NVIDIA-AI-Blueprints/ai-virtual-assistant

Customizable, AI-driven virtual assistant designed to streamline customer service operations, handle common inquiries, and improve overall user satisfaction through automated and contextually aware responses.

54
/ 100
Established

Powered by NVIDIA NIM microservices (including Llama 3.3-70B for inference, embeddings, and reranking models), it uses a LangGraph-based orchestrator with retrieval-augmented generation (RAG) combining Milvus vector database for unstructured data and PostgreSQL for structured data. Docker Compose and Helm deployment options enable both single-node and production-scale deployments with GPU optimization (L40 minimum for vector operations, 8xH100 for full self-hosting).

235 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 25 / 25

How are scores calculated?

Stars

235

Forks

133

Language

Python

License

Apache-2.0

Last pushed

Feb 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/NVIDIA-AI-Blueprints/ai-virtual-assistant"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.