Weaviate 分享了智能体RAG的5个关键系统，告诉你为什么优化提示词没用，以及如何真正控制信息流。
可靠智能体RAG依赖控制信息如何到达模型、何时到达以及以何种形式到达。上下文工程分为5个相互关联的系统：1. 查询增强，用户输入混乱，需重写、扩展或分解查询以匹配检索系统。2. 检索，分块存在权衡，小分块提高精度但丢失上下文，大分块增加上下文但消耗更多窗口。3. 记忆，完整对话历史会产生噪音，长期记忆应存储在模型外部并定期维护。4. 工具，工具描述和选择消耗上下文，暴露过多 poorly described 工具会降低效率。5. 智能体，连接所有部分但会放大上游错误。
Better prompts won't fix a broken context pipeline. Reliable agentic RAG depends on controlling ...
Better prompts won't fix a broken context pipeline. Reliable agentic RAG depends on controlling 𝘄𝗵𝗮𝘁 𝗶𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 𝗿𝗲𝗮𝗰𝗵𝗲𝘀 𝘁𝗵𝗲 𝗺𝗼𝗱𝗲𝗹, 𝘄𝗵𝗲𝗻 𝗶𝘁 𝗮𝗿𝗿𝗶𝘃𝗲𝘀, 𝗮𝗻𝗱 𝗶𝗻 𝘄𝗵𝗮𝘁 𝗳𝗼𝗿𝗺. In @victorialslocum ’s latest video, she breaks context engineering into 5 interconnected systems: 𝟭. 𝗤𝘂𝗲𝗿𝘆 𝗮𝘂𝗴𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 User input is messy. Rewriting, expanding, or decomposing queries helps translate intent into something your retrieval system can actually use. No retrieval technique can compensate for misunderstood intent. 𝟮. 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 Chunking creates a real trade-off: small chunks improve precision but lose surrounding meaning, while large chunks add context but consume more of the window. Start with a simple baseline, then benchmark recursive or semantic chunking on representative data. 𝟯. 𝗠𝗲𝗺𝗼𝗿𝘆 Dumping complete conversation history into the prompt creates noise. Long-term memory should live outside the model and only be retrieved when relevant. It also needs maintenance: pruning stale information, merging duplicates, resolving contradictions, and deliberately forgetting what is no longer useful. 𝟰. 𝗧𝗼𝗼𝗹𝘀 Tool descriptions, argument formats, and tool selection all consume context. Exposing 100 poorly described tools doesn't make an agent more capable. It makes the relevant tool harder to find. 𝟱. 𝗔𝗴𝗲𝗻𝘁𝘀 Agents connect everything together by deciding what to retrieve, which tools to call, what to retain, and how to recover when a step fails. But they also compound upstream errors. Wrong chunks, stale memories, and malformed tool calls propagate through the entire pipeline. The model is only one part youtu.be/sUoNoaatRvU?si… ble agentic RAG comes from engineering how context flows around it. Watch here: https://t.co/0nxtfBfxZm Your browser does not support the video tag. 🔗 View on Twitter 💬 0 🔄 0 ❤️ 0 👀 142 ⚡