Update README.md

README.md

@@ -17,7 +17,7 @@ The model uses special tokens to structure its output:
 
 ### Input Format
 The model expects input in the following format:
-<|title|>{ticket_title}<|title|><|description|>{ticket_description}<|description|>
+<|title|>{ticket_title}</|title|><|desc|>{ticket_description}</|desc|>
 
 
 ### Output Parsing
@@ -71,12 +71,37 @@ tokenizer = T5Tokenizer.from_pretrained(model_path)
 
 model.half()
 
+def create_model_input(short_description:str, description:str, max_chars = 1024) -> str:
+    # Convert the newlines to sentences
+    lines = description.split("\n")
+
+    for line in lines:
+        if line[-1] in [".", "!", "?"]:
+            line += " "
+        else:
+            line += ". "
+    description = "".join(lines)
+
+    # constrain the description to the specified length
+    total_chars = 0
+    sentences = []
+    for s in sent_tokenize(description):
+        total_chars += len(s)
+        if total_chars < max_chars:
+            sentences.append(s)
+        else:
+            break
+
+    description = " ".join(sentences)
+
+    return "<|title|>" + short_description + "</|title|><|desc|>" + description + "</|desc|>"
+
 def predict_ticket_summary(model:T5ForConditionalGeneration, title, description, max_length=128):
     """
     Generate system and topic predictions for a ticket using quantized model
     """
     # Format input text as used during training
-    input_text = f"<|title|>{title}<|title|><|description|>{description}<|description|>"
+    input_text = create_model_input(title, description, max_length)
     
     # Clear any previous tokenizer state and create fresh inputs
     tokenizer.pad_token = tokenizer.eos_token  # Ensure pad token is set