In this video tutorial, we'll walk through how to get started with the open source ChatGPT retrieval plugin, which:
...provides a flexible solution for semantic search and retrieval of personal or organizational documents using natural language queries.
For this project, we'll be hosting the retrieval plugin at Replit and adding long term memory by computing and storing embeddings at a vector database, Pinecone.
As highlighted in the written version of this guide, the steps we'll take include:
- Setting Up the Retrieval Plugin in Replit
- Storing Vector Embeddings at Pinecone
- Testing the Query API Endpoint
- Deploying the ChatGPT Retrieval Plugin
- Using the Retrieval Plugin in ChatGPT