change routes.py

Dockerfile

@@ -1,3 +1,4 @@
+# syntax=docker/dockerfile:1.4
 FROM python:3.11-slim
 
 # install system deps…
@@ -24,8 +25,7 @@ COPY . .
 ENV PORT=7860 \
     XDG_CACHE_HOME=/data/.cache \
     TRANSFORMERS_CACHE=/data/.cache/huggingface \
-    HF_HOME=/data/.cache/huggingface \
-    EASYOCR_MODEL_STORAGE=/data/.EasyOCR
+    HF_HOME=/data/.cache/huggingface
 
 EXPOSE ${PORT}
 

app/routes.py

@@ -1,7 +1,6 @@
 from flask import Blueprint, request, jsonify
 from werkzeug.utils import secure_filename
 import os
-import easyocr
 import pytesseract  # Ensure this is imported
 import base64
 from huggingface_hub import InferenceApi
@@ -20,8 +19,6 @@ from werkzeug.utils import secure_filename
 # Initialize Flask Blueprint
 bp = Blueprint('main', __name__)
 
-model_dir = os.getenv('EASYOCR_MODEL_STORAGE', None)
-
 # ── OCR via HF Inference API ─────────────────────────────────────────────────
 # We're using Microsoft's TrOCR for printed text:
 
@@ -121,11 +118,20 @@ def analyze_image():
             #     )
                 img = Image.open(path).convert("RGB")
 
-                extracted = ocr_pipe(img)
+                # run OCR pipeline, which returns a list of dicts
+                ocr_results = ocr_pipe(img)
+                # extract the generated text from the first result
+                extracted = ""
+                if isinstance(ocr_results, list) and len(ocr_results) > 0 and "generated_text" in ocr_results[0]:
+                    extracted = ocr_results[0]["generated_text"].strip()
+                else:
+                    extracted = str(ocr_results)
 
-                print(extracted)
+                print("OCR extracted text:", extracted)
 
+                # now analyze the extracted string
                 analysis = analyze_text_internal(extracted)
+
                 tags     = generate_tags(extracted)
                 return jsonify({
                     "extracted_text": extracted,

requirements.txt

@@ -32,7 +32,6 @@ openai-whisper==20231106          # pins triton 2.0.0 (now satisfied)
 
 ###############################################################################
 # 6.  OCR / CV
-easyocr==1.7.2
 opencv-python-headless==4.11.0.86
 pytesseract==0.3.13
 scikit-image==0.25.1