原文
| ||||||||||
| ||||||||||
 | ||||||||||
（评论）
(comments)
原始链接: https://news.ycombinator.com/item?id=43417511
Zacharyhuang 发布了一篇教程，解释说 LLM 智能体（例如 OpenAI 智能体、Pydantic AI、AutoGPT 和 PerplexityAI）本质上是具有循环和分支的图。他提供了来自 OpenAI 智能体、Pydantic AI 和 Langchain 的代码示例链接，以说明这种底层结构。这篇教程旨在通过揭示其简单的基于图的架构来消除围绕 LLM 智能体的炒作。Czbond 感谢作者的深刻解释以及将其免费提供，无需付费墙的决定。
相关文章
OpenAI Agents: for the workflow logic: https://github.com/openai/openai-agents-python/blob/48ff99bb...
Pydantic Agents: organizes steps in a graph: https://github.com/pydantic/pydantic-ai/blob/4c0f384a0626299...
Langchain: demonstrates the loop structure: https://github.com/langchain-ai/langchain/blob/4d1d726e61ed5...
If all the hype has been confusing, this guide shows how they actually work under the hood, with simple examples. Check it out!
https://zacharyhuang.substack.com/p/llm-agent-internal-as-a-...
reply