varunshenoy/honestgpt

Grounding LLMs in truth with under 30 lines of code.

22
/ 100
Experimental

This project helps developers build more reliable applications using large language models (LLMs) like GPT-3. It takes a document and a user's question, then produces an accurate summary of the relevant parts of the document with citations. Developers who want to ensure their LLM applications provide factual, verifiable answers grounded in source material, rather than general or potentially incorrect information, would use this.

No commits in the last 6 months.

Use this if you are a developer looking for concise, factual summaries from documents, ensuring your LLM outputs are directly supported by the provided text with citations.

Not ideal if you need to build a complex conversational agent or require extensive customization beyond grounding LLMs in provided documents.

LLM development API integration Information retrieval Truthful AI Application development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

20

Forks

2

Language

License

Last pushed

Jul 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/varunshenoy/honestgpt"

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