NVIDIA
Explore Models Blueprints GPUs
Terms of Use

|

Privacy Policy

|

Manage My Privacy

|

Contact

Copyright © 2025 NVIDIA Corporation

ModelsExplore Models
BlueprintsGet Started with Blueprints
GPUsLaunch a GPU Instance

Deploy Models Now with NVIDIA NIM

Optimized inference for the world’s leading models
Free serverless APIs for developmentAccelerated by DGX Cloud
Self-Host on your GPU infrastructure
Continuous vulnerability fixes
DiscoverModelsBlueprintsGPUs
Docs
Forums
models
ReasoningVisionVisual DesignRetrievalSpeechBiologySimulationClimate & WeatherSafety & Moderation
industries
AutomotiveGamingHealthcareIndustrialRobotics

Retrieval

Embedding Models

Connect AI agents to enterprise data with world-class NVIDIA NeMo Retriever and community models for multilingual/cross-lingual text question-answering.

Run Anywhere

nvidiallama-3.2-nv-embedqa-1b-v2

Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.

embeddingnemo retrieverrun on rtxretrieval augmented generationtext-to-embedding
Run Anywhere

nvidianv-embedqa-mistral-7b-v2

Multilingual text question-answering retrieval, transforming textual information into dense vector representations.

embeddingretrieval augmented generationnemo retriever
Run Anywhere

nvidianv-embedqa-e5-v5

English text embedding model for question-answering retrieval.

embeddingnemo retrieverretrieval augmented generationtext-to-embedding
Run Anywhere

snowflakearctic-embed-l

Optimized community model for text embedding.

embeddingnemo retrieverretrieval augmented generationtext-to-embedding

Reranking Models

Improve information retrieval accuracy with world-class NVIDIA NeMo Retriever models for reranking retrieved enterprise data to improve answer relevancy.

Run Anywhere

nvidiallama-3.2-nv-rerankqa-1b-v2

Fine-tuned reranking model for multilingual, cross-lingual text question-answering retrieval, with long context support.

nemo retrieverrerankingretrieval augmented generation
Run Anywhere

nvidianv-rerankqa-mistral-4b-v3

Multilingual text reranking model.

rerankingnemo retrieverretrieval augmented generation

Extraction Models

Leverage retrieval-augmented generation to ground large language models in your proprietary data.

Run Anywhere

baidupaddleocr

Model for table extraction that receives an image as input, runs OCR on the image, and returns the text within the image and its bounding boxes.

optical character detectionoptical character recognitiontable extractiondata ingestionextractionnemo retrieverrun on rtx
Run Anywhere

nvidianv-yolox-page-elements-v1

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

chart detectiondata ingestionobject detectiontable detectionextractionnemo retrieverrun on rtx
Run Anywhere

nvidianemoretriever-parse

Cutting-edge vision-language model exceling in retrieving text and metadata from images.

data ingestionnemo retrieveroptical character recognitionsupported language - englishtable extraction
Run Anywhere

nvidianemoretriever-page-elements-v2

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

chart detectionobject detectiontable detectiondata ingestionnemo retriever
PREVIEW

googledeplot

Translate images of plots into tables with one-shot visual language understanding.

multimodaldata ingestionnemo retrieverimage-to-text
Run Anywhere

nvidianemoretriever-table-structure-v1

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

chart detectionobject detectiontable detectiondata ingestionnemo retriever
Run Anywhere

nvidianemoretriever-graphic-elements-v1

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

chart detectionobject detectiontable detectiondata ingestionnemo retriever

Explore NVIDIA Blueprints

Connect your data to AI with comprehensive reference workflows that accelerate AI application development and deployment, featuring NVIDIA NIM and NeMo building blocks for RAG, AI agents, digital humans, and more.

nvidiaBuild an Enterprise RAG pipeline

Connect AI applications to multimodal enterprise data with a scalable retrieval augmented generation (RAG) pipeline built on highly performant, industry-leading NIM microservices, for faster PDF data extraction and more accurate information retrieval.

blueprintnimnemo retrieverretrieval-augmented generationenterpriselaunchablenvidia ai

nvidiaBuild an AI Virtual Assistant

Create intelligent virtual assistants for customer service across every industry

blueprintcustomer serviceretrieval-augmented generationlaunchablenvidia aicontact centerllm

nvidiaBuild a Video Search and Summarization (VSS) Agent

Ingest massive volumes of live or archived videos and extract insights for summarization and interactive Q&A

blueprintenterpriselaunchablenvidia aichatgenerative aivideo-to-textvision

nvidiaBuild a Digital Human

Create intelligent, interactive avatars for customer service across industries

audio-to-faceblueprintchatdigital humansspeech-to-textenterprisenvidia ainvidia omniverse

nvidiaBuild an AI Agent for Research and Reporting

Create AI agents that reason, plan, reflect and refine to produce high-quality reports based on source materials of your choice.

blueprintllama nemotronnimnemo retrieverreasoningretrieval-augmented generationenterprisenvidia ai

llamaindexDocument Research Assistant for Blog Creation

Automate research, and generate blogs with AI Agents using LlamaIndex and Llama3.3-70B NIM LLM.

ai agentsblog creationblueprintllamaindexpartnerlaunchablenvidia ai

crewaiCode Documentation for Software Development

Document your github repositories with AI Agents using CrewAI and Llama3.3 70B NIM.

ai agentsblueprintcode documentationcrewaipartnerlaunchablenvidia ai