heh

Dockerfile

@@ -13,6 +13,8 @@ WORKDIR /app
 
 COPY --chown=user ./requirements.txt requirements.txt
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
+RUN apt-get update && \
+    apt-get install -y tesseract-ocr tesseract-ocr-eng libtesseract-dev
 
 COPY --chown=user . .
 

app.py

@@ -619,13 +619,12 @@ async def download_and_process_file(url: str) -> Dict[str, Any]:
             from PIL import Image
             img = Image.open(io.BytesIO(content))
             text = pytesseract.image_to_string(img)
-            b64 = base64.b64encode(content).decode('utf-8')
-            logger.info(f"[FILE] Image OCR: {len(text)} chars")
             return {'type': 'image', 'ocr_text': text, 'size': img.size}
         except Exception as e:
-            logger.warning(f"[FILE] Image OCR error: {e}")
-            b64 = base64.b64encode(content[:1000]).decode('utf-8')
-            return {'type': 'image', 'error': str(e), 'base64_sample': b64}
+            logger.warning(f"[FILE] OCR unavailable, sending base64 sample instead")
+            b64 = base64.b64encode(content).decode('utf-8')
+            return {'type': 'image', 'base64_sample': b64, 'ocr_error': str(e)}
+
     
     elif ext in ['mp3', 'wav']:
         b64 = base64.b64encode(content[:5000]).decode('utf-8')