

SKILL.md

OpenClaw Skill: glmocr

⚡ Quick Start

Configuration Priority

Key Environment Variables

Python API

Convenience function (single call)

Class-based (multiple calls / resource reuse)

Constructor Parameters

Working with PipelineResult

Fields

json_result structure

Serialization

Error Handling

CLI Reference

Basic usage

Read results in the terminal (agent-friendly)

Save control

Batch processing

Debugging

Full flag reference

Typical Agent Workflow

Filter by label

Multi-page PDF → iterate pages

Programmatic config (no env vars)

Output Directory Layout

Common Pitfalls

FAQ

More from modelscope.cn

Popular media & creative skills

Working with `PipelineResult`

`json_result` structure