Update app.py

app.py

@@ -15,6 +15,7 @@ from langchain.chains import ConversationChain
 from langchain.memory import ConversationBufferMemory
 from langchain_community.llms import HuggingFaceEndpoint
 import torch
+
 api_token = os.getenv("HF_TOKEN")
 
 list_llm = ["meta-llama/Meta-Llama-3-8B-Instruct", "mistralai/Mistral-7B-Instruct-v0.3"]
@@ -155,6 +156,33 @@ def upload_file(file_obj):
         list_file_path.append(file.name)
     return list_file_path
 
+def initialize_database(list_file_obj, chunk_size, chunk_overlap, db_type, progress=gr.Progress()):
+    list_file_path = [x.name for x in list_file_obj if x is not None]
+    progress(0.1, desc="Creating collection name...")
+    collection_name = create_collection_name(list_file_path[0])
+    progress(0.25, desc="Loading document...")
+    doc_splits = load_doc(list_file_path, chunk_size, chunk_overlap)
+    progress(0.5, desc="Generating vector database...")
+    vector_db = create_db(doc_splits, collection_name, db_type)
+    progress(0.9, desc="Done!")
+    return vector_db, collection_name, "Complete!"
+
+def create_collection_name(filepath):
+    collection_name = Path(filepath).stem
+    collection_name = collection_name.replace(" ", "-")
+    collection_name = unidecode(collection_name)
+    collection_name = re.sub('[^A-Za-z0-9]+', '-', collection_name)
+    collection_name = collection_name[:50]
+    if len(collection_name) < 3:
+        collection_name = collection_name + 'xyz'
+    if not collection_name[0].isalnum():
+        collection_name = 'A' + collection_name[1:]
+    if not collection_name[-1].isalnum():
+        collection_name = collection_name[:-1] + 'Z'
+    print('Filepath: ', filepath)
+    print('Collection name: ', collection_name)
+    return collection_name
+
 def demo():
     with gr.Blocks(theme="base") as demo:
         vector_db = gr.State()
@@ -257,7 +285,7 @@ def demo():
         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,