Update app.py

app.py

@@ -1,63 +1,70 @@
 import gradio as gr
-import google.generativeai as genai
 import os
-import time
 import json
+import mimetypes
 from dotenv import load_dotenv
 
-# --- Configuration ---
+# Your exact requested imports
+from google import genai
+from google.genai import types
+
+# --- Configuration and Client Initialization ---
 load_dotenv()
 
-# This is the correct way to initialize for the 'google-genai' library
+# Initializing the client exactly as in your code
 try:
-    genai.configure(api_key=os.environ["GEMINI_API_KEY"])
+    client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])
 except KeyError:
     raise gr.Error("FATAL: GEMINI_API_KEY not found. Please set it in your Hugging Face Space secrets.")
 
-# --- Core Function ---
+# --- Core Gradio Function ---
 
 def analyze_device_condition(video_file_path):
     if not video_file_path:
         return "Please upload video", "", ""
 
     try:
-        # 1. This library has a simple helper to upload and process the file
-        print("Log: Uploading file to Google...")
-        video_file = genai.upload_file(path=video_file_path)
-
-        while video_file.state.name == "PROCESSING":
-            print("Log: Waiting for video processing...")
-            time.sleep(5)
-            video_file = genai.get_file(video_file.name)
-
-        if video_file.state.name == "FAILED":
-            raise gr.Error("Video processing failed. The file might be corrupted or in an unsupported format.")
-            
-        print(f"Log: File processed successfully.")
+        print(f"Log: Starting analysis for video: {video_file_path}")
 
-        # 2. Prompt for JSON output
+        # 1. Prepare video file for the client API
+        mime_type, _ = mimetypes.guess_type(video_file_path)
+        if not mime_type or not mime_type.startswith("video"):
+            raise ValueError("Unsupported file type. Please upload a valid video.")
+        
+        with open(video_file_path, "rb") as video:
+            video_part = types.Part(
+                inline_data=types.Blob(mime_type=mime_type, data=video.read())
+            )
+        
+        # 2. Prepare the prompt and model settings from your code
         prompt = """
-        Analyze the provided video. Respond ONLY with a valid JSON object with three keys:
+        Analyze the provided video of a device. Respond ONLY with a valid JSON object.
+        The JSON object must have the following three keys and nothing else:
         1. "device_type": A short string identifying the device.
-        2. "condition": A single word: "Mint", "Excellent", "Good", "Fair", or "Poor".
-        3. "reason": A brief string explaining the condition.
+        2. "condition": A single word describing its condition. Choose from: "Mint", "Excellent", "Good", "Fair", "Poor".
+        3. "reason": A brief string explaining the condition rating.
         """
-
-        # 3. Call the Gemini Model using the simpler syntax
-        # Using a reliable flash model
-        model = genai.GenerativeModel(model_name="gemini-1.5-flash-latest")
         
-        print("Log: Sending prompt and video to Gemini...")
-        response = model.generate_content(
-            [prompt, video_file],
-            generation_config=genai.types.GenerationConfig(
-                response_mime_type="application/json",
-                temperature=0.2
-            )
+        # USING YOUR EXACT REQUESTED MODEL NAME
+        model_name = "gemini-2.5-flash"
+        
+        generate_content_config = types.GenerateContentConfig(
+            temperature=0.2,
+            response_mime_type="application/json"
         )
         
-        print("Log: Analysis received from Gemini.")
-        genai.delete_file(video_file.name)
+        # The contents list must contain both the text prompt and the video part
+        contents = [prompt, video_part]
+
+        # 3. Call the Gemini API using the client.generate_content method
+        print(f"Log: Sending request to model: {model_name}...")
+        response = client.generate_content(
+            model=f"models/{model_name}",
+            contents=contents,
+            generation_config=generate_content_config,
+        )
+
+        print("Log: Analysis received.")
 
         # 4. Parse the JSON response
         parsed_json = json.loads(response.text)