Update app.py

app.py

@@ -9,9 +9,6 @@ client = InferenceClient(model="mistralai/Mistral-7B-Instruct-v0.3")
 # Load model Named Entity Recognition (NER)
 ner_pipeline = pipeline("ner", model="d4data/biomedical-ner-all")
 
-# Entitas yang dianggap penting
-important_entities = {"Disease_disorder", "Sign_symptom", "Diagnostic_procedure", "Therapeutic_procedure", "Medication", "Dosage"}
-
 # Fungsi untuk ekstraksi entitas medis dari teks
 def extract_entities(text):
     entities = ner_pipeline(text)
@@ -37,10 +34,8 @@ def extract_entities(text):
     if current_word and current_entity:  # Tambahkan kata terakhir yang sudah digabung
         merged_entities.append({"word": current_word, "entity": current_entity})
     
-    # Filter hanya entitas yang relevan
-    filtered_entities = [ent for ent in merged_entities if ent["entity"] in important_entities]
     
-    return filtered_entities
+    return merged_entities
 
 # Fungsi untuk highlight teks dan menampilkan daftar entitas yang dikenali
 def highlight_text(text, entities):
@@ -74,7 +69,7 @@ def chat_with_ner(message, history):
         prompt = f"This text contains medical terms: {', '.join(recognized_entities)}. Please explain briefly."
     else:
         prompt = message  
-    show_to_history = f"Medical Object Recognized : {', '.join(recognized_entities)}. Here are the information about the recognized medical object."
+    show_to_history = f"Medical Object Recognized : {', '.join(recognized_entities)}. Here are the informations about the recognized medical object."
     response = client.text_generation(prompt, max_new_tokens=100)  # Gunakan text_generation()
     highlighted_message = highlight_text(message, entities)