Articles tagged "image analysis"

TencentCloud VITA：在 Agent 里调用腾讯云图像与视频理解

2026-10-20 Big Model Skills TencentCloud VITA video understanding image analysis SkillHub Agent Skill

TencentCloud VITA（@tencent-adm/tencentcloud-vita，v1.0.9）是腾讯云内容识别团队在 SkillHub 发布的企业 Skill，封装腾讯云 VITA 的图片与视频理解能力。支持单图、多图按时序分析与视频 URL 理解，可持久化 vita prompt，通过 scripts/main.py 调用并要求 Agent 禁止在服务失败时编造结果。安装需 SkillHub CLI 或 Zip 包，并配置 TENCENTCLOUD_VITA_API_KEY。本地视频需先获得公网 URL。

dsh-codex-media: Local OpenAI Codex-Powered Image and Document Analysis Tool

2026-09-15 DeepSeek Harness plugin DeepSeek Harness dsh-codex-media image analysis Document Processing Plugin

`dsh-codex-media` is a local media analysis tool designed for DeepSeek Harness (DSH), addressing the limitation of pure-text models in directly processing images and documents. The plugin provides image description, document analysis, and image generation capabilities, runs using the local OpenAI Codex CLI, and requires no third-party runtime libraries. It must be paired with the `dsh-drop-to-path` plugin before installation, supports multiple transport methods (CLI, Hermes, and API), and enforces strict permission and security validation mechanisms.