fix arm image problem

.dockerignore

@@ -0,0 +1,26 @@
+# Ignore Python cache
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+
+# Ignore virtual environments
+.venv
+
+# Ignore development tools
+*.log
+*.swp
+.DS_Store
+
+# Ignore Git
+.git
+.gitignore
+
+# Ignore Docker files not needed in build context
+docker-compose.yml
+docker-compose.override.yml
+
+# Ignore tests and docs if not needed
+tests/
+docs/
+uv.look

Dockerfile

@@ -1,12 +1,23 @@
-FROM python:3.10-slim
+FROM --platform=linux/amd64 python:3.11-slim
+RUN apt-get update && apt-get install -y \
+    make \
+    curl \
+    ca-certificates \
+    build-essential \
+    cmake \
+    nano\
+    pkg-config \
+    libopenblas-dev \
+    && rm -rf /var/lib/apt/lists/*
 
-RUN apt-get update && apt-get install -y build-essential cmake
-
-COPY requirements.txt .
+RUN curl -Ls https://astral.sh/uv/install.sh | bash
+ENV PATH="/root/.cargo/bin:/root/.local/bin:${PATH}"
+WORKDIR /app
+COPY . .
+RUN which uv || echo "uv not found"
 
-RUN pip install --upgrade pip && pip install -r requirements.txt
+ENV CMAKE_ARGS="-DGGML_USE_OPENMP=ON -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS"
 
-COPY . /app
-WORKDIR /app
+RUN uv add llama-cpp-python 
 
-CMD ["python", "app.py"]
+CMD ["uv", "run", "app.py"]

app.py

@@ -97,4 +97,4 @@ with gr.Blocks() as demo:
         show_progress=True  # 🛠️ Important when using async fn
     )
 
-demo.launch()
+demo.launch(share=True)

llms/qwen.py

@@ -1,9 +1,4 @@
 from huggingface_hub import hf_hub_download
-from langchain_huggingface import HuggingFacePipeline
-from transformers import pipeline
-from langchain_community.llms import LlamaCpp
-from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler
-from langchain_core.runnables import RunnableLambda
 from llama_cpp import Llama
 from llama_cpp.llama_chat_format import Qwen25VLChatHandler
 
@@ -28,26 +23,4 @@ qwen_model = Llama(
     use_mlock=True,           # Facultatif mais recommandé si tu veux garder en RAM
     offload_kv=True,          # Offload KV cache sur le GPU (important)
     verbose=True , 
-    
 )
-
-# messages = [
-# 		{
-# 			"role": "user",
-# 			"content": [
-# 				{
-# 					"type": "text",
-# 					"text": "Describe this image in one sentence."
-# 				},
-# 				{
-# 					"type": "image_url",
-# 					"image_url": {
-# 						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
-# 					}
-# 				}
-# 			]
-# 		}
-# 	]
-
-
-# qwen_model = RunnableLambda(lambda messages: llm.create_chat_completion(messages=messages))

main.py

@@ -1,27 +1,23 @@
-from llama_cpp import Llama
+import time
 
-llm = Llama.from_pretrained(
-	repo_id="unsloth/Qwen2.5-VL-3B-Instruct-GGUF",
-	filename="Qwen2.5-VL-3B-Instruct-BF16.gguf",
-)
+def main():
+    try:
+        # Try to import and run your actual logic
+        from services.analyse_image import ErrorResponse, analyze_image
+        # You can also call a Flask/Gradio/FastAPI app here if needed
+        print("Application started successfully.")
+        # Keep running (e.g., start a web server or background process)
+        while True:
+            time.sleep(60)
+    except ImportError as e:
+        print(f"[ImportError] Could not load some modules: {e}")
+    except Exception as e:
+        print(f"[Startup Error] {e}")
+    finally:
+        # Keep the container alive even if errors happen
+        print("Container is running in idle mode for debugging.")
+        while True:
+            time.sleep(3600)
 
-
-llm.create_chat_completion(
-	messages = [
-		{
-			"role": "user",
-			"content": [
-				{
-					"type": "text",
-					"text": "Describe this image in one sentence."
-				},
-				{
-					"type": "image_url",
-					"image_url": {
-						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
-					}
-				}
-			]
-		}
-	]
-)
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -0,0 +1,26 @@
+[project]
+name = "object-analyser"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "dotenv>=0.9.9",
+    "gradio>=5.38.1",
+    "huggingface-hub>=0.34.1",
+    "jinja2>=3.1.6",
+    "langchain>=0.3.27",
+    "langchain-community>=0.3.27",
+    "langchain-huggingface>=0.3.1",
+    "langchain-ollama>=0.3.6",
+    "langchainhub>=0.1.21",
+    "langgraph>=0.5.4",
+    "pillow>=11.3.0",
+    "python-multipart>=0.0.20",
+    "text-generation>=0.7.0",
+    "torch>=2.7.1",
+    "torchvision>=0.22.1",
+    "transformers>=4.53.3",
+]
+
+

requirements.txt

@@ -1,16 +0,0 @@
-dotenv>=0.9.9
-gradio>=5.38.1
-huggingface-hub>=0.34.1
-jinja2>=3.1.6
-langchain>=0.3.27
-langchain-community>=0.3.27
-langchain-huggingface>=0.3.1
-langchain-ollama>=0.3.6
-langchainhub>=0.1.21
-langgraph>=0.5.4
-llama-cpp-python>=0.3.14
-python-multipart>=0.0.20
-text-generation>=0.7.0
-torch>=2.7.1
-torchvision>=0.22.1
-transformers>=4.53.3