Skip to content

Latest commit

 

History

History
63 lines (37 loc) · 772 Bytes

README.md

File metadata and controls

63 lines (37 loc) · 772 Bytes
Raw

LLM-RAG-with-MLDE

LLM RAG System with MLDE

Architecture

RAG System Architecture

Index Generation

Index Generation

Retrieval Index

Index Retrieval

Showcase

Screenshot

Prerequisite

docker create network rag-system

How to Run

Build container images

make build

Start LLM

make up-fastchat-controller
make up-fastchat-model-worker
make up-fastchat-api-server

Start determined cluster

make up-determined

Create Embedding DB

make run-inference

Start RAG System

make up-rag