---
name: Knowledge Retrieval
slug: knowledge-retrieval
category: AI Engineering
description: Knowledge Retrieval performs semantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG). Use it to find information in PDFs, whitepapers, or technical documentation when domain-specific knowledge is not available on the open web.
github: "https://github.com/open-gitagent/opengap/tree/main/examples/nvidia-deep-researcher/skills/knowledge-retrieval"
language: TypeScript
stars: 2916
forks: 346
install: "npx degit https://github.com/open-gitagent/opengap/tree/main/examples/nvidia-deep-researcher/skills/knowledge-retrieval ~/.claude/skills/knowledge-retrieval"
installs_to: ~/.claude/skills/knowledge-retrieval
source_path: examples/nvidia-deep-researcher/skills/knowledge-retrieval/SKILL.md
collection_size: 18
category_size: 2451
collection_url: "https://dirskills.com/collections/open-gitagent/opengap"
added: 2026-08-17T07:10:06.056Z
last_synced: 2026-08-17T07:10:06.056Z
canonical_url: "https://dirskills.com/skills/knowledge-retrieval"
---

# Knowledge Retrieval

Knowledge Retrieval performs semantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG). Use it to find information in PDFs, whitepapers, or technical documentation when domain-specific knowledge is not available on the open web.

**Install:**

```bash
npx degit https://github.com/open-gitagent/opengap/tree/main/examples/nvidia-deep-researcher/skills/knowledge-retrieval ~/.claude/skills/knowledge-retrieval
```

## README

# 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

1. Formulate a semantic search query describing the information needed
2. Call `knowledge_retrieval` with the query
3. Review returned chunks for relevance
4. 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
- Returns ranked chunks based on semantic similarity
- Citation format: `Citation: filename.ext, p.X`
- Each call counts toward the researcher's 8-call limit per task

## Backend Options

- **LlamaIndex + ChromaDB** — Local vector store with LlamaIndex orchestration
- **NVIDIA Foundational RAG** — NVIDIA-hosted RAG service with NeMo Retriever