Eino Component

This is your reference guide when working with eino-ext components in Go. It covers the entire component ecosystem: ChatModel and AgenticModel for LLM inference (classic message path vs. block-based agentic path), embeddings, vector stores like Milvus and Redis, document loaders, and tools including MCP support. The guide distinguishes clearly between the two inference paths, which matters because AgenticModel handles reasoning blocks and passes tools at call time rather than via WithTools. Useful when you're choosing between providers (OpenAI, Claude, Gemini, Ark, Ollama, DeepSeek) or setting up RAG pipelines. The interface reference and code examples are practical, showing actual Generate and Stream calls rather than just listing options.

skills.sh installs: 348
GitHub stars: 835
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cloudwego/eino-ext --skill eino-component --agent claude-code

Installs into .claude/skills of the current project.

Files

Eino Component Guide

Component Selection Guide

ChatModel -- LLM inference (classic Message path)

Provider	Package	Notes
OpenAI	`model/openai`	Also supports Azure via `ByAzure: true`
Claude	`model/claude`	Also supports AWS Bedrock via `ByBedrock: true`
Gemini	`model/gemini`	Requires `genai.Client`
Ark (Volcengine)	`model/ark`	Doubao models
Ollama	`model/ollama`	Local models
DeepSeek	`model/deepseek`	Reasoning support
Qwen	`model/qwen`	Alibaba DashScope API
Qianfan	`model/qianfan`	Baidu ERNIE models
OpenRouter	`model/openrouter`	Multi-provider routing

AgenticModel -- LLM inference (AgenticMessage path)

AgenticModel operates on *schema.AgenticMessage with block-based content (reasoning, text, images, audio, video, tool calls/results). Tools are always passed at call time via model.WithTools option (no WithTools method).

SKILL.md on GitHub