Update app.py

app.py

@@ -103,94 +103,16 @@ def process_speech(input_language, audio_input):
     except Exception as e :
         return f"{e}"
 
-def decode_image(encoded_image: str) -> Image:
-    decoded_bytes = base64.b64decode(encoded_image.encode("utf-8"))
-    buffer = io.BytesIO(decoded_bytes)
-    image = Image.open(buffer)
-    return image
-
-
-def encode_image(image: Image.Image, format: str = "PNG") -> str:
-    with io.BytesIO() as buffer:
-        image.save(buffer, format=format)
-        encoded_image = base64.b64encode(buffer.getvalue()).decode("utf-8")
-    return encoded_image
-
-
-def get_conv_log_filename():
-    t = datetime.datetime.now()
-    name = os.path.join(LOGDIR, f"{t.year}-{t.month:02d}-{t.day:02d}-conv.json")
-    return name
-
-
-def get_conv_image_dir():
-    name = os.path.join(LOGDIR, "images")
-    os.makedirs(name, exist_ok=True)
-    return name
-
-
-def get_image_name(image, image_dir=None):
-    buffer = io.BytesIO()
-    image.save(buffer, format="PNG")
-    image_bytes = buffer.getvalue()
-    md5 = hashlib.md5(image_bytes).hexdigest()
-
-    if image_dir is not None:
-        image_name = os.path.join(image_dir, md5 + ".png")
-    else:
-        image_name = md5 + ".png"
-
-    return image_name
-
-def resize_image(image, max_size):
-    width, height = image.size
-    aspect_ratio = float(width) / float(height)
-
-    if width > height:
-        new_width = max_size
-        new_height = int(new_width / aspect_ratio)
-    else:
-        new_height = max_size
-        new_width = int(new_height * aspect_ratio)
-
-    resized_image = image.resize((new_width, new_height))
-    return resized_image
-
-
-
 def process_image(image_input):
     # Initialize the Gradio client with the URL of the Gradio server
     client = Client("https://adept-fuyu-8b-demo.hf.space/--replicas/pqjvl/")
 
-    # Check if the image input is a NumPy array
-    if isinstance(image_input, np.ndarray):
-        # Convert the NumPy array to a PIL Image
-        image = Image.fromarray(image_input)
-        # Save the PIL Image to a temporary file
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as tmp_file:
-            image.save(tmp_file.name)
-            image_path = tmp_file.name
-    elif isinstance(image_input, str):
-        try:
-            # Try to decode if it's a base64 string
-            image = decode_image(image_input)
-        except Exception:
-            # If decoding fails, assume it's a file path or a URL
-            image_path = image_input
-        else:
-            # If decoding succeeds, save the decoded image to a temporary file
-            with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as tmp_file:
-                image.save(tmp_file.name)
-                image_path = tmp_file.name
-    else:
-        # Assuming it's a PIL Image, save it to a temporary file
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as tmp_file:
-            image_input.save(tmp_file.name)
-            image_path = tmp_file.name
+    # Assuming image_input is a URL path to the image
+    image_path = image_input
 
     # Call the predict method of the client
     result = client.predict(
-        image_path,  # File path or URL of the image
+        image_path,  # URL of the image
         True,        # Additional parameter for the server (e.g., enable detailed captioning)
         fn_index=2   # Function index if the server has multiple functions
     )