LLM: RAG-GPT
Revision as of 13:30, 16 July 2024 by Onnowpurbo (talk | contribs)
Sumber: https://github.com/gpt-open/rag-gpt?tab=readme-ov-file#using-local-llms
Buat API di LLamaCloud, login mengggunakan email
https://cloud.llamaindex.ai/api-key
Sebagai user biasa, clone RAG-GPT
git clone https://github.com/open-kf/rag-gpt.git && cd rag-gpt cp env_of_ollama .env
Edit .env
LLM_NAME="Ollama" OLLAMA_MODEL_NAME="xxxx" OLLAMA_BASE_URL="http://127.0.0.1:11434" MIN_RELEVANCE_SCORE=0.4 BOT_TOPIC="xxxx" URL_PREFIX="http://127.0.0.1:7000/" USE_PREPROCESS_QUERY=1 USE_RERANKING=1 USE_DEBUG=0 USE_LLAMA_PARSE=0 LLAMA_CLOUD_API_KEY="xxxx"
menjadi misalnya
LLM_NAME="Ollama" OLLAMA_MODEL_NAME="llama3" OLLAMA_BASE_URL="http://127.0.0.1:11434" MIN_RELEVANCE_SCORE=0.4 BOT_TOPIC="OpenIM" URL_PREFIX="http://127.0.0.1:7000/" USE_PREPROCESS_QUERY=1 USE_RERANKING=1 USE_DEBUG=0 USE_LLAMA_PARSE=0 LLAMA_CLOUD_API_KEY="llx-HYs1KFrtKm5eeLAJeJW4goCnAaeKZeHd6RmjKSprrogxYdwP!"
Buat dari source
sudo apt install python3.12-venv python3 -m venv myenv source myenv/bin/activate pip install -r requirements.txt python3 create_sqlite_db.py
sh start.sh
Browser
http://ipaddress:7000