> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# NVIDIARAGRetriever integration

> Integrate with the NVIDIARAGRetriever using LangChain Python.

`NVIDIARAGRetriever` connects LangChain to a running [NVIDIA RAG Blueprint](https://docs.nvidia.com/rag/latest/index.html) server and retrieves relevant documents via the `/v1/search` endpoint. It supports sync and async retrieval, reranking, query rewriting, and metadata filtering.

## Overview

### Integration details

| Class                                                                                                                      | Package                                                                                                 | Local | Serializable | JS support |                                                    Downloads                                                   |                                                   Version                                                   |
| :------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------ | :---: | :----------: | :--------: | :------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------: |
| [`NVIDIARAGRetriever`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever) | [`langchain-nvidia-ai-endpoints`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints) |   ✅   |     beta     |      ❌     | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_nvidia_ai_endpoints?style=flat-square\&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_nvidia_ai_endpoints?style=flat-square\&label=%20) |

## Setup

`NVIDIARAGRetriever` requires a running NVIDIA RAG Blueprint server. Refer to the [NVIDIA RAG Blueprint documentation](https://docs.nvidia.com/rag/latest/index.html) for deployment instructions. By default the server listens on `http://localhost:8081` and expects at least one ingested collection in its vector database.

No API key is required for the retriever; authentication is handled by the RAG server.

### Installation

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -qU langchain-nvidia-ai-endpoints
```

## Instantiation

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_nvidia_ai_endpoints import NVIDIARAGRetriever

retriever = NVIDIARAGRetriever(
    base_url="http://localhost:8081",
    k=4,
    collection_names=["my_collection"],
)
```

Key parameters:

| Parameter                | Type        | Default               | Description                                             |
| ------------------------ | ----------- | --------------------- | ------------------------------------------------------- |
| `base_url`               | `str`       | —                     | Base URL of the RAG Blueprint server                    |
| `k`                      | `int`       | `10`                  | Number of documents to return (0–25)                    |
| `collection_names`       | `list[str]` | `["multimodal_data"]` | Vector database collections to search                   |
| `vdb_top_k`              | `int`       | `100`                 | Results retrieved before reranking (0–400)              |
| `enable_reranker`        | `bool`      | `True`                | Enable reranking of retrieved results                   |
| `enable_query_rewriting` | `bool`      | `False`               | Enable query rewriting before search                    |
| `confidence_threshold`   | `float`     | `0.0`                 | Minimum relevance score (0.0–1.0) to include a document |
| `timeout`                | `float`     | `60`                  | HTTP request timeout in seconds                         |

## Usage

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
docs = retriever.invoke("What is NVIDIA NIM?")
for doc in docs:
    print(doc.page_content)
```

Async retrieval is also supported:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
docs = await retriever.ainvoke("What is NVIDIA NIM?")
```

## Use within a chain

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_nvidia_ai_endpoints import ChatNVIDIA, NVIDIARAGRetriever

retriever = NVIDIARAGRetriever(base_url="http://localhost:8081", k=4)
llm = ChatNVIDIA(model="meta/llama3-8b-instruct")

prompt = ChatPromptTemplate.from_template(
    "Answer the question based only on the following context:\n{context}\n\nQuestion: {question}"
)


def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)


chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

chain.invoke("What is NVIDIA NIM?")
```

## API reference

For detailed documentation of all `NVIDIARAGRetriever` features and configurations head to the [API reference](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever).

## Related topics

* [NVIDIA Provider Page](/oss/python/integrations/providers/nvidia)
* [`ChatNVIDIA` integration](/oss/python/integrations/chat/nvidia_ai_endpoints)
* [`NVIDIAEmbeddings` integration](/oss/python/integrations/embeddings/nvidia_ai_endpoints)
* [NVIDIA RAG Blueprint documentation](https://docs.nvidia.com/rag/latest/index.html)

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/retrievers/nvidia.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>