CoRAL-ASU/weaver

(EMNLP 2025) Weaver: A modular agentic pipeline that dynamically combines SQL and LLMs for advanced table-based question answering

23
/ 100
Experimental

This tool helps data analysts and researchers answer complex questions by querying structured data like CSV files and database tables. You provide it with a table and a natural language question, and it gives you a precise answer, even for questions requiring multiple steps or external context. It's designed for anyone who needs to extract insights from tabular data quickly and accurately.

No commits in the last 6 months.

Use this if you need to automate accurate question-answering over your tabular datasets, combining the precision of database queries with the semantic understanding of AI models.

Not ideal if your primary data source is unstructured text documents or if you don't have well-structured tables to query.

data-analysis business-intelligence financial-reporting scientific-research data-extraction
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

HTML

License

Apache-2.0

Last pushed

Jul 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/CoRAL-ASU/weaver"

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