Update app.py

app.py

@@ -1,11 +1,10 @@
 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 google.generativeai as genai
+import os
 
+# Load API key from Hugging Face Secrets
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
+genai.configure(api_key=GEMINI_API_KEY)
 
 def respond(
     message,
@@ -18,31 +17,24 @@ def respond(
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
-        if val[0]:
+        if val[0]:  # User message
             messages.append({"role": "user", "content": val[0]})
-        if val[1]:
+        if val[1]:  # Assistant response
             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
+    # Call Gemini API
+    model = genai.GenerativeModel("gemini-1.5-flash")
+    response = model.generate_content(message, stream=True)
 
+    output = ""
+    for chunk in response:
+        if chunk.text:
+            output += chunk.text
+            yield output  # Stream response in real-time
 
-"""
-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 +51,6 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()
+