Gitagent knowledge-retrieval

Semantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG)

install

source · Clone the upstream repo

git clone https://github.com/open-gitagent/gitagent

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/open-gitagent/gitagent "$T" && mkdir -p ~/.claude/skills && cp -r "$T/examples/nvidia-deep-researcher/skills/knowledge-retrieval" ~/.claude/skills/open-gitagent-gitagent-knowledge-retrieval && rm -rf "$T"

manifest: examples/nvidia-deep-researcher/skills/knowledge-retrieval/SKILL.md

source content

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_retrieval
```
with 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
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