# NVIDIARAGRetriever

> **Class** in `langchain_nvidia_ai_endpoints`

📖 [View in docs](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever)

LangChain retriever that queries the NVIDIA RAG Blueprint /v1/search endpoint.

Targets containerized RAG deployments where the rag-server exposes the search API.
Supports all DocumentSearch parameters from the RAG server schema.

## Signature

```python
NVIDIARAGRetriever()
```

## Description

**Example:**

.. code-block:: python

from langchain_nvidia_ai_endpoints import NVIDIARAGRetriever

retriever = NVIDIARAGRetriever(
    base_url="http://localhost:8081",
    collection_names=["test_multimodal_query"],
    k=4,
)
docs = retriever.invoke("What is machine learning?")

## Extends

- `BaseRetriever`

## Properties

- `model_config`
- `base_url`
- `k`
- `collection_names`
- `vdb_top_k`
- `vdb_endpoint`
- `enable_reranker`
- `enable_query_rewriting`
- `enable_filter_generator`
- `enable_citations`
- `filter_expr`
- `confidence_threshold`
- `embedding_model`
- `embedding_endpoint`
- `reranker_model`
- `reranker_endpoint`
- `messages`
- `timeout`

---

[View source on GitHub](https://github.com/langchain-ai/langchain-nvidia/blob/5bfb68d5b10aa0330a6b79a36375b9bc0c6acef7/libs/ai-endpoints/langchain_nvidia_ai_endpoints/retrievers.py#L74)