Update app.py

app.py

@@ -52,6 +52,31 @@ login(HF_TOKEN)
 api = HfApi()
 
 
+def initialize():
+    global vectorstore, chunks, llm
+
+    
+    download_gitlab_repo_to_hfspace(GITLAB_API_URL, GITLAB_PROJECT_ID, GITLAB_PROJECT_VERSION)
+    
+    code_texts, code_references = extract_repo_files(DATA_DIR, ['kadi_apy'], [])
+    #doc_texts, doc_references = extract_files_and_filepath_from_dir(DATA_DIR, ['docs/source/'], [])
+    doc_texts, doc_references = extract_repo_files(DATA_DIR, [], [])
+    
+    print("LEEEEEEEEEEEENGTH of code_texts: ", len(code_texts))
+    print("LEEEEEEEEEEEENGTH 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 = setup_vectorstore(doc_chunks + code_chunks, EMBEDDING_MODEL_NAME, VECTORSTORE_DIRECTORY)
+    llm = get_groq_llm(LLM_MODEL_NAME, LLM_MODEL_TEMPERATURE, GROQ_API_KEY)
+
+
+initialize()
+
 def rag_workflow(query):
     """
     RAGChain class to perform the complete RAG workflow.
@@ -98,32 +123,14 @@ def rag_workflow(query):
 
     return response
 
-
-def initialize():
-    global vectorstore, chunks, llm
-
     
-    download_gitlab_repo_to_hfspace(GITLAB_API_URL, GITLAB_PROJECT_ID, GITLAB_PROJECT_VERSION)
-    
-    code_texts, code_references = extract_repo_files(DATA_DIR, ['kadi_apy'], [])
-    #doc_texts, doc_references = extract_files_and_filepath_from_dir(DATA_DIR, ['docs/source/'], [])
-    doc_texts, doc_references = extract_repo_files(DATA_DIR, [], [])
-    
-    print("LEEEEEEEEEEEENGTH of code_texts: ", len(code_texts))
-    print("LEEEEEEEEEEEENGTH 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)}")
+def bot_kadi(history):
+    user_query = history[-1][0]
+    response = rag_workflow(user_query)
+    history[-1] = (user_query, response)
 
-    vectorstore = setup_vectorstore(doc_chunks + code_chunks, EMBEDDING_MODEL_NAME, VECTORSTORE_DIRECTORY)
-    llm = get_groq_llm(LLM_MODEL_NAME, LLM_MODEL_TEMPERATURE, GROQ_API_KEY)
+    yield history  
 
-    from langchain_community.document_loaders import TextLoader
-          
-initialize()
 
 
 # Gradio utils
@@ -140,14 +147,6 @@ def add_text(history, text):
 
 import gradio as gr
 
-
-def bot_kadi(history):
-    user_query = history[-1][0]
-    response = rag_workflow(user_query)
-    history[-1] = (user_query, response)
-
-    yield history  
-
 def main():
     with gr.Blocks() as demo:
         gr.Markdown("## KadiAPY - AI Coding-Assistant")