https://sre-ai-blog.pages.dev/en/tags/rag/Recent content in RAG on SRE & AI Field NotesHugoenSun, 26 Jul 2026 01:29:48 +0800https://sre-ai-blog.pages.dev/en/posts/rag-knowledge-base/Wed, 15 Jul 2026 00:00:00 +0000https://sre-ai-blog.pages.dev/en/posts/rag-knowledge-base/<h2 id="1-the-pain-of-operations-knowledge-management">1. The Pain of Operations Knowledge Management</h2> <p>In large organizations, operations knowledge is often scattered across Wikis, Runbooks, Slack records, and incident reports. On-call engineers must navigate multiple systems to locate critical information. RAG technology offers a new approach to solving this problem.</p> <h2 id="2-system-architecture">2. System Architecture</h2> <p>We built a complete RAG pipeline based on the LangChain framework: documents are parsed, split, and stored in Chroma vector database; when an engineer asks a question, the system first retrieves the most relevant document fragments, then generates an answer via an LLM.</p> <h2 id="3-key-technologies-and-implementation">3. Key Technologies and Implementation</h2> <p>We chose text-embedding-3-small as the embedding model, with a chunk size of 512 tokens and 64 token overlap. The retrieval uses a hybrid strategy: vector similarity + BM25 keyword weighting.</p>