hanjiale/Temporal-GraphRAG

Official code for ''RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge''.

28
/ 100
Experimental

This project helps financial analysts, market researchers, or business strategists understand how information evolves over time within large document sets like earnings call transcripts. It processes your text documents (like reports or articles) and extracts key information, organizing it into a 'time-aware' knowledge graph. The output is more accurate, context-rich answers to your questions, especially those related to specific time periods or trends, enabling you to track how financial concepts, companies, or events change over time.

Use this if you need to ask precise, time-sensitive questions about a constantly updated body of documents and require answers that reflect the most current or relevant information for a given period.

Not ideal if your documents contain static information that rarely changes or if you only need simple fact retrieval without any temporal context.

financial-analysis market-research business-intelligence trend-analysis knowledge-management
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 4 / 25

How are scores calculated?

Stars

26

Forks

1

Language

Python

License

Category

retrieval

Last pushed

Feb 25, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/hanjiale/Temporal-GraphRAG"

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