Update app.py

app.py

@@ -25,17 +25,12 @@ labels = [
     "education", "engineering", "entertainment", "environment",
     "fashion", "finance", "food commerce", "general",
     "gaming", "healthcare", "history", "html",
-    "information technology", "keywords", "legal",
+    "information technology", "IT", "keywords", "legal",
     "literature", "machine learning", "marketing", "medicine",
-    "music", "philosophy", "physics", "politics", "programming", "real estate", "retail", 
+    "music", "personal development", "philosophy", "physics",
+    "politics", "poetry", "programming", "real estate", "retail", 
     "robotics", "slang", "social media", "speech", "sports",
-    "technical", "theater", "tourism", "travel"
-]
-
-styles = [
-    "formal", "positive", "negative", "poetic", "polite", "subtle", "casual", "neutral",
-    "informal", "pompous", "sustained", "rude", "sustained",
-    "sophisticated", "playful", "serious", "friendly"
+    "sustained", "technical", "theater", "tourism", "travel"
 ]
 
 @lru_cache(maxsize=1)
@@ -63,11 +58,6 @@ def detect_context(input_text, top_n=3):
     # Compute cosine similarities
     similarities = cosine_similarity(input_embedding, label_embeddings)[0]
 
-    # Debugging: Print all labels and their similarity scores
-    print("Debug: Similarity scores for all labels:")
-    for label, score in zip(labels, similarities):
-        print(f"{label}: {score:.4f}")
-
     # Apply softmax to convert similarities to probabilities
     probabilities = softmax(similarities)
 
@@ -80,7 +70,8 @@ def detect_context(input_text, top_n=3):
     # Select the top N contexts
     top_contexts = label_probabilities[:top_n]
 
-    return top_contexts
+    # Return both the top N contexts and all context scores
+    return top_contexts, label_probabilities
 
 # Translation client
 translation_client = Client("Frenchizer/space_7")
@@ -94,21 +85,27 @@ def process_request(input_text):
     translation = translate_text(input_text)
 
     # Step 2: Detect context
-    context_results = detect_context(input_text)
+    top_contexts, all_contexts = detect_context(input_text)
 
-    # Step 3: Print the list of high-confidence contexts
-    print("Detected Contexts (Top 3):", context_results)
+    # Step 3: Print the list of high-confidence contexts and all context scores
+    print("Detected Contexts (Top 3):", top_contexts)
+    print("All Context Scores:")
+    for context, score in all_contexts:
+        print(f"- {context}: {score:.4f}")
 
     # Return the translation and contexts
-    return translation, context_results
+    return translation, top_contexts, all_contexts
 
 # Gradio interface
 def gradio_interface(input_text):
-    translation, contexts = process_request(input_text)
+    translation, top_contexts, all_contexts = process_request(input_text)
     # Format the output
     output = f"Translation: {translation}\n\nDetected Contexts (Top 3):\n"
-    for context, score in contexts:
+    for context, score in top_contexts:
         output += f"- {context} (confidence: {score:.4f})\n"
+    output += "\nAll Context Scores:\n"
+    for context, score in all_contexts:
+        output += f"- {context}: {score:.4f}\n"
     return output.strip()
 
 # Create the Gradio interface