files restructured

codes/config_loader.py

@@ -1,10 +1,10 @@
 import yaml
 import os
 
-with open('../config.yaml', 'r') as f:
+with open('config.yaml', 'r') as f:
     config_data = yaml.safe_load(f)
         
-with open('../system_prompts.yaml', 'r') as f:
+with open('system_prompts.yaml', 'r') as f:
     system_prompts = yaml.safe_load(f)
     
 if 'GPT_CONFIG_FILE' in config_data:

codes/run_setup.py

@@ -0,0 +1,14 @@
+import os
+from kg_rag.codes.utility import config_data
+
+
+print("")
+print("Starting to set up KG-RAG ...")
+print("")
+
+if os.path.exists(config_data["VECTOR_DB_PATH"]):
+    print("vectorDB already exists!")
+else:
+    print("Creating vectorDB ...")
+    from kg_rag.codes.py_scripts.vectorDB.create_vectordb import create_vectordb
+    create_vectordb()

codes/utility.py

@@ -12,7 +12,7 @@ from langchain.vectorstores import Chroma
 from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM, TextStreamer, GPTQConfig
-from py_scripts.config_loader import *
+from kg_rag.codes.config_loader import *
 
 
 

codes/vectorDB/create_vectordb.py

@@ -1,5 +1,5 @@
 import pickle
-from py_scripts.utility import RecursiveCharacterTextSplitter, Chroma, SentenceTransformerEmbeddings, config_data, time
+from kg_rag.codes.utility import RecursiveCharacterTextSplitter, Chroma, SentenceTransformerEmbeddings, config_data, time
 
 
 DATA_PATH = config_data["VECTOR_DB_DISEASE_ENTITY_PATH"]

config.yaml

@@ -10,4 +10,11 @@ VECTOR_DB_SENTENCE_EMBEDDING_MODEL : 'sentence-transformers/all-MiniLM-L6-v2'
 # Just note that, this assumes your GPT config file is in the $HOME path, if not, change it accordingly
 # Also, GPT '.env' file should contain values for API_KEY, API_VERSION, RESOURCE_ENDPOINT. We are not including those parameters in this yaml file
 GPT_CONFIG_FILE : '$HOME/.gpt_config.env'
-GPT_API_TYPE : 'azure'
+GPT_API_TYPE : 'azure'
+
+# Llama model name (Refer Hugging face to get the correct name for the model version you would like to use, also make sure you have the right permission to use the model)
+LLAMA_MODEL_NAME : 'meta-llama/Llama-2-13b-chat-hf'
+LLAMA_MODEL_BRANCH : 'main'
+
+# Path for caching LLM model files (When the model gets downloaded from hugging face, it will be saved in this path)
+LLM_CACHE_DIR : '/data/somank/llm_data/llm_models/huggingface'