vlmrun-cookbook

vlm-run活跃维护

VLM Run API 的示例与指南合集，用 Jupyter Notebook 演示如何调用视觉语言模型完成 OCR、文档解析和 ETL 等任务，方便快速上手多模态推理。

Examples and guides for using the VLM Run API

暂无版本313star +1 / 7 天21fork同步于 2026-11-11 05:57 UTC

视觉语言模型多模态推理 OCR 文档解析 ETL

对比 GitHub 官网 cookbook etl llm ocr vlm

怎么上手

由 README 提炼，执行前请确认

原文

pip install vlmrun

硬件要求按 README 说明

README 未说明，示例以 Colab 笔记本形式运行，算力由 VLM Run 云端 API 承担

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼

没人工点评？写下你的经验

VLM Run API 的示例笔记本合集，教你从图像、视频和文档中抽取结构化数据

VLM Run API 的示例与指南合集，用 Jupyter Notebook 演示如何调用视觉语言模型完成 OCR、文档解析和 ETL 等任务，方便快速上手多模态推理。

核心能力

提供可直接在 Colab 运行的完整示例笔记本
覆盖视觉定位、长视频转写、文档转 Markdown 等能力
演示自定义 Schema 生成与多 Schema 抽取
包含驾照、财报、电视新闻、医疗表单等落地案例
展示 Orion 系列模型的图像、视频与 3D 重建用法

容易踩的坑

需先注册 VLM Run 平台并配置 API Key 才能调用；示例依赖云端服务，离线无法运行；部分笔记本引用的模型或接口版本较新，需对照 docs.vlm.run 确认

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

用户点评

登录用户的真实使用记录，可按版本和硬件筛选

共 0 条

还没有人点评。第一个说出真实体验的人最有价值。

README 原文

未翻译

在 GitHub 打开

Welcome to VLM Run Cookbook, a comprehensive collection of examples and notebooks demonstrating the power of structured visual understanding using the VLM Run Platform. This repository hosts practical examples and tutorials for extracting structured data from images, videos, and documents using Vision Language Models (VLMs).

💡 Why Use This Cookbook?

📚 Practical Examples: A comprehensive collection of Colab notebooks demonstrating real-world applications of VLM Run.
🔋 Ready-to-Use: Each example comes with complete code and documentation, making it easy to adapt for your use case.
🎯 Domain-Specific: Examples cover various domains from financial documents to TV news analysis.

📖 Cookbook Notebooks

Our collection of Colab notebooks demonstrates various use cases and integrations:

Name	Type	Last Updated
API Quickstart		02-08-2025
Schema Showcase	feature	02-08-2025
Visual Grounding	feature	02-18-2025
Long-form Video Transcription	feature	03-13-2025
US Drivers License	application	02-08-2025
Parsing Financial Presentations	application	02-04-2025
TV News Analysis	application	02-15-2025
Fashion Product Catalog	application	02-20-2025
Fashion Images Hybrid Search	application	02-21-2025
Generate Custom Schema	feature	03-13-2025
Document Markdown Extraction	feature	06-02-2025
Video RAG	application	07-14-2025
Orion Image Understanding	showcase	12-01-2025
Orion 3D Reconstruction	showcase	12-04-2025
Orion Document Understanding	showcase	12-12-2025
Handwritten Medical Forms to JSON	application	04-10-2026
Healthcare Multi-Document Workflow	application	06-24-2026
Orion 2 Video Understanding	showcase	07-07-2026
Orion 2 Migration Tutorial	showcase	07-20-2026
Orion 2 Multi-Schema Extraction	showcase	07-22-2026

🔗 Quick Links

💬 Send us an email at [email protected] or join our Discord for help
📣 Follow us on Twitter and LinkedIn to keep up-to-date on our products
📚 Check out our Documentation for detailed guides and API reference