Update app.py

app.py

@@ -5,69 +5,33 @@ import streamlit as st
 from huggingface_hub import HfApi, login
 from dotenv import load_dotenv
 
-from download_repo import download_gitlab_repo_to_hfspace
-from process_repo import extract_repo_files
-from chunking import chunk_pythoncode_and_add_metadata, chunk_text_and_add_metadata
-from vectorstore import setup_vectorstore
 from llm import get_groq_llm
 from vectorstore import get_chroma_vectorstore
 from embeddings import get_SFR_Code_embedding_model
 from kadi_apy_bot import KadiAPYBot
-from repo_versions import store_message_from_json
 
 # Load environment variables from .env file
 load_dotenv()
 
-# Load configuration from JSON file
-
-with open("config.json", "r") as file:
-    config = json.load(file)
+vectorstore_path = "data/vectorstore"
 
 GROQ_API_KEY = os.environ["GROQ_API_KEY"]
 HF_TOKEN = os.environ["HF_Token"]
 
-
-VECTORSTORE_DIRECTORY = config["vectorstore_directory"]
-CHUNK_SIZE = config["chunking"]["chunk_size"]
-CHUNK_OVERLAP = config["chunking"]["chunk_overlap"]
-
-EMBEDDING_MODEL_NAME = config["embedding_model"]["name"]
-EMBEDDING_MODEL_VERSION = config["embedding_model"]["version"]
-
-LLM_MODEL_NAME = config["llm_model"]["name"]
-LLM_MODEL_TEMPERATURE = config["llm_model"]["temperature"]
-
-GITLAB_API_URL = config["gitlab"]["api_url"]
-GITLAB_PROJECT_ID = config["gitlab"]["project id"]
-GITLAB_PROJECT_VERSION = config["gitlab"]["project version"]
-
-DATA_DIR = config["data_dir"]
-HF_SPACE_NAME = config["hf_space_name"]
+with open("config.json", "r") as file:
+    config = json.load(file)
 
 login(HF_TOKEN)
 hf_api = HfApi()
 
+# Access the values
+LLM_MODEL_NAME = config["llm_model_name"]
+LLM_MODEL_TEMPERATURE = float(config["llm_model_temperature"])
 
 def initialize():
     global kadiAPY_bot
 
-
-    
-    # download_gitlab_repo_to_hfspace(GITLAB_API_URL, GITLAB_PROJECT_ID, GITLAB_PROJECT_VERSION, DATA_DIR, hf_api, HF_SPACE_NAME)
-    
-    # code_texts, code_references = extract_repo_files(DATA_DIR, ['kadi_apy'], [])
-    # doc_texts, doc_references = extract_repo_files(DATA_DIR, ['docs'], [])
-    
-    # print("Length of code_texts: ", len(code_texts))
-    # print("Length of doc_files: ", len(doc_texts))
-    
-    # code_chunks = chunk_pythoncode_and_add_metadata(code_texts, code_references)
-    # doc_chunks = chunk_text_and_add_metadata(doc_texts, doc_references, CHUNK_SIZE, CHUNK_OVERLAP)
-
-    # print(f"Total number of code_chunks: {len(code_chunks)}")
-    # print(f"Total number of doc_chunks: {len(doc_chunks)}")
-
-    vectorstore = get_chroma_vectorstore(get_SFR_Code_embedding_model(), "data/vectorstore")
+    vectorstore = get_chroma_vectorstore(get_SFR_Code_embedding_model(), vectorstore_path)
     llm = get_groq_llm(LLM_MODEL_NAME, LLM_MODEL_TEMPERATURE, GROQ_API_KEY)
 
     kadiAPY_bot = KadiAPYBot(llm, vectorstore)
@@ -75,7 +39,6 @@ def initialize():
 initialize()
 
 
-
 def bot_kadi(history):
     user_query = history[-1][0]   
     response = kadiAPY_bot.process_query(user_query)