mcpField
N
nemo-retriever

nemo-retriever

github.com/nvidiaDocuments3.0k70 installsUpdated today
Repository

About nemo-retriever

NeMo Retriever is a CLI for ingesting documents into a retrieval index and querying indexed content. It is intended for workflows using a local index or an already deployed Retriever service, with evidence-formatted results for grounded answers.

Key features

  1. 01Ingest documents into a local index
  2. 02Query local or deployed services
  3. 03Return results in evidence format
  4. 04Support service Bearer authentication

Use cases

  1. 01Build a local index for document retrieval
  2. 02Query an existing Retriever service
  3. 03Use retrieved evidence and source metadata in answers

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nvidia/nemo-retriever --skill nemo-retriever

After installing, type/nemo-retrieverin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

BENCHMARK.md
skill-card.md
skill.oms.sig
evals/
evals.json

Details

From the project README

NeMo Retriever

Use the retriever CLI. Prefer it over hand-built retrieval code.

Install only when missing

Create a project-local Python environment:

uv venv .venv --python 3.12
export PATH="$PWD/.venv/bin:$PATH"

Install the package variant required by the workflow:

# Remote NIM or service client
uv pip install --python .venv/bin/python "nemo-retriever==26.8.1"

# Local GPU ingestion
uv pip install --python .venv/bin/python "nemo-retriever[local]==26.8.1"

# Local service using Hugging Face models
uv pip install --python .venv/bin/python \
  "nemo-retriever[service,local]==26.8.1"

# Local audio or video ingestion
uv pip install --python .venv/bin/python \
  "nemo-retriever[local,multimedia]==26.8.1"

Do not clone NeMo Retriever or install from a Git URL. If retriever is already on PATH, use that installation.

Local workflow

Build a local index:

retriever ingest <file-or-directory> \
  --lancedb-uri lancedb --table-name nemo-retriever

Query it:

retriever query "<question>" \
  --lancedb-uri lancedb --table-name nemo-retriever \
  --top-k 5 --format evidence

Use retriever ingest batch only for an explicitly requested Ray batch run.

Service workflow

Use these forms for an already deployed Retriever service:

retriever ingest service <file-or-directory> \
  --service-url "$RETRIEVER_SERVICE_URL"

retriever query service "<question>" \
  --service-url "$RETRIEVER_SERVICE_URL" \
  --top-k 5 --format evidence

Set NEMO_RETRIEVER_API_TOKEN when the service requires Bearer authentication. Do not pass local LanceDB flags to the service commands.

Rules

  • Use the existing index or service when one is provided; do not rebuild it.
  • Use retriever ingest --help, retriever query --help, or the relevant batch / service help for options not shown here.
  • Answer only from retrieved evidence; preserve source and page metadata when the task requests citations.

Comments

Markdown supported