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
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.
Stars
40
Forks
8
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
langchain-ai/langgraph
Build resilient language agents as graphs.
langchain-ai/langchain
The agent engineering platform
emarco177/langchain-course
A project-based course repository for developing AI agents using LangChain v1+ and LangGraph:...
teddylee777/langchain-teddynote
LangChain 을 더 쉽게 구현하기 위한 유틸 함수, 클래스를 만들어서 패키지로 배포하였습니다.
Harmeet10000/AgentNexus-LangChain-FastAPI
Langchain FastAPI server