Update app.py

app.py

@@ -84,50 +84,29 @@ def process_speech(input_language, audio_input):
 
 
 
-def process_image(image) : 
+def process_image(image):
+    # Save the image to a file
     img_name = f"{np.random.randint(0, 100)}.jpg"
     PIL.Image.fromarray(image.astype('uint8'), 'RGB').save(img_name)
-    image = open(img_name, "rb").read()
-    base64_image = base64_image = base64.b64encode(image).decode('utf-8')
-    openai_api_key = os.getenv('OPENAI_API_KEY')
-    # oai_org = os.getenv('OAI_ORG')
-
-    headers = {
-        "Content-Type": "application/json",
-        "Authorization": f"Bearer {openai_api_key}"
-    }
 
+    # Prepare the payload for the Gradio client
     payload = {
-        "model": "gpt-4-vision-preview",
-        "messages": [
-        {
-            "role": "user",
-            "content": [
-            {
-                "type": "text",
-                "text": "You are clinical consultant discussion training cases with students at TonicUniversity. Assess and describe the photo in minute detail. Explain why each area or item in the photograph would be inappropriate to describe if required. Pay attention to anatomy, symptoms and remedies. Propose a course of action based on your assessment. Exclude any other commentary:"
-            },
-            {
-                "type": "image_url",
-                "image_url": {
-                "url": f"data:image/jpeg;base64,{base64_image}"
-                }
-            }
-            ]
-        }
+        "data": [
+            img_name,  # File path of the saved image
+            "Hello!!"  # Example text, replace with relevant text if needed
         ],
-        "max_tokens": 1200
+        "api_name": "/http_bot"
     }
 
-    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
+    # Initialize the Gradio client
+    client = Client("https://teamtonic-otterhd-demo.hf.space/--replicas/rcng4/")
 
-    try :
-        out = response.json()
-        out = out["choices"][0]["message"]["content"]
-
-        return out
-    except Exception as e :
-        return f"{e}"
+    try:
+        # Send the request to the Gradio client
+        result = client.predict(payload)
+        return result
+    except Exception as e:
+        return f"Error: {e}"
 
 
 def query_vectara(text):