Metadata-Version: 2.4
Name: nvidia_rag
Version: 2.2.1
Summary: This blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.
Author-email: NVIDIA RAG <foundational-rag-dev@exchange.nvidia.com>
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/NVIDIA-AI-Blueprints/rag
Project-URL: Documentation, https://github.com/NVIDIA-AI-Blueprints/rag/blob/main/README.md
Requires-Python: >=3.12
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: bleach==6.2.0
Requires-Dist: dataclass-wizard==0.27.0
Requires-Dist: fastapi==0.115.5
Requires-Dist: langchain==0.3.7
Requires-Dist: langchain-community==0.3.7
Requires-Dist: langchain-milvus>=0.1.10
Requires-Dist: langchain-nvidia-ai-endpoints==0.3.10
Requires-Dist: minio==7.2.15
Requires-Dist: pdfplumber>=0.6
Requires-Dist: pydantic==2.9.2
Requires-Dist: pymilvus==2.5.8
Requires-Dist: pymilvus-model==0.3.2
Requires-Dist: python-multipart==0.0.18
Requires-Dist: pyyaml==6.0.2
Requires-Dist: unstructured[all-docs]>=0.15.1
Requires-Dist: uvicorn[standard]==0.32.0
Requires-Dist: langchain-core>=0.3.31
Requires-Dist: redis==5.2.1
Requires-Dist: protobuf>=5.29.5
Provides-Extra: rag
Requires-Dist: langchain-openai==0.2.8; extra == "rag"
Requires-Dist: opentelemetry-api==1.29.0; extra == "rag"
Requires-Dist: opentelemetry-exporter-otlp==1.29.0; extra == "rag"
Requires-Dist: opentelemetry-exporter-prometheus==0.50b0; extra == "rag"
Requires-Dist: opentelemetry-instrumentation==0.50b0; extra == "rag"
Requires-Dist: opentelemetry-instrumentation-fastapi==0.50b0; extra == "rag"
Requires-Dist: opentelemetry-instrumentation-milvus==0.36.0; extra == "rag"
Requires-Dist: opentelemetry-processor-baggage==0.50b0; extra == "rag"
Requires-Dist: opentelemetry-sdk==1.29.0; extra == "rag"
Provides-Extra: ingest
Requires-Dist: nv-ingest-api==25.6.2; extra == "ingest"
Requires-Dist: nv-ingest-client==25.6.3; extra == "ingest"
Requires-Dist: tritonclient==2.57.0; extra == "ingest"
Requires-Dist: overrides==7.7.0; extra == "ingest"
Requires-Dist: tqdm==4.67.1; extra == "ingest"
Requires-Dist: opentelemetry-api==1.29.0; extra == "ingest"
Requires-Dist: opentelemetry-exporter-otlp==1.29.0; extra == "ingest"
Requires-Dist: opentelemetry-exporter-prometheus==0.50b0; extra == "ingest"
Requires-Dist: opentelemetry-instrumentation==0.50b0; extra == "ingest"
Requires-Dist: opentelemetry-instrumentation-fastapi==0.50b0; extra == "ingest"
Requires-Dist: opentelemetry-instrumentation-milvus==0.36.0; extra == "ingest"
Requires-Dist: opentelemetry-processor-baggage==0.50b0; extra == "ingest"
Requires-Dist: opentelemetry-sdk==1.29.0; extra == "ingest"
Provides-Extra: all
Requires-Dist: nvidia-rag[ingest,rag]; extra == "all"
Dynamic: license-file

<h1><img align="center" src="https://github.com/user-attachments/assets/cbe0d62f-c856-4e0b-b3ee-6184b7c4d96f">NVIDIA RAG Blueprint</h1>


## Overview
This python package enables developers to interact with the [NVIDIA RAG Blueprint](https://build.nvidia.com/nvidia/build-an-enterprise-rag-pipeline).
The NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.
One of the key use cases in Generative AI is enabling users to ask questions and receive answers based on their enterprise data corpus.
This blueprint demonstrates how to set up a RAG solution that uses NVIDIA NIM and GPU-accelerated components.
By default, this blueprint leverages locally-deployed NVIDIA NIM microservices to meet specific data governance and latency requirements.
However, you can replace these models with your NVIDIA-hosted models available in the [NVIDIA API Catalog.](https://build.nvidia.com)

The target audience for this blueprint is developers who want a quick start to set up a RAG solution with a path-to-production with the NVIDIA NIM.

## Source code
The source code for this python package is available [here.](https://github.com/NVIDIA-AI-Blueprints/rag)

## Example usage
Refer to [this notebook](https://github.com/NVIDIA-AI-Blueprints/rag/blob/main/notebooks/rag_library_usage.ipynb) to understand how to leverage this python package for building enterprise RAG usecases!
