{"enrichment":{"faq":[{"a":"Knowledge-retrieval uses Retrieval-Augmented Generation to perform semantic search across your ingested document collection. Rather than matching keywords, it understands the meaning of your query and ranks results by relevance, returning text passages with citation metadata so you can trace answers back to their sources.","q":"How does knowledge-retrieval search documents with semantic search?"},{"a":"Yes. Knowledge-retrieval is designed to search pre-ingested PDFs, reports, and technical documentation. It retrieves relevant passages by semantic similarity, making it ideal for locating domain-specific information across your uploaded document collection without needing external sources.","q":"Can knowledge-retrieval find information in my ingested PDFs?"},{"a":"Knowledge-retrieval can access NVIDIA and LlamaIndex RAG backends for powering its semantic search capabilities. This flexibility allows you to choose the infrastructure that best fits your deployment and performance requirements.","q":"What backends does knowledge-retrieval support?"},{"a":"Yes. Knowledge-retrieval returns text passages alongside citation metadata, allowing you to verify where each answer came from within your knowledge base. This transparency is essential for domain-specific queries where source attribution matters.","q":"Does knowledge-retrieval provide citations with results?"},{"a":"Knowledge-retrieval is optimized to query your knowledge base first, retrieving relevant passages from your pre-ingested documents before turning to external sources. This approach keeps your answers grounded in your own domain-specific content and reduces reliance on outside information.","q":"How should I use knowledge-retrieval before external sources?"},{"a":"Knowledge-retrieval is released under the MIT license, giving you freedom to use, modify, and distribute it in both open-source and commercial projects with minimal restrictions.","q":"What license does knowledge-retrieval use?"}],"shadow_tags":["vector-search","document-indexing","semantic-retrieval","citation-tracking","rag-pipeline","knowledge-base-query","embedding-similarity","text-chunking"],"summary_rewrite":"Knowledge Retrieval performs semantic search across your ingested document collection using Retrieval-Augmented Generation. It ranks results by relevance and returns text passages with citation metadata, making it ideal for finding domain-specific information in PDFs, reports, and technical documentation."},"files":[{"bytes":1546,"path":"examples/nvidia-deep-researcher/skills/knowledge-retrieval/SKILL.md","sha256":"b15b4ea2aa0b0015baf88e8fa25e7f06001be17349188a27796e4774ba645ea7","url":"https://skillfed.io/files/open-gitagent/opengap/knowledge-retrieval/ff75a1fd/SKILL.md"}],"id":"open-gitagent/opengap/knowledge-retrieval","links":{"html":"https://skillfed.io/open-gitagent/opengap/knowledge-retrieval","md":"https://skillfed.io/open-gitagent/opengap/knowledge-retrieval.md","repo":"https://github.com/open-gitagent/opengap"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":343,"language":"TypeScript","last_updated":"2026-07-02","license":"MIT","name":"knowledge-retrieval","publisher":"open-gitagent","stars":2903},"relations":{"similar":[{"id":"open-gitagent/opengap/paper-search"},{"id":"open-gitagent/opengap/wiki-query"},{"id":"open-gitagent/opengap/wiki-ingest"},{"id":"open-gitagent/opengap/web-search"},{"id":"open-gitagent/opengap/get-started"},{"id":"open-gitagent/opengap/export-agent"},{"id":"open-gitagent/opengap/run-agent"},{"id":"open-gitagent/opengap/manage-skills"},{"id":"open-gitagent/opengap/create-agent"},{"id":"open-gitagent/opengap/code-review"}]},"slug":{"owner":"open-gitagent","repo":"opengap","skill":"knowledge-retrieval"},"version":"ff75a1fd"}