updated the output format

README.md

@@ -37,9 +37,10 @@ Because **MarkOne** operates as an NLI cross-encoder, it evaluates candidate cho
 ### Zero-Shot NLI Classification (Python)
 
 ```python
+import json
 import torch
 import torch.nn.functional as F
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
 # Load model and tokenizer
 MODEL_ID = "ChandruK/MarkOne"
@@ -50,7 +51,7 @@ model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID).to(device)
 model.eval()
 
 # Entailment label index (Index 2 for standard DeBERTa MNLI architecture)
-ENTAILMENT_IDX = 2  
+ENTAILMENT_IDX = 2
 
 # 1. Define Candidate Labels and Hypothesis Template
 CANDIDATE_LABELS = [
@@ -58,7 +59,8 @@ CANDIDATE_LABELS = [
     "an Excel spreadsheet creation request",
     "a PowerPoint presentation deck creation request",
     "a PDF document analysis or extraction query",
-    "general chitchat or off-topic conversation"
+    "general chitchat or off-topic conversation",
+    "a Question answer related",
 ]
 HYPOTHESIS_TEMPLATE = "This user prompt is {}."
 
@@ -75,7 +77,7 @@ inputs = tokenizer(
     text_pair=hypotheses,
     padding=True,
     truncation=True,
-    return_tensors="pt"
+    return_tensors="pt",
 ).to(device)
 
 # 5. Model Inference
@@ -83,7 +85,7 @@ with torch.no_grad():
     outputs = model(**inputs)
     # Extract Entailment logits vector across all dynamic candidates
     entailment_logits = outputs.logits[:, ENTAILMENT_IDX]
-    
+
     # Softmax probability normalization
     probabilities = F.softmax(entailment_logits / 0.5, dim=-1)
     top_prob, top_idx = torch.max(probabilities, dim=-1)
@@ -91,5 +93,23 @@ with torch.no_grad():
 predicted_label = CANDIDATE_LABELS[top_idx.item()]
 confidence = top_prob.item() * 100
 
-print(f"💬 Prompt    : '{prompt}'")
-print(f"🏷️  Predicted : {predicted_label} ({confidence:.2f}% confidence)")
+# =====================================================================
+# MODIFICATION FOR JSON OUTPUT
+# =====================================================================
+
+# Build dictionary containing key details and all category probabilities
+label_scores = {
+    label: round(prob.item() * 100, 2)
+    for label, prob in zip(CANDIDATE_LABELS, probabilities)
+}
+
+output_json_data = {
+    "prompt": prompt,
+    "predicted_label": predicted_label,
+    "confidence": round(confidence, 2),
+    "all_scores": label_scores,
+}
+
+# Output as formatted JSON string
+json_output = json.dumps(output_json_data, indent=2)
+print(json_output)