本页尚未翻译

本页内容仍为英文原文，源自官方文档 tutorials/agents/nvidia-rag-blueprint/index。中文翻译正在分批进行中。

NVIDIA RAG Blueprint with LanceDB

Use LanceDB as the retrieval layer for NVIDIA RAG Blueprint with a Docker-first, retrieval-only reference integration.

What this tutorial shows

If you are using NVIDIA RAG Blueprints and want to evaluate LanceDB in that stack, this tutorial gives you a concrete starting point. It shows how to use LanceDB as the retrieval layer for a Docker-based NVIDIA RAG deployment with a small, script-driven reference integration where LanceDB Embedded runs directly in the NVIDIA containers, the collection is prepared ahead of time, and the RAG server retrieves from it for search and generation. The example is intentionally retrieval-only, but it also includes hybrid search and reranker selection so you can see how LanceDB fits into a realistic NVIDIA retrieval workflow.

提示

The runnable example for this tutorial lives in the VectorDB recipes repository.

How NVIDIA organizes vector databases

NVIDIA's RAG Blueprint documentation effectively describes three different patterns for vector database support.

1. There are built-in backends such as Milvus, where NVIDIA already owns both ingestion and retrieval.
2. There are built-in alternatives such as Elasticsearch, where NVIDIA still owns the end-to-end flow but switches the backend through configuration.
3. Then, there is the custom vector database path, where you implement a VDBRag backend yourself and register it in NVIDIA's factory.

The LanceDB example shown below fits into the third category. More specifically, it follows NVIDIA's retrieval-only custom backend path: the data is prepared in LanceDB ahead of time, and NVIDIA RAG Blueprint is then pointed at that existing collection for search and generation. It does not yet teach NVIDIA's ingestor how to write new documents into LanceDB automatically.

Deployment model

This reference integration uses LanceDB Embedded as an embedded retrieval library, not as a separate database service. In practice, APP_VECTORSTORE_NAME is set to lancedb, APP_VECTORSTORE_URL points to a local filesystem path inside the NVIDIA containers, the LanceDB collection is prepared ahead of time, and the NVIDIA RAG server loads the LanceDB adapter to retrieve directly from that local dataset.

What the recipe contains

The recipe at examples/nvidia-rag-blueprint-lancedb is organized around a small number of practical pieces. The data-prep script builds a demo LanceDB collection from scratch, generates embeddings through the LanceDB embedding registry, and creates a full-text index so hybrid retrieval works immediately. The adapter file shows the retrieval-only integration point for NVIDIA RAG Blueprint, while the Docker override and NVIDIA change guide show the minimal configuration and source changes needed to run the example against NVIDIA's containers.

End-to-end flow

1. Prepare the LanceDB collection

From the recipe directory:

uv sync
uv run prepare_lancedb.py --embedder demo-keyword --reranker mrr

That script creates:

• a local LanceDB dataset under data/
• a collection named nvidia_blueprint_demo
• automatic embeddings generated at ingest time
• an FTS index for hybrid search

The default embedder is an offline demo embedder so the example stays easy to run. If you want a more realistic setup, the same script can switch to a sentence-transformers embedder.

2. Patch the NVIDIA blueprint

Follow the instructions in the recipe's nvidia_blueprint_changes.md. The essential changes are:

• add LanceDB dependencies to the NVIDIA environment
• copy lancedb_vdb.py into the NVIDIA source tree
• register the lancedb branch in NVIDIA's VDB factory

NVIDIA's RAG blueprint documentation and custom-VDB guide provide useful background if you want more context before applying the LanceDB-specific changes.

3. Start the Docker deployment

Set the absolute path to the recipe directory:

export LANCEDB_RECIPE_DIR=/absolute/path/to/vectordb-recipes/examples/nvidia-rag-blueprint-lancedb

Then from the NVIDIA repo root:

docker compose \
  -f deploy/compose/docker-compose-rag-server.yaml \
  -f "$LANCEDB_RECIPE_DIR"/docker-compose.override.yml \
  up -d --build

docker compose \
  -f deploy/compose/docker-compose-ingestor-server.yaml \
  -f "$LANCEDB_RECIPE_DIR"/docker-compose.override.yml \
  up -d --build

The key environment values are:

• APP_VECTORSTORE_NAME=lancedb
• APP_VECTORSTORE_URL=/opt/lancedb-recipe/data
• COLLECTION_NAME=nvidia_blueprint_demo
• APP_VECTORSTORE_SEARCHTYPE=hybrid
• LANCEDB_RERANKER=mrr

Verifying the integration

Search

curl -X POST http://localhost:8081/v1/search \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "How do I replace Milvus in the NVIDIA RAG blueprint with LanceDB?",
    "use_knowledge_base": true,
    "collection_names": ["nvidia_blueprint_demo"],
    "vdb_top_k": 3,
    "reranker_top_k": 0
  }'

Generate

curl -N -X POST http://localhost:8081/v1/generate \
  -H 'Content-Type: application/json' \
  -d '{
    "messages": [{"role":"user","content":"Summarize the LanceDB integration approach."}],
    "use_knowledge_base": true,
    "collection_names": ["nvidia_blueprint_demo"],
    "vdb_top_k": 3,
    "reranker_top_k": 0
  }'

Hybrid retrieval and rerankers

This example is meant to prove more than a trivial vector lookup.

• LanceDB hybrid retrieval combines vector search with full-text search
• the recipe creates the FTS index as part of dataset prep
• the adapter supports RRFReranker, MRRReranker, and CrossEncoderReranker
• the default example uses MRRReranker, not a plain weighted linear combination

Hybrid retrieval is important for NVIDIA partner workloads because product names, storage platforms, and technical jargon often need exact lexical matching as well as semantic retrieval.

How this can be extended

The current example follows NVIDIA's custom retrieval-only backend path. In practice, that means the LanceDB collection is created ahead of time and NVIDIA RAG Blueprint is then pointed at that existing collection for search and generation. The sample data in prepare_lancedb.py exists only to make that flow runnable end to end: it creates a small local collection, inserts a few documents, generates embeddings, and builds an FTS index so the NVIDIA side has something real to query.

A fuller integration is possible. NVIDIA's custom VDBRag interface also supports the pattern used by built-in backends such as Milvus and Elasticsearch, where NVIDIA owns both ingestion and retrieval. To make LanceDB work that way, a complete LanceDB backend would need to implement the ingestion methods NVIDIA documents, especially create_collection and write_to_index, along with the retrieval and collection-management methods expected by the rest of the stack.

The open work is in defining how NVIDIA's ingestor should write records into LanceDB, how that storage is shared between the ingestor and the RAG server, and how document and collection metadata should be exposed so the broader NVIDIA APIs behave correctly. Until those pieces exist, this example should be read as: prepare LanceDB first, then let NVIDIA retrieve from it.