I am experimenting with Langchain RAG to implement DocGenie.
The idea is to break down the process into two steps
Indexing: Load the document, store the embeddings
Retrieval: Find the right embeddings and generate
Since this will be the core of the DocGenie, I created a core folder and underneath we have two files. The store.py file is doing the indexing and the genie.py is supposed to use the stored data to answer any questions.
Right now the issue is genie.py is throwing error when I run it.
I am experimenting with Langchain RAG to implement DocGenie.
The idea is to break down the process into two steps
Since this will be the core of the DocGenie, I created a core folder and underneath we have two files. The store.py file is doing the indexing and the genie.py is supposed to use the stored data to answer any questions.
Right now the issue is genie.py is throwing error when I run it.