#601

Global Rank · of 601 Skills

byted-las-vlm-video AI Agent Skill

View Source: bytedance/agentkit-samples

Medium

Installation

npx skills add bytedance/agentkit-samples --skill byted-las-vlm-video

74

Installs

LAS 视频内容理解(las_vlm_video

本 Skill 用于调用 LAS las_vlm_video 算子进行视频理解(会先压缩视频到 50MB 以内,再调用豆包模型进行理解),并将同步 process 调用封装为可重复执行的脚本化工作流:

  • POST https://operator.las.cn-beijing.volces.com/api/v1/process 同步处理

你需要准备什么

  • LAS_API_KEY:优先从环境变量读取;也支持放在当前目录的 env.sh(内容形如 export LAS_API_KEY="..."
  • Operator Region(二选一):
    • 环境变量:LAS_REGION(推荐)/ REGION / region,取值 cn-beijing(默认)或 cn-shanghai
    • 或在命令里通过 --region cn-shanghai 指定
  • video_url:可下载的视频地址(http/httpstos://bucket/key
  • prompt:你希望模型对视频做什么理解/分析(例如“总结剧情”“列出关键事件”“回答我某个问题”)

参数与返回字段(详细版)

完整参数/返回字段速查见:

推荐使用方式

本 Skill 自带可执行脚本:scripts/skill.py

为方便在不同工程/不同 Agent 之间迁移,下面示例默认你位于该 Skill 目录(与 SKILL.md 同级),因此命令使用相对路径 scripts/skill.py

1) 执行视频理解

python3 scripts/skill.py process \
  --video-url "https://example.com/video.mp4" \
  --text "分析视频内容,输出要点列表,并回答:视频里出现了哪些主要物体?" \
  --model-name "doubao-seed-1.6-vision" \
  --region cn-beijing \
  --out result.json

2) 仅查看 endpoint 信息

python3 scripts/skill.py info --region cn-beijing

Region / Endpoint 的选择逻辑

脚本解析顺序:

  1. --region 命令行参数(cn-beijingcn-shanghai
  2. 环境变量 LAS_REGION / REGION / region
  3. 默认值 cn-beijing

Endpoint 由 region 自动映射到 operator.las.<region>.volces.com,不支持自定义 API base。

输出结果你会得到什么

当请求成功(task_status=COMPLETED)时,返回里通常会包含:

  • data.vlm_result:豆包对话的原生返回(可直接取 choices[0].message.content 作为主要文本输出)
  • data.compress_result:压缩前后的视频信息、压缩过程、耗时等元数据

脚本会把核心信息打印为易读摘要,并可选将原始 JSON 落盘。

常见问题

1) 提示“无法找到 LAS_API_KEY”怎么办?

  • 优先推荐设置环境变量:export LAS_API_KEY="..."
  • 或在运行目录准备 env.sh,内容形如:export LAS_API_KEY="..."
  • 注意脚本是从“当前工作目录”读取 env.sh:如果你在别的目录运行,可能读不到。

2) 视频链接有什么限制?

  • 视频需要公网或火山内网可访问(不可访问会导致失败)
  • 视频文件占用存储空间需小于 1 GiB
  • 算子暂不支持理解视频中的音频信息

Installs

Installs 74
Global Rank #601 of 601

Security Audit

ath Safe
socket Safe
Alerts: 0 Score: 90
snyk Medium
EU EU-Hosted Inference API

Power your AI Agents with the best open-source models.

Drop-in OpenAI-compatible API. No data leaves Europe.

Explore Inference API

GLM

GLM 5

$1.00 / $3.20

per M tokens

Kimi

Kimi K2.5

$0.60 / $2.80

per M tokens

MiniMax

MiniMax M2.5

$0.30 / $1.20

per M tokens

Qwen

Qwen3.5 122B

$0.40 / $3.00

per M tokens

How to use this skill

1

Install byted-las-vlm-video by running npx skills add bytedance/agentkit-samples --skill byted-las-vlm-video in your project directory. Run the install command above in your project directory. The skill file will be downloaded from GitHub and placed in your project.

2

No configuration needed. Your AI agent (Claude Code, Cursor, Windsurf, etc.) automatically detects installed skills and uses them as context when generating code.

3

The skill enhances your agent's understanding of byted-las-vlm-video, helping it follow established patterns, avoid common mistakes, and produce production-ready output.

What you get

Skills are plain-text instruction files — not executable code. They encode expert knowledge about frameworks, languages, or tools that your AI agent reads to improve its output. This means zero runtime overhead, no dependency conflicts, and full transparency: you can read and review every instruction before installing.

Compatibility

This skill works with any AI coding agent that supports the skills.sh format, including Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider, and other tools that read project-level context files. Skills are framework-agnostic at the transport level — the content inside determines which language or framework it applies to.

Data sourced from the skills.sh registry and GitHub. Install counts and security audits are updated regularly.

EU Made in Europe

Chat with 100+ AI Models in one App.

Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, GLM-5, Kimi K2.5 and many more.

Customer Support