Creating and using embeddings from bulk-loaded pdf documents

[lpm0073]

Greetings, i teach an AI course at university of british columbia, and i use this public repo for demonstrating how to use LangChain to bulk load a Pinecone vector database from a collection of pdf documents, and also how build hybrid prompts from this data. It additionally demonstrates how to use Pydantic for working with sensitive credentials data (like api keys for example), so overall, it’s a good scaffolding tool for real-world RAG projects.

Hope you find it helpful. Don’t forget to star the repo :)
https://github.com/FullStackWithLawrence/openai-embeddings