Update app.py

app.py

@@ -1,10 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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
-"""
-
 # Default client with the first model
 client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
 
@@ -14,12 +10,12 @@ def switch_client(model_name: str):
 
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history: list[dict],
     system_message,
     max_tokens,
     temperature,
     top_p,
-    model_name  # Add this parameter for model selection
+    model_name
 ):
     # Switch client based on model selection
     global client
@@ -28,26 +24,22 @@ def respond(
     messages = [{"role": "system", "content": system_message}]
 
     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": val['role'], "content": val['content']})
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
+    # Get the response from the model
+    response = client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    )
 
-        response += token
-        yield response
+    # Extract the content from the response
+    final_response = response.choices[0].message['content']
+    
+    return final_response
 
 # Model names and their pseudonyms
 model_choices = [
@@ -60,7 +52,7 @@ pseudonyms = [model[1] for model in model_choices]
 # Function to handle model selection and pseudonyms
 def respond_with_pseudonym(
     message,
-    history: list[tuple[str, str]],
+    history: list[dict],
     system_message,
     max_tokens,
     temperature,
@@ -71,16 +63,14 @@ def respond_with_pseudonym(
     model_name = next(model[0] for model in model_choices if model[1] == selected_pseudonym)
     
     # Call the existing respond function
-    response = list(respond(message, history, system_message, max_tokens, temperature, top_p, model_name))
+    response = respond(message, history, system_message, max_tokens, temperature, top_p, model_name)
     
     # Add pseudonym at the end of the response
-    response[-1] += f"\n\n[Response generated by: {selected_pseudonym}]"
+    response += f"\n\n[Response generated by: {selected_pseudonym}]"
     
     return response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio Chat Interface
 demo = gr.ChatInterface(
     respond_with_pseudonym,
     additional_inputs=[
@@ -99,4 +89,4 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()