RingBDStack/DyG-RAG

Code implementation for DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning.

38
/ 100
Emerging

This project helps you answer complex questions that depend on understanding events and their sequence over time, even from large amounts of unstructured text. It takes your text data and a question, then uses an 'event-centric' approach to extract and organize temporal information into a dynamic graph. The output is a highly accurate answer, especially for 'when' and 'what happened next' types of questions. This is for researchers, analysts, or anyone who needs to extract precise temporal insights from text.

No commits in the last 6 months.

Use this if you need to perform accurate question-answering on text where the timing and sequence of events are critical to finding the correct answer.

Not ideal if your questions are simple factual lookups or do not require deep temporal reasoning over event sequences.

temporal-knowledge-extraction event-sequencing-analysis historical-data-query narrative-intelligence longitudinal-analysis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

51

Forks

7

Language

Python

License

Last pushed

Aug 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/RingBDStack/DyG-RAG"

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