Locating and editing factual associations in GPT (NeurIPS 2022)

在本项目中使用Haystack框架实现模拟健康档案私有知识库构建和检索全流程，通过一份代码实现了同时支持多种大模型（如OpenAI、阿里通义千问等）的RAG（检索增强生成）功能:(1)离线步骤:文档加载->文档切分->向量化->灌入向量数据库；在线步骤:获取用户问题->用户问题向量化->检索向量数据库->将检索结果和用户问题填入prompt模版->用最终的prompt调用LLM->由LLM生成回复

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

A library for efficient similarity search and clustering of dense vectors.