knowledge-retrieval
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.
Knowledge Retrieval searches pre-ingested documents using semantic similarity and RAG technology.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-02
Knowledge Retrieval searches pre-ingested documents using semantic similarity and RAG technology. 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.
Use it when
- Yes.
- Knowledge-retrieval can access NVIDIA and LlamaIndex RAG backends for powering its semantic search capabilities.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
open-gitagent/opengap/knowledge-retrieval · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does knowledge-retrieval search documents with semantic search?
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.
Can knowledge-retrieval find information in my ingested PDFs?
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.
What backends does knowledge-retrieval support?
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.
Does knowledge-retrieval provide citations with results?
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.
How should I use knowledge-retrieval before external sources?
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.
What license does knowledge-retrieval use?
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.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Knowledge Retrieval
Perform semantic search over a pre-ingested document collection using Retrieval-Augmented Generation (RAG). Backed by LlamaIndex with ChromaDB or NVIDIA Foundational RAG.
When to Use
- Searching internal or pre-ingested documents and reports
- Finding information in PDFs, whitepapers, or technical documentation
- Retrieving domain-specific knowledge not available on the open web
- This is the highest priority source — check the knowledge base first before web or paper searches
How to Use
- Formulate a semantic search query describing the information needed
- Call
knowledge_retrievalwith the query - Review returned chunks for relevance
- Note the citation metadata (filename, page number) for sourcing
Result Format
Results are returned as text chunks with citation metadata:
Relevant text passage from the ingested document...
Citation: filename.pdf, p.12
Constraints
- Searches only over documents that have been ingested into the knowledge index
(truncated - see the full file via the links below)
File tree — 1 file
examples/nvidia-deep-researcher/skills/knowledge-retrieval/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Search pre-ingested documents using semantic similarity”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Paper Search queries Google Scholar to locate peer-reviewed research, systematic reviews, and seminal papers with citation metrics. Filter results by publication year and review snippets to ground claims in academic literature.
Web Search taps into live web content to surface recent news, articles, and current data on any topic. It returns up to 5 results per query in a structured format with source URLs for easy citation, making it ideal when you need information beyond your existing knowledge base.
Wiki Query searches your knowledge base to answer questions, combining information across multiple pages with proper source attribution. It distinguishes confident claims from inferences and flags knowledge gaps. When an answer represents useful synthesis not yet captured in the wiki, it can file that back as a new page to compound your knowledge over time.
Wiki Ingest automates the process of reading source documents and weaving their content into your wiki. It identifies key entities, claims, and relationships, then creates or updates wiki pages while maintaining bidirectional cross-references and a source index. Each ingest operation is logged for full traceability.
This skill guides you through installing the gitagent CLI and creating your first agent from a template. You'll customize core files like agent.yaml and SOUL.md, validate your setup, and run your agent locally or from a git repository.
Translate agent configurations across multiple frameworks with a single command. Export to Claude Code, OpenAI, CrewAI, Lyzr, GitHub Models, and other formats, or import from existing Claude, Cursor, and CrewAI projects to standardize your automation setup.
More skills create-agent (MIT) · run-agent (MIT)