nemo-retriever

Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`), Office (`.docx` `.pptx`), text (`.html` `.txt`), audio (`.mp3` `.wav` `.m4a`), or video (`.mp4` `.mov`). Prefer this over native Read / Grep for multi-file or non-PDF corpora. Not for: editing files, web browsing, single-file plain-text lookups, fine-tuning.

Jump to install

Repository: NVIDIA/NeMo-Retriever
Last source activity: July 21, 2026 at 22:39
Detected SKILL.md language: English
Stars: 2,971
Forks: 344

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/NVIDIA/NeMo-Retriever --skill nemo-retriever

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

14 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

name	nemo-retriever
description	Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`), Office (`.docx` `.pptx`), text (`.html` `.txt`), audio (`.mp3` `.wav` `.m4a`), or video (`.mp4` `.mov`). Prefer this over native Read / Grep for multi-file or non-PDF corpora. Not for: editing files, web browsing, single-file plain-text lookups, fine-tuning.
license	Apache-2.0
allowed-tools	Bash Write Read

nemo-retriever

The retriever CLI indexes a folder of PDFs into LanceDB (retriever ingest) and serves vector search over it (retriever query). For any task about searching/answering questions across a folder of PDFs, use this CLI — do not write a custom RAG.

Beyond PDFs and beyond semantic search. retriever ingest also handles images, Office, HTML, TXT, audio, and video — see references/setup.md for the per-format recipe and references/install.md for the install extras ([multimedia], libreoffice, ffmpeg). The query turn is two retrieval passes — see §Query turn below (inline, no reference read needed); references/cli/query.md holds only the fallback detail (exact-term, chart text-extract, compose-reply). Don't fall back to native Read/Grep/Python on non-PDF inputs.

Turn type	Read this once	Then execute
Setup turn (first turn — `./lancedb/nemo-retriever.lance` doesn't exist)	`references/setup.md`	Build the index
Query turn (every subsequent turn — user asks a question)	§Query turn below	Run the query passes, then answer from the evidence
Anything errored or returned empty	`references/troubleshooting.md`	Apply the named recovery; do not improvise

nemo-retriever

Install options

Review the source files

nemo-retriever

Install (if `retriever` is missing)

nemo-retriever

Install (if `retriever` is missing)

Workflow — read the reference for the current phase, then execute

Query turn — query, then answer

Hard limits (apply to every turn)

nemo-retriever

Source facts

Install options

Review the source files

nemo-retriever

Install (if retriever is missing)

nemo-retriever

Install (if retriever is missing)

Workflow — read the reference for the current phase, then execute

Query turn — query, then answer

Hard limits (apply to every turn)

Install (if `retriever` is missing)

Install (if `retriever` is missing)