Update app.py

app.py

@@ -31,7 +31,8 @@ def load_doc(list_file_path, chunk_size, chunk_overlap):
     return doc_splits
 
 # Create vector database
-def create_db(splits, collection_name, db_type):
+def create_db(list_file_path, chunk_size, chunk_overlap, db_type):
+    splits = load_doc(list_file_path, chunk_size, chunk_overlap)
     embedding = HuggingFaceEmbeddings()
     
     if db_type == "ChromaDB":
@@ -40,7 +41,7 @@ def create_db(splits, collection_name, db_type):
             documents=splits,
             embedding=embedding,
             client=new_client,
-            collection_name=collection_name,
+            collection_name="default_collection",
         )
     elif db_type == "FAISS":
         vectordb = FAISS.from_documents(
@@ -56,12 +57,12 @@ def create_db(splits, collection_name, db_type):
         vectordb = Milvus.from_documents(
             documents=splits,
             embedding=embedding,
-            collection_name=collection_name,
+            collection_name="default_collection",
         )
     else:
         raise ValueError(f"Unsupported vector database type: {db_type}")
     
-    return vectordb
+    return vectordb, "default_collection", "Vector database created successfully"
 
 # Initialize langchain LLM chain
 def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, initial_prompt, progress=gr.Progress()):
@@ -251,13 +252,13 @@ def demo():
                 clear_btn_no_doc = gr.ClearButton([msg_no_doc, chatbot_no_doc], value="Clear conversation")
 
         # Preprocessing events
-        db_btn.click(initialize_database, 
+        db_btn.click(create_db, 
             inputs=[document, slider_chunk_size, slider_chunk_overlap, db_type_radio], 
             outputs=[vector_db, collection_name, db_progress])
         set_prompt_btn.click(lambda prompt: gr.update(value=prompt), 
                              inputs=prompt_input, 
                              outputs=initial_prompt)
-        qachain_btn.click(initialize_LLM, 
+        qachain_btn.click(initialize_llmchain, 
             inputs=[llm_btn, slider_temperature, slider_maxtokens, slider_topk, vector_db, initial_prompt], 
             outputs=[qa_chain, llm_progress]).then(lambda:[None,"",0,"",0,"",0], 
             inputs=None,