Upload 5 files

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,6 @@
+**/__pycache__/
+.env
+src/model/detect.onnx
+src/model/segment.pt
+.venv
+# src/model/segment.onnx

Dockerfile

@@ -0,0 +1,17 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+RUN apt-get update && apt-get install -y tesseract-ocr && rm -rf /var/lib/apt/lists/*
+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 +1,110 @@
+from dotenv import load_dotenv
+from src.inference.segment_inference import inference
+from src.utils.utils_segment import extract_text, draw_bounding_boxes
+from fastapi import FastAPI, UploadFile, status, Form, File
+from fastapi.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+import cv2
+import numpy as np
+from src.config.llm import llm
+from src.prompt.promt import format_prompt
+from langchain_core.output_parsers import JsonOutputParser
+import uvicorn
+from io import BytesIO
+import base64
+from pydantic import Field, BaseModel
+from concurrent.futures import ThreadPoolExecutor
+import asyncio
+import os
+import functools
+import threading
+
+load_dotenv()
+app = FastAPI(docs_url="/")
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+model_path = "./src/model/segment.onnx"
+executor = ThreadPoolExecutor(max_workers=int(os.cpu_count() + 4))
+
+
+def run_in_thread(func, *args, **kwargs):
+    loop = asyncio.get_event_loop()
+    func_name = func.__name__
+
+    # Function to wrap the original function to print the thread ID
+    def wrapper(*args, **kwargs):
+        thread_id = threading.get_ident()
+        print(f"[Running function '{func_name}' in thread ID: {thread_id}]")
+        return func(*args, **kwargs)
+
+    # Run the wrapped function in the executor
+    return loop.run_in_executor(executor, functools.partial(wrapper, *args, **kwargs))
+
+
+def predict_func(threshold_confidence, threshold_iou, image):
+
+    image = np.frombuffer(image, np.uint8)
+    image = cv2.imdecode(image, cv2.IMREAD_COLOR)
+    outputs = inference(
+        image,
+        model_path=model_path,
+        threshold_confidence=threshold_confidence,
+        threshold_iou=threshold_iou,
+    )
+    text = extract_text(outputs=outputs, image_origin=image)
+    image = draw_bounding_boxes(image, outputs)
+    buffer = BytesIO()
+    image.save(buffer, format="JPEG")
+    buffer.seek(0)
+
+    image_base64 = base64.b64encode(buffer.getvalue()).decode("utf-8")
+    response = {"outputs": text, "image_base64": image_base64}
+    return response
+
+
+@app.post("/inference", status_code=status.HTTP_200_OK)
+async def predict(
+    threshold_confidence: float = Form(default=0.7, ge=0, le=1),
+    threshold_iou: float = Form(default=0.7, ge=0, le=1),
+    image: UploadFile = File(...),
+):
+    try:
+        image = await image.read()
+
+        response = await run_in_thread(
+            predict_func, threshold_confidence, threshold_iou, image
+        )
+        return JSONResponse(content=response, status_code=status.HTTP_200_OK)
+    except Exception as e:
+        response = {"error": str(e)}
+        return JSONResponse(content=response, status_code=status.HTTP_400_BAD_REQUEST)
+
+
+class LLMRequest(BaseModel):
+    text: str = Field(..., title="Text to generate completion")
+
+
+def call_llm(data):
+    input = format_prompt.format(input=data)
+    response = llm.invoke(input)
+    response = JsonOutputParser().parse(response)
+    return response
+
+
+@app.post("/llm", status_code=status.HTTP_200_OK)
+async def llm_predict(data: LLMRequest):
+    try:
+        response = await run_in_thread(call_llm, data.text)
+        return JSONResponse(content=response, status_code=status.HTTP_200_OK)
+    except Exception as e:
+        response = {"error": str(e)}
+        return JSONResponse(content=response, status_code=status.HTTP_400_BAD_REQUEST)
+
+
+if __name__ == "__main__":
+    uvicorn.run("app:app", host="localhost", port=8080, reload=True)

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+python-dotenv
+pytesseract
+opencv-python
+langchain-google-genai
+uvicorn
+python-multipart
+asycnio