added app file

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.12
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,135 @@
+from io import BytesIO
+import json, re
+import os
+import base64
+import requests
+
+from fastapi import FastAPI, UploadFile, File
+from fastapi.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+from PIL import Image
+
+app = FastAPI(title="LLaMA 3.2 Vision Menu Extractor")
+
+# Enable CORS for frontend interaction (Gradio/Spaces UI)
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+API_URL = "https://router.huggingface.co/v1/chat/completions"
+HEADERS = {
+    "Authorization": f"Bearer {os.environ['access_token']}",
+    "Content-Type": "application/json"
+}
+
+PROMPT = """
+You are an AI assistant. Extract item names and their prices from the following image.
+
+Your task is to extract item names and their corresponding prices from the image provided.
+
+Return ONLY a clean JSON array in this format:
+[
+  {"item": "<item_name>", "price": "<price>"},
+  ...
+]
+
+⚠️ Guidelines:
+- Do not include any explanation or text before/after the JSON.
+- Include only entries that have both item and price.
+- Preserve original spellings and formatting from the image.
+- If prices are written in ₹, Rs., or INR, keep the symbol as is.
+- Handle both packaged labels (like chips or snacks) and printed/handwritten menus.
+- If there are duplicates or unclear text, skip them.
+
+Only return the final JSON output, No explanation.
+
+Make sure each entry has both item and price, and preserve the original spelling.
+"""
+
+def resize_image(image: Image.Image, max_size=(1024, 1024)) -> Image.Image:
+    image.thumbnail(max_size)
+    return image
+
+
+async def encode_image_to_data_url(file: UploadFile=File(...)) -> str:
+
+    image = Image.open(BytesIO(await file.read()))
+
+    # Preprocessing
+    image = resize_image(image)
+
+    # Compress and convert to bytes
+    buffered = BytesIO()
+
+    image.save(buffered, quality=80, format="JPEG")
+    buffered.seek(0)
+    image_bytes = buffered.getvalue()
+    
+    # Encode to base64
+    base64_image = base64.b64encode(image_bytes).decode("utf-8")
+    mime_type = file.content_type
+
+    return f"data:{mime_type};base64,{base64_image}"
+    
+@app.get("/")
+def root():
+    return {"message": "GLM 4.1V API for menu extraction is running."}
+
+@app.post("/extract/")
+async def extract(file: UploadFile = File(...)):
+    try:
+        # Convert uploaded image to base64 URL format
+        image_data_url = await encode_image_to_data_url(file)
+
+        # Create chat-style payload
+        payload = {
+            # "model": "zai-org/GLM-4.1V-9B-Thinking:novita",
+            # "model": "meta-llama/Llama-3.2-11B-Vision-Instruct:together",
+            # "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct:novita",
+            # "model": "llama3.2-vision:11b",
+            "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct:novita",
+            "messages": [
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": PROMPT
+                        },
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": image_data_url
+                            }
+                        }
+                    ]
+                }
+            ]
+        }
+
+        # Send POST request to Hugging Face Chat Completion endpoint
+        response = requests.post(API_URL, headers=HEADERS, json=payload)
+
+        result = response.json()
+        print("result :", result)
+        reply = result["choices"][0]["message"]["content"]
+
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=400)
+
+    match = re.search(r"\[\s*{.*?}\s*\]", reply, re.DOTALL)
+    if match:
+        json_str = match.group(0)
+        try:
+            items = json.loads(json_str)
+            return JSONResponse(content={"menu_items": items})
+        except json.JSONDecodeError:
+            return JSONResponse(status_code=500, content={"error": "Failed to parse JSON", "raw": json_str})
+    else:
+        return JSONResponse(status_code=404,
+                            content={"error": "No JSON array found in response", "model_response": reply})
+        

requirements.txt

@@ -0,0 +1,121 @@
+accelerate==1.9.0
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.15
+aiosignal==1.4.0
+annotated-types==0.7.0
+anyio==4.9.0
+async-timeout==4.0.3
+attrs==25.3.0
+Brotli==1.1.0
+certifi==2025.7.14
+charset-normalizer==3.4.2
+click==8.2.1
+dataclasses-json==0.6.7
+dnspython==2.7.0
+email_validator==2.2.0
+exceptiongroup==1.3.0
+fastapi==0.116.1
+fastapi-cli==0.0.8
+fastapi-cloud-cli==0.1.5
+ffmpy==0.6.1
+filelock==3.18.0
+frozenlist==1.7.0
+fsspec==2025.7.0
+gradio==5.39.0
+gradio_client==1.11.0
+greenlet==3.2.3
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.1.5
+httpcore==1.0.9
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.1
+huggingface-hub==0.34.3
+idna==3.10
+Jinja2==3.1.6
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.27
+langchain-community==0.3.27
+langchain-core==0.3.72
+langchain-ollama==0.3.6
+langchain-text-splitters==0.3.9
+langsmith==0.4.9
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.6.3
+mypy_extensions==1.1.0
+networkx==3.4.2
+numpy==2.2.6
+nvidia-cublas-cu12==12.6.4.1
+nvidia-cuda-cupti-cu12==12.6.80
+nvidia-cuda-nvrtc-cu12==12.6.77
+nvidia-cuda-runtime-cu12==12.6.77
+nvidia-cudnn-cu12==9.5.1.17
+nvidia-cufft-cu12==11.3.0.4
+nvidia-cufile-cu12==1.11.1.6
+nvidia-curand-cu12==10.3.7.77
+nvidia-cusolver-cu12==11.7.1.2
+nvidia-cusparse-cu12==12.5.4.2
+nvidia-cusparselt-cu12==0.6.3
+nvidia-nccl-cu12==2.26.2
+nvidia-nvjitlink-cu12==12.6.85
+nvidia-nvtx-cu12==12.6.77
+ollama==0.5.1
+orjson==3.11.1
+packaging==25.0
+pandas==2.3.1
+pillow==11.3.0
+propcache==0.3.2
+psutil==7.0.0
+pydantic==2.11.7
+pydantic-settings==2.10.1
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.1
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+regex==2025.7.34
+requests==2.32.4
+requests-toolbelt==1.0.0
+rich==14.1.0
+rich-toolkit==0.14.9
+rignore==0.6.4
+ruff==0.12.7
+safehttpx==0.1.6
+safetensors==0.5.3
+semantic-version==2.10.0
+sentry-sdk==2.34.1
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+SQLAlchemy==2.0.42
+starlette==0.47.2
+sympy==1.14.0
+tenacity==9.1.2
+tokenizers==0.21.4
+tomlkit==0.13.3
+torch==2.7.1
+tqdm==4.67.1
+transformers==4.55.0
+triton==3.3.1
+typer==0.16.0
+typing-inspect==0.9.0
+typing-inspection==0.4.1
+typing_extensions==4.14.1
+tzdata==2025.2
+urllib3==2.5.0
+uvicorn==0.35.0
+uvloop==0.21.0
+watchfiles==1.1.0
+websockets==15.0.1
+yarl==1.20.1
+zstandard==0.23.0