Update app.py

app.py

@@ -1,60 +1,52 @@
 import streamlit as st
-from transformers import pipeline
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
 import pandas as pd
-import re
 
-# Load the Question Answering model
+# Memuat model dan tokenizer IndoBERT
 @st.cache_resource
-def load_qa_pipeline():
-    """Load the QA pipeline with deepset/roberta-base-squad2 model."""
-    return pipeline("question-answering", model="deepset/roberta-base-squad2")
+def load_indobert_model():
+    model_name = "indobenchmark/indobert-base-p1"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForQuestionAnswering.from_pretrained(model_name)
+    return pipeline("question-answering", model=model, tokenizer=tokenizer)
 
-qa_pipeline = load_qa_pipeline()
+qa_pipeline = load_indobert_model()
 
-# Load SOP Dataset
+# Memuat dataset SOP
 @st.cache_data
 def load_sop_dataset():
-    """Load SOP dataset from CSV."""
-    return pd.read_csv("dataset.csv")  # Ensure this file is uploaded to your Hugging Face Space
+    return pd.read_csv("dataset.csv")
 
 dataset = load_sop_dataset()
 
-# Utility function to find the most relevant context
+# Fungsi untuk menemukan konteks terbaik
 def find_best_context(question, dataset):
-    """Find the single best context for a given question."""
     best_score = 0
     best_context = None
-
     for _, row in dataset.iterrows():
-        # Simple heuristic: Count the number of overlapping words
         overlap = len(set(question.lower().split()) & set(row["text"].lower().split()))
         if overlap > best_score:
             best_score = overlap
             best_context = row["text"]
-
     return best_context
 
-# Streamlit UI
-st.title("SOP Question Answering AI")
-st.markdown("Ask any question about Standard Operating Procedures:")
+# Antarmuka Streamlit
+st.title("Sistem Penjawab Pertanyaan SOP dengan IndoBERT")
+st.markdown("Ajukan pertanyaan seputar Prosedur Operasional Standar:")
 
-# User input
-question = st.text_area("Enter your question:", "")
+question = st.text_area("Masukkan pertanyaan Anda:", "")
 
-# Generate answer
-if st.button("Get Answer"):
+if st.button("Dapatkan Jawaban"):
     if question:
-        with st.spinner("Finding the best context..."):
-            # Automatically find the most relevant context
+        with st.spinner("Mencari konteks yang relevan..."):
             context = find_best_context(question, dataset)
-
             if context:
-                with st.spinner("Answering your question..."):
+                with st.spinner("Menjawab pertanyaan Anda..."):
                     result = qa_pipeline(question=question, context=context)
-                    st.success("Answer:")
+                    st.success("Jawaban:")
                     st.write(result["answer"])
-                    st.write("Confidence Score:", result["score"])
+                    st.write("Skor Keyakinan:", result["score"])
             else:
-                st.warning("No relevant context found. Please try rephrasing your question.")
+                st.warning("Konteks yang relevan tidak ditemukan. Silakan coba pertanyaan lain.")
     else:
-        st.warning("Please enter a question.")
+        st.warning("Silakan masukkan pertanyaan.")