Upload 2 files

handler.py

@@ -1,20 +1,14 @@
 from typing import  Dict, List, Any
-from ctransformers import AutoModelForCausalLM
-
+import base64
+from PIL import Image
+from io import BytesIO
+import numpy as np
+from paddleocr import PaddleOCR, draw_ocr
 
 class EndpointHandler():
     def __init__(self, path=""):
-        model_id = path
-        model_file="mistralllux1000-7b-v5.gguf.q5_k_m.bin"
-        config = {'context_length' : 2048,'max_new_tokens': 656, 'repetition_penalty': 1.1,'temperature': 0.1, 'stream': True}
-        llm = AutoModelForCausalLM.from_pretrained(
-                                           model_id,
-                                           model_file=model_file,
-                                           model_type="mistral",
-                                           gpu_layers=50,#50 #110
-                                           **config
-                                           )
-        self.pipeline = llm
+        
+        self.pipeline = PaddleOCR(lang="en",ocr_version="PP-OCRv4",show_log = False,use_gpu=True)
 
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
@@ -27,13 +21,15 @@ class EndpointHandler():
                 - "label": A string representing what the label/class is. There can be multiple labels.
                 - "score": A score between 0 and 1 describing how confident the model is for this label/class.
         """
+        
         inputs = data.pop("inputs", data)
-        parameters = data.pop("parameters", None)
-
+        #parameters = data.pop("parameters", None)
+        
+        receipt_image = Image.open(BytesIO(base64.b64decode(inputs)))
+        receipt_image_array = np.array(receipt_image.convert('RGB'))
+        result = self.pipeline.ocr(receipt_image_array,cls=True)
+        txts = [line[1][0] for line in result[0]]
         # pass inputs with all kwargs in data
-        if parameters is not None:
-            prediction = self.pipeline(inputs, stream=False)
-        else:
-            prediction = self.pipeline(inputs, stream=False)
+        extract = "".join(txts)
         # postprocess the prediction
-        return prediction
+        return extract

requirements.txt

@@ -1 +1,4 @@
-ctransformers --no-binary ctransformers
+paddlepaddle-gpu -i https://pypi.tuna.tsinghua.edu.cn/simple
+"paddleocr>=2.0.1"
+pillow 
+numpy