Skip to content

it-is-jay/RAG-Video-Transcript-Prompt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

RAG - Retrieval Augmented Generation

The RAG code performs the following tasks:

To summarize the overall flow:
1.  Embeddings for question is generated.
2.  Based on this embeddings the most similar content embedding is retrieved from vector DB (Pinecone)
3.  Not this content and question is sent into the LLM model
4.  parser gets the output and prints the string based on the context.

In order to execute the code, install requirements present in the first cell and have .env file which specifies the API keys for OPENAI and PINECONE,

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors