How can I get the same result from LlamaCPP using it in Llama-index?

reno_queen

I am trying to do the same prompt (query) I did on a simple pdf (legal pt-br document) using pure llama cpp python but now using llama index: from llama_cpp import Llama import os, re, sys from pypdf import PdfReader reader = PdfReader('inicial_pg10_teste.pdf') # https://files.pdfupload.io/documents/c2683560/inicial_pg10_teste.pdf total_pages = len(reader.pages) texto_inicial = '' for page_num in range(total_pages): page = reader.pages[page_num]...

Originally asked by celsowm on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

Kindly use some Vector Storage like pinecone or qdrant, etc. Reduce the chunk size and introduce chunk overlap. Also you can use embedding models like "thenlper/gte-large" or similar. Please let me know if by doing these changes you are able to achieve better results.

Full answer by Siddhartha Sengupta: https://stackoverflow.stackexchange.com/a/78254693 (CC BY-SA 4.0).

Need it done for your business? UphillTech.