A new technique called task-aware knowledge compression (TAKC) addresses the limitations of Retrieval-Augmented Generation (RAG) for complex analytical tasks spanning hundreds of documents, such as financial due diligence or regulatory compliance reviews. RAG’s similarity search surfaces relevant fragments but often misses cross-document connections. TAKC uses an LLM to produce shorter, task-focused summaries of documents, with different summaries for different tasks. For example, an annual report compressed for financial analysis needs revenue figures, margins, and cash flow data, while the same report compressed for a compliance review needs regulatory citations and violation histories. The system compresses documents offline, once per document per task type. At query time, it retrieves a pre-compressed representation rather than the original document. If the compressed representation lacks sufficient detail, a query complexity analyzer routes the question to a lower compression tier. TAKC provides access to the entire knowledge base in compressed form, not just the top-k chunks from similarity search, and preserves connections between documents by compressing them together. A complete open-source implementation can be deployed on AWS.