Upload pipeline.py with huggingface_hub

pipeline.py

@@ -18,7 +18,8 @@ class ThoughtCompletionPipeline(Pipeline):
     def ends_with_incomplete_word(self, text):
         """Check if text ends with words that indicate incomplete thought"""
         text = text.strip().lower()
-        text = re.sub(r'[.,!?;]$', '', text)
+        # Remove trailing punctuation
+        text = re.sub(r'[.,!?;:]$', '', text)
         words = text.split()
         
         if not words:
@@ -36,35 +37,29 @@ class ThoughtCompletionPipeline(Pipeline):
         
         ai_utterance = parts[0].strip()
         cx_utterance = parts[1].strip()
+        cx_lower = cx_utterance.lower().strip()
         
-        # Check if customer utterance ends with incomplete word
-        if self.ends_with_incomplete_word(cx_utterance):
-            return [{'label': 'INCOMPLETE', 'score': 0.95}], 'rule:incomplete_ending'
-        
-        cx_lower = cx_utterance.lower()
+        # Remove punctuation for exact matching
+        cx_lower_clean = re.sub(r'[.,!?;:]$', '', cx_lower)
         
-        # Complete thought indicators
-        complete_phrases = [
-            "that's all", "nothing else", "i'm done", "that's it", 
-            "no thanks", "no thank you", "yes", "yes please",
-            "perfect", "great", "sounds good", "that's everything"
+        # RULE 1: Check for EXACT MATCH complete thoughts (full sentence match)
+        complete_full_sentences = [
+            "that's all", "that's it", "nothing else", "i'm done", "i'm good",
+            "no thanks", "no thank you", "yes please", "yes", "no",
+            "perfect", "great", "sounds good", "that's everything",
+            "all set", "done", "finished", "that is all", "that is it",
+            "nope", "yep", "yeah"
         ]
         
-        for phrase in complete_phrases:
-            if phrase in cx_lower:
-                return [{'label': 'COMPLETE', 'score': 0.95}], f'rule:contains_{phrase}'
+        for phrase in complete_full_sentences:
+            if cx_lower_clean == phrase:  # EXACT MATCH ONLY
+                return [{'label': 'COMPLETE', 'score': 0.95}], f'rule:exact_match_{phrase.replace(" ", "_")}'
         
-        # Incomplete thought indicators
-        incomplete_phrases = [
-            "let me add", "actually", "wait", "i also need",
-            "can i get", "i want", "i'd like", "i need",
-            "hold on", "one more", "oh and"
-        ]
-        
-        for phrase in incomplete_phrases:
-            if phrase in cx_lower:
-                return [{'label': 'INCOMPLETE', 'score': 0.95}], f'rule:contains_{phrase}'
+        # RULE 2: Check if sentence ENDS with incomplete word
+        if self.ends_with_incomplete_word(cx_utterance):
+            return [{'label': 'INCOMPLETE', 'score': 0.95}], 'rule:ends_with_incomplete_word'
         
+        # No rule applies - use the neural model
         return None, None
     
     def preprocess(self, inputs):