Update app.py

app.py

@@ -1,19 +1,19 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+#from huggingface_hub import InferenceClient
 from transformers import pipeline
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 #client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-client = InferenceClient("distilbert/distilgpt2")
+
 modelpath = "distilgpt2"
 
 pipe = pipeline(
     "text-generation",
     model=modelpath
 )
-messages = [
+initial_messages = [
     {"role": "system", "content": "You are a customer applying for a housing loan in India. Provide dummy details about your application and negotiate the terms."},
     {"role": "user", "content": "Hi!Welcome to Hero Housing Finance!"},
     {"role": "assistant", "content": "Hello, I would like to apply for a loan."},
@@ -34,6 +34,10 @@ def respond(
 ):
     messages = [{"role": "system", "content": system_message}]
     try:
+        #add initil message to the conversation history
+        for msg in initial_messages:
+            messages.append(msg)
+
         for val in history:
             if val[0]:
                 messages.append({"role": "user", "content": val[0]})
@@ -44,19 +48,15 @@ def respond(
     except Exception as e:
         return f"Error: {str(e)}"
 
-    response = ""
+    combined_messages = " ".join([msg["content"] for msg in messages])
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    response = pipe(
+        combined_messages,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+    )[0]["generated_text"]
+    yield response
 
 
 """