Update app.py

app.py

@@ -1,11 +1,11 @@
 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("HuggingFaceH4/zephyr-7b-beta")
 
 modelpath = "distilgpt2"
 
@@ -13,7 +13,7 @@ pipe = pipeline(
     "text-generation",
     model=modelpath
 )
-initial_messages = [
+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."},
@@ -33,30 +33,28 @@ def respond(
     top_p,
 ):
     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]})
-            if val[1]:
-                messages.append({"role": "assistant", "content": val[1]})
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
-        messages.append({"role": "user", "content": message})
-    except Exception as e:
-        return f"Error: {str(e)}"
+    messages.append({"role": "user", "content": message})
 
-    combined_messages = " ".join([msg["content"] for msg in messages])
+    response = ""
 
-    response = pipe(
-        combined_messages,
-        max_new_tokens=max_tokens,
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
         temperature=temperature,
         top_p=top_p,
-    )[0]["generated_text"]
-    yield response
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
 
 
 """
@@ -80,4 +78,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()