Update app.py

app.py

@@ -1,45 +1,43 @@
 import os
 import gradio as gr
 import requests
-import openai
 from PIL import Image
 
-# Set your API keys (replace with your actual keys or environment variables)
-sambanova_api_key = os.getenv("Vision")  # Sambanova API Key
-imagebb_api_key = os.getenv("ImageAPI")  # Your imgbb API key from environment variables
+# Set your API keys (replace with your actual keys or use environment variables)
+nvidia_api_key = os.getenv("Vision")  # NVIDIA API Key
+imagebb_api_key = os.getenv("ImageAPI")  # Imgbb API Key
 
-# Initialize Sambanova OpenAI client
-openai.api_key = sambanova_api_key
-openai.api_base = "https://api.sambanova.ai/v1"
+# NVIDIA API Endpoint
+invoke_url = "https://ai.api.nvidia.com/v1/gr/meta/llama-3.2-90b-vision-instruct/chat/completions"
 
 def upload_image_to_imgbb(image_path):
-    """Uploads an image to imgbb and returns the URL."""
+    """Uploads an image to ImgBB and returns the URL."""
     url = f"https://api.imgbb.com/1/upload?key={imagebb_api_key}"
     with open(image_path, "rb") as image_file:
-        files = {"image": image_file.read()}
-        response = requests.post(url, files=files)
-        if response.status_code == 200:
-            return response.json()["data"]["url"]
-        else:
-            raise ValueError(f"Image upload failed: {response.json()}")
+        response = requests.post(url, files={"image": image_file})
+    if response.status_code == 200:
+        return response.json()["data"]["url"]
+    else:
+        raise ValueError(f"Image upload failed: {response.json()}")
 
 def analyze_image(image, instruction):
-    """Analyzes the image using Sambanova's Llama 3.2 Vision Instruct based on the provided instruction."""
+    """Analyzes the image using NVIDIA’s Llama 3.2 Vision Instruct model based on the provided instruction."""
     try:
-        # Save the uploaded image locally
+        # Save image locally
         image_path = "uploaded_image.png"
         image.save(image_path)
 
-        # Upload the image to imgbb
+        # Upload image to ImgBB and get the URL
         image_url = upload_image_to_imgbb(image_path)
 
-        # Debug: Log the uploaded image URL
-        print(f"Uploaded Image URL: {image_url}")
-
-        # Call the Sambanova API to analyze the image
-        completion = openai.ChatCompletion.create(
-            model="Llama-3.2-90B-Vision-Instruct",
-            messages=[
+        # NVIDIA API Request
+        headers = {
+            "Authorization": f"Bearer {nvidia_api_key}",
+            "Accept": "application/json"
+        }
+        payload = {
+            "model": "meta/llama-3.2-90b-vision-instruct",
+            "messages": [
                 {
                     "role": "user",
                     "content": [
@@ -48,18 +46,23 @@ def analyze_image(image, instruction):
                     ]
                 }
             ],
-            temperature=0.1,
-            top_p=0.1,
-        )
-        print("API Response:", response)
-        # Extract the content from the first choice
-        analysis = response["choices"][0]["message"]["content"]
-        return analysis.strip()
-    except KeyError:
-        return "Error: Response format from the API is unexpected."
+            "max_tokens": 512,
+            "temperature": 0.1,
+            "top_p": 0.1
+        }
+
+        response = requests.post(invoke_url, headers=headers, json=payload)
+        response_data = response.json()
+
+        # Extract the response
+        if "choices" in response_data:
+            return response_data["choices"][0]["message"]["content"]
+        else:
+            return f"Error in response: {response_data}"
+
     except Exception as e:
-        return f"Error:"
-        
+        return f"Error: {str(e)}"
+
 # Gradio interface
 iface = gr.Interface(
     fn=analyze_image,
@@ -70,9 +73,8 @@ iface = gr.Interface(
     outputs="text",
     title="Deep Image Analysis using LLM",
     description=(
-        "Upload an image and provide instructions to analyze the image using Llama 3.2 90B Vision. "
-        "You can upload and analyze as many pictures as possible with no restrictions. "
-        "However, it's one at a time."
+        "Upload an image and provide instructions to analyze it using Llama 3.2 90B Vision. "
+        "You can upload and analyze multiple pictures, but one at a time."
     ),
     live=False,
 )