Explore: RAG llama

[Ganes556]

source video: https://www.youtube.com/watch?v=ojl2CyI78S0 -> but using python

to create the knowledge base -> raw text - create the chunk - create embedded and store in vector db (pgvector, chromadb, etc)

[Ganes556]

LLM framework python - https://python.langchain.com/docs/integrations/text_embedding/

source video: https://www.youtube.com/watch?v=JRU1CMvEae0 -> he uses RAG in Laravel but that's not official he creates it manually

[Ganes556]

• add chunks table and add embedded content, but still get some error in API fetch in route

[Ganes556]

• already implement in laravel, but to search the data (16k) need lot of memory to set in php.ini, at least 512M