mddunlap924/LangChain-SynData-RAG-Eval

LangChain, Llama2-Chat, and zero- and few-shot prompting are used to generate synthetic datasets for IR and RAG system evaluation

40
/ 100
Emerging

This project helps evaluate Information Retrieval (IR) and Retrieval Augmented Generation (RAG) systems by generating synthetic datasets. It takes existing documents or text sources as input and produces realistic question-and-answer pairs based on those sources. Anyone building or improving search functionalities or AI chatbots can use this to create test data without manual annotation.

No commits in the last 6 months.

Use this if you need to create diverse and comprehensive test datasets for your search or RAG system, especially when human-annotated data is too costly or time-consuming to obtain.

Not ideal if you are looking for a solution that relies on external cloud-based LLM APIs or if you need to generate data for tasks other than IR and RAG evaluation.

Information Retrieval RAG systems LLM evaluation AI chatbot testing Synthetic data generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

40

Forks

8

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/mddunlap924/LangChain-SynData-RAG-Eval"

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