graphgeeks-lab/odsc-agentic-ai-summit-2025

Code from the ODSC Agentic Graph RAG workshop combining vector, FTS & graph retrieval for RAG. Includes observability and guardrails for evaluating outputs.

24
/ 100
Experimental

Implements a complete agentic RAG pipeline using BAML for structured LLM extraction, embedding notes in LanceDB with hybrid vector+FTS indexing, and persisting entity relationships in Kuzu for multi-hop graph queries. Instruments the entire workflow with Opik for observability and adds PII guardrails to prevent sensitive healthcare data leakage during answer generation.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 1 / 25
Community 15 / 25

How are scores calculated?

Stars

18

Forks

4

Language

Python

License

Last pushed

Aug 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/graphgeeks-lab/odsc-agentic-ai-summit-2025"

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