Update app.py

app.py

@@ -1,12 +1,17 @@
+import os
+import requests
 import gradio as gr
-from huggingface_hub import InferenceClient
+from dotenv import load_dotenv
 
-"""
-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")
+# Load environment variables from .env file
+load_dotenv()
 
+# Fetch token from environment variables
+CLOUDFLARE_TOKEN = os.getenv("CLOUDFLARE_TOKEN")
+if not CLOUDFLARE_TOKEN:
+    raise EnvironmentError("CLOUDFLARE_TOKEN not found in environment variables.")
 
+# Function to send API requests to the Gemma model
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,34 +20,45 @@ def respond(
     temperature,
     top_p,
 ):
+    # Construct the messages payload
     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 = ""
+    # Define API endpoint and headers
+    url = "https://api.cloudflare.com/client/v4/accounts/e16531aac7469b4b54ef1e8108e93495/ai/run/@cf/google/gemma-2b-it-lora"
+    headers = {
+        "Authorization": f"Bearer {CLOUDFLARE_TOKEN}",
+        "Content-Type": "application/json",
+    }
 
-    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
+    # Payload with model settings and messages
+    payload = {
+        "messages": messages,
+        "raw": "true",
+        "lora": "1b3c4e5c-ba8a-4e98-973b-573c572cfb34",
+        "max_tokens": max_tokens,
+        "temperature": temperature,
+        "top_p": top_p,
+    }
 
-        response += token
-        yield response
+    # Make the API request
+    response = requests.post(url, headers=headers, json=payload)
 
+    if response.status_code == 200:
+        data = response.json()
+        # Extract response content
+        result = data.get("choices", [{}])[0].get("message", {}).get("content", "")
+        return result
+    else:
+        return f"Error: {response.status_code} - {response.text}"
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+
+# Gradio Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +75,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()