Update app.py

app.py

@@ -1,64 +1,50 @@
+import base64
+import os
+from google import genai
+from google.genai import types
 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")
 
+def generate(prompt):
+    client = genai.Client(
+        api_key=os.environ.get("GEMINI_API_KEY"),
+    )
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    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})
+    model = "gemini-2.0-flash"
+    contents = [
+        types.Content(
+            role="user",
+            parts=[
+                types.Part.from_text(text=prompt),
+            ],
+        ),
+    ]
+    tools = [
+        types.Tool(google_search=types.GoogleSearch())
+    ]
+    generate_content_config = types.GenerateContentConfig(
+        temperature=0.35,
+        top_p=0.95,
+        top_k=40,
+        max_output_tokens=8192,
+        tools=tools,
+        response_mime_type="text/plain",
+    )
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
+    for chunk in client.models.generate_content_stream(
+        model=model,
+        contents=contents,
+        config=generate_content_config,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-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.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(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+        response += chunk.text
+    return response
 
 
 if __name__ == "__main__":
-    demo.launch()
+    iface = gr.ChatInterface(
+        fn=generate,
+        title="Gemini Chatbot with Google Search",
+        description="A chatbot powered by Gemini 2.0 Flash and Google Search.",
+    )
+    iface.launch()