WIP

.gitignore

@@ -0,0 +1,2 @@
+.venv/
+.vscode/

app.py

@@ -1,52 +1,62 @@
 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
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
+import requests
+import json
 
 def respond(
     message,
     history: list[tuple[str, str]],
     system_message,
+    access_token,
+    model_endpoint,
     max_tokens,
     temperature,
     top_p,
 ):
+    # Build conversation history
     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": "user", "content": message})
-
-    response = ""
-
-    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
-
-        response += token
-        yield response
+    
+    # Vertex AI API request
+    headers = {
+        "Authorization": f"Bearer {access_token}",
+        "Content-Type": "application/json"
+    }
+    
+    payload = {
+        "instances": [{
+            "messages": messages,
+            "max_tokens": max_tokens,
+            "temperature": temperature,
+            "top_p": top_p
+        }]
+    }
+    
+    try:
+        response = requests.post(model_endpoint, headers=headers, json=payload)
+        response.raise_for_status()
+        
+        result = response.json()
+        # Extract response text from Vertex AI response format
+        generated_text = result["predictions"][0]["content"]
+        yield generated_text
+        
+    except Exception as e:
+        yield f"Error: {str(e)}"
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="", label="Google Cloud Access Token", type="password"),
+        gr.Textbox(value="", label="Vertex AI Model Endpoint URL", placeholder="https://us-central1-aiplatform.googleapis.com/v1/projects/YOUR_PROJECT/locations/us-central1/endpoints/YOUR_ENDPOINT:predict"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+gradio
+google-cloud-aiplatform
+requests