Update app.py

app.py

@@ -8,6 +8,7 @@ import subprocess
 ### monkey patch 
 
 import llama_cpp._internals as internals
+from llama_cpp.llama_chat_format import Qwen3VLChatHandler
 
 
 # 2️⃣ Monkey patch BEFORE creating Llama()
@@ -235,6 +236,126 @@ llm_model_qwen= None
 
 
 
+_IMAGE_MIME_TYPES = {
+    # Most common formats
+    '.png':  'image/png',
+    '.jpg':  'image/jpeg',
+    '.jpeg': 'image/jpeg',
+    '.gif':  'image/gif',
+    '.webp': 'image/webp',
+
+    # Next-generation formats
+    '.avif': 'image/avif',
+    '.jp2':  'image/jp2',
+    '.j2k':  'image/jp2',
+    '.jpx':  'image/jp2',
+
+    # Legacy / Windows formats
+    '.bmp':  'image/bmp',
+    '.ico':  'image/x-icon',
+    '.pcx':  'image/x-pcx',
+    '.tga':  'image/x-tga',
+    '.icns': 'image/icns',
+
+    # Professional / Scientific imaging
+    '.tif':  'image/tiff',
+    '.tiff': 'image/tiff',
+    '.eps':  'application/postscript',
+    '.dds':  'image/vnd-ms.dds',
+    '.dib':  'image/dib',
+    '.sgi':  'image/sgi',
+
+    # Portable Map formats (PPM/PGM/PBM)
+    '.pbm':  'image/x-portable-bitmap',
+    '.pgm':  'image/x-portable-graymap',
+    '.ppm':  'image/x-portable-pixmap',
+
+    # Miscellaneous / Older formats
+    '.xbm':  'image/x-xbitmap',
+    '.mpo':  'image/mpo',
+    '.msp':  'image/msp',
+    '.im':   'image/x-pillow-im',
+    '.qoi':  'image/qoi',
+}
+
+def image_to_base64_data_uri(
+    file_path: str,
+    *,
+    fallback_mime: str = "application/octet-stream"
+) -> str:
+    """
+    Convert a local image file to a base64-encoded data URI with the correct MIME type.
+
+    Supports 20+ image formats (PNG, JPEG, WebP, AVIF, BMP, ICO, TIFF, etc.).
+
+    Args:
+        file_path: Path to the image file on disk.
+        fallback_mime: MIME type used when the file extension is unknown.
+
+    Returns:
+        A valid data URI string (e.g., data:image/webp;base64,...).
+
+    Raises:
+        FileNotFoundError: If the file does not exist.
+        OSError: If reading the file fails.
+    """
+    if not os.path.isfile(file_path):
+        raise FileNotFoundError(f"Image file not found: {file_path}")
+
+    extension = os.path.splitext(file_path)[1].lower()
+    mime_type = _IMAGE_MIME_TYPES.get(extension, fallback_mime)
+
+    if mime_type == fallback_mime:
+        print(f"Warning: Unknown extension '{extension}' for '{file_path}'. "
+              f"Using fallback MIME type: {fallback_mime}")
+
+    try:
+        with open(file_path, "rb") as img_file:
+            encoded_data = base64.b64encode(img_file.read()).decode("utf-8")
+    except OSError as e:
+        raise OSError(f"Failed to read image file '{file_path}': {e}") from e
+
+    return f"data:{mime_type};base64,{encoded_data}"
+
+
+
+######################   sample code ################################################
+# --- Main Logic for Image Processing ---
+
+# # 1. Create a list containing all image paths
+# image_paths = [
+#     r'./scene.jpeg',
+#     r'./cat.png',
+#     r'./network.webp',
+#     # Add more image paths here if needed
+# ]
+
+# # 2. Create an empty list to store the message objects (images and text)
+# images_messages = []
+
+
+
+# # 3. Loop through the image path list, convert each image to a Data URI,
+# #    and add it to the message list as an image_url object.
+# for path in image_paths:
+#     data_uri = image_to_base64_data_uri(path)
+#     images_messages.append({"type": "image_url", "image_url": {"url": data_uri}})
+
+# # 4. Add the final text prompt at the end of the list
+# images_messages.append({"type": "text", "text": "Describes the images."})
+
+# # 5. Use this list to build the chat_completion request
+# res = llm.create_chat_completion(
+#     messages=[
+#         {"role": "system", "content": "You are a highly accurate vision-language assistant. Provide detailed, precise, and well-structured image descriptions."},
+#         # The user's content is the list containing both images and text
+#         {"role": "user", "content": images_messages}
+#     ]
+# )
+
+# # Print the assistant's response
+# print(res["choices"][0]["message"]["content"])
+
 
 
 
@@ -267,11 +388,15 @@ def respond(
                 flash_attn=True,
                 n_gpu_layers=-1,
                 n_batch=2048,        # increase
-                n_ctx= 4098,          # reduce if you don’t need 8k
+                n_ctx= 8196,          # reduce if you don’t need 8k
                 n_threads=16,        # set to your CPU cores
                 use_mlock=True,
                 verbose=True,
-                chat_format="qwen"
+                chat_handler=Qwen3VLChatHandler(
+      clip_model_path=MMPROJ_PATH,
+      force_reasoning=True,
+      image_min_tokens=1024, # Note: Qwen-VL models require at minimum 1024 image tokens to function correctly on bbox grounding tasks
+    ),
             )
             
         x=llm_model_qwen.create_chat_completion(
@@ -293,7 +418,7 @@ def respond(
                 flash_attn=True,
                 n_gpu_layers=-1,
                 n_batch=2048,        # increase
-                n_ctx=4098,          # reduce if you don’t need 8k
+                n_ctx=8196,          # reduce if you don’t need 8k
                 n_threads=16,        # set to your CPU cores
                 use_mlock=True,
                 verbose=True,