🚀 Final Hindi OCR API with PDF + Image support

Dockerfile

@@ -7,12 +7,11 @@ RUN apt-get update && apt-get install -y \
     libglib2.0-0 \
     libsm6 \
     libxrender1 \
-    libxext6
+    libxext6 \
+ && apt-get clean
 
 WORKDIR /app
-
-COPY . .
-
-RUN pip install --no-cache-dir -r requirements.txt
+COPY . /app
+RUN pip install -r requirements.txt
 
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,10 +1,9 @@
 ---
 title: Hindi OCR API
-emoji: 📄
-colorFrom: yellow
-colorTo: red
+emoji: 📖
+colorFrom: blue
+colorTo: indigo
 sdk: docker
-sdk_version: "1.0"
 app_file: app.py
 pinned: false
 ---

app.py

@@ -1,30 +1,22 @@
 from fastapi import FastAPI, UploadFile, File
+from fastapi.responses import JSONResponse
 from pdf2image import convert_from_bytes
-import pytesseract
 from PIL import Image
+import pytesseract
 import io
 
 app = FastAPI()
 
-@app.get("/")
-def read_root():
-    return {"message": "✅ Hindi OCR API is live!"}
+def ocr_image(image: Image.Image) -> str:
+    return pytesseract.image_to_string(image, lang='hin+eng')
 
 @app.post("/ocr")
 async def extract_text(file: UploadFile = File(...)):
-    content = await file.read()
-
-    if file.filename.endswith(".pdf"):
-        images = convert_from_bytes(content, dpi=300)  # high quality
-        full_text = ""
-        for img in images:
-            text = pytesseract.image_to_string(img, lang='hin+eng')
-            full_text += text + "\n"
-        return {"text": full_text.strip()}
-
-    elif file.filename.endswith((".jpg", ".jpeg", ".png")):
-        image = Image.open(io.BytesIO(content))
-        text = pytesseract.image_to_string(image, lang='hin+eng')
-        return {"text": text.strip()}
-
-    return {"error": "❌ Unsupported file format"}
+    contents = await file.read()
+    if file.filename.lower().endswith(".pdf"):
+        images = convert_from_bytes(contents)
+        text = "\n".join([ocr_image(img) for img in images])
+    else:
+        image = Image.open(io.BytesIO(contents))
+        text = ocr_image(image)
+    return JSONResponse(content={"text": text})