vectara/py-vectara-agentic

A python library for creating AI assistants with Vectara, using Agentic RAG

54
/ 100
Established

Leverages LlamaIndex's agent framework with built-in support for ReAct and function-calling patterns, enabling agents to iteratively reason and call Vectara RAG tools. Provides pre-built domain-specific tools for finance, legal, and other verticals, plus integration with Vectara's hallucination correction (VHC) to ground responses in retrieved data. Supports streaming responses and observability via Arize Phoenix, while offering seamless multi-LLM compatibility (OpenAI, Anthropic, Gemini, Cohere, Bedrock, and others).

114 stars. Available on PyPI.

Maintenance 6 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 14 / 25

How are scores calculated?

Stars

114

Forks

13

Language

Python

License

Apache-2.0

Last pushed

Nov 10, 2025

Commits (30d)

0

Dependencies

46

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/vectara/py-vectara-agentic"

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