Update pipeline.py

pipeline.py

@@ -1,33 +1,36 @@
 import numpy as np
+import tensorflow as tf
 from tensorflow.keras.preprocessing.sequence import pad_sequences
 from tensorflow.keras.preprocessing.text import tokenizer_from_json
-import tensorflow as tf
 import json
 import os
 
-class ToxicPipeline:
-    def __init__(self, model, tokenizer_path="tokenizer.json", max_len=150, label_map=None):
-        self.model = model
-        with open(tokenizer_path, "r", encoding="utf-8") as f:
+class Pipeline:
+    def __init__(self):
+        # Load tokenizer
+        with open("tokenizer.json", "r", encoding="utf-8") as f:
             tokenizer_json = f.read()
             self.tokenizer = tokenizer_from_json(tokenizer_json)
-        self.max_len = max_len
-        self.label_map = label_map
+        self.max_len = 150
+
+        # Load model (SavedModel format)
+        self.model = tf.keras.models.load_model(".")
 
-    def __call__(self, text, image_desc):
+        # Optionally, load label map if you have one
+        self.label_map = None
+        if os.path.exists("label_map.json"):
+            with open("label_map.json", "r", encoding="utf-8") as f:
+                self.label_map = json.load(f)
+
+    def __call__(self, inputs):
+        # Accepts a dict with keys 'text' and 'image_desc'
+        text = inputs.get("text", "")
+        image_desc = inputs.get("image_desc", "")
         input_text = text + " " + image_desc
         seq = self.tokenizer.texts_to_sequences([input_text])
         padded = pad_sequences(seq, maxlen=self.max_len, padding='post', truncating='post')
         pred_probs = self.model.predict(padded)
         pred_label = int(np.argmax(pred_probs, axis=1)[0])
         if self.label_map:
-            return self.label_map.get(pred_label, pred_label)
-        return pred_label
-
-# Example usage (for README):
-# from huggingface_hub import from_pretrained_keras
-# from pipeline import ToxicPipeline
-# model = from_pretrained_keras("NightPrince/Toxic_Classification")
-# pipeline = ToxicPipeline(model, tokenizer_path="data/tokenizer.json", label_map={0: "toxic", 1: "not toxic", ...})
-# result = pipeline("This is a dangerous post", "Knife shown in the image")
-# print(result)
+            return {"label": self.label_map.get(str(pred_label), pred_label), "score": float(np.max(pred_probs))}
+        return {"label": pred_label, "score": float(np.max(pred_probs))}