Update app.py

app.py

@@ -6,42 +6,63 @@ from retriever import *
 from retrieve_docs import *
 from make_chain_model import make_chain_llm
 from make_answer import *
+from transformers import TextStreamer
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+llm = load_Auto()
+pinecone,bm25 = all_files('files')
+retriever=retriever(pinecone,bm25)
+rag_chain = make_chain_llm(retriever,llm)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def response(message, history):
+    return rag_chain.invoke(message)
 
-    messages.append({"role": "user", "content": message})
+# def talk(,history):
+#     # k = 1 # number of retrieved documents
+#     # scores , retrieved_documents = search(prompt, k)
+#     # formatted_prompt = format_prompt(prompt,retrieved_documents,k)
+#     # formatted_prompt = formatted_prompt[:2000] # to avoid GPU OOM
+    
+#     messages =[
+#     {"role": "system", "content": f"{PROMPT}"},
+#     {}
+#     {"role": "user", "content": f"{instruction}"}
+#     ]
+    
+#     # tell the model to generate
+#     input_ids = tokenizer.apply_chat_template(
+#     messages,
+#     add_generation_prompt=True,
+#     return_tensors="pt"
+#     ).to(model.device)
 
-    response = ""
+#     terminators = [
+#     tokenizer.eos_token_id,
+#     tokenizer.convert_tokens_to_ids("<|eot_id|>")
+#     ]
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+#     text_streamer = TextStreamer(tokenizer)
 
-        response += token
-        yield response
+#     outputs = model.generate(
+#     input_ids,
+#     max_new_tokens=4096,
+#     eos_token_id=terminators,
+#     do_sample=True,
+#     streamer = text_streamer,
+#     temperature=0.6,
+#     top_p=0.9,
+#     repetition_penalty = 1.1
+#     )
+#     response = []
+#     for text in streamer:
+#         response.append(outputs)
+#         print(response)
+#         yield "".join(response)
+        
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
+
 TITLE = "FUT FUT Chatbot"
 
 DESCRIPTION = """
@@ -57,7 +78,7 @@ Resources used to build this project :
 Examples = [['시흥 풋살 구장 추천해줘'],['풋살 경기 규칙 설명해줘'], ['풋살 경기 시간 알려줘']]
 
 demo = gr.ChatInterface(
-    fn=talk,
+    fn=response,
     chatbot=gr.Chatbot(
         show_label=True,
         show_share_button=True,
@@ -67,11 +88,9 @@ demo = gr.ChatInterface(
         bubble_full_width=False,
     ),
     theme="Soft",
-    examples=[["what's anarchy ? "]],
+    examples=Examples,
     title=TITLE,
     description=DESCRIPTION,
-    examples=Examples
-    
 )
 demo.launch(debug=True)