Skip to content

Latest commit

 

History

History
14 lines (10 loc) · 495 Bytes

README.md

File metadata and controls

14 lines (10 loc) · 495 Bytes

HippoRAG using APIs PDF-RAG

Implementation of the paper HippoRAG using APIs

The goal was to create a version that can run without GPUs using only API services to search over PDF

The paper is available at: https://arxiv.org/pdf/2405.14831

The authors' implementation is available at: https://github.com/OSU-NLP-Group/HippoRAG

Uses:

  • OpenAI: GPT-3.5-turbo-1106 for (LLM)
  • OpenAI: text-embedding-small 256 (embedding)
  • Neo4j (auraDB): GraphDB / Vector DB
  • Langchain