nvidia/skills · Official
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`).
npx skills add nvidia/skills --skill nemo-retriever
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggr…
68 installsUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybr…
568.2K installsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or bot…
216.8K installsUse this skill whenever the user wants to do anything with PDF files. This includes reading or …
192.4K installsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.do…
184.5K installsOther skills from nvidia/skills · top by installs.
npx skills add nvidia/skills
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main
Parsed from SKILL.md frontmatter.
Bash Write ReadFiles included with this skill beyond the listing page.
SKILL.md
3,417 B
SUMMARY.md
456 B
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). For non-semantic operations — page filter, verbatim quote with citation, corpus-level aggregate, chart/image caption hits — see references/query.md. Don't fall back to native Read/Grep/Python on non-PDF inputs.
retriever is missing)If command -v retriever returns nothing, follow references/install.md to install the NeMo Retriever Library before proceeding. It prints RETRIEVERVENV=<path>; substitute that path for <RETRIEVERVENV> in every example in this skill (setup, query, troubleshooting, and the CLI references).
| Turn type | Read this once | Then execute |
|---|---|---|
Setup turn (first turn — ./lancedb/nv-ingest.lance doesn't exist) |
references/setup.md |
Build the index |
| Query turn (every subsequent turn — user asks a question) | references/query.md |
One retriever query call |
| Anything errored or returned empty | references/troubleshooting.md |
Apply the named recovery; do not improvise |
For the full retriever ingest / retriever query CLI specs, see references/cli/ingest.md and references/cli/query.md. You do not need these for routine turns — <RETRIEVER_VENV>/bin/retriever <subcommand> --help is faster.
Before ingesting a mixed folder, inventory extensions (find <dir> -name '.' | sed 's/.*\.//' | sort -u) — --input-type=auto silently drops anything outside the supported set. See references/troubleshooting.md "Unsupported file types".
references/setup.md). STOP after the index lands.retriever query, +1 optional targeted text-extract per references/query.md. Reply and then STOP.TodoWrite, Glob, Grep, Read of whole PDFs, re-running setup, spawning subagents, speculative "confirmation" calls.Long query turns (5+ tool calls, 1M+ cache-read tokens) cost ~5× a disciplined turn and almost always still produce the wrong answer. Answering partially beats timing out.