Update app.py

app.py

@@ -7,7 +7,7 @@ import re
 qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
 
 # Load SOP Dataset
-@st.cache
+@st.cache_data
 def load_sop_dataset():
     """Load SOP dataset from CSV."""
     dataset = pd.read_csv("dataset.csv")  # Ensure this file is uploaded to your Hugging Face Space
@@ -16,14 +16,20 @@ def load_sop_dataset():
 # Load the dataset
 dataset = load_sop_dataset()
 
-# Utility function to find relevant contexts
-def find_relevant_contexts(question, dataset):
-    """Search for relevant contexts in the dataset."""
-    relevant_contexts = []
+# Utility function to find the most relevant context
+def find_best_context(question, dataset):
+    """Find the single best context for a given question."""
+    best_score = 0
+    best_context = None
+
     for index, row in dataset.iterrows():
-        if re.search(question, row["text"], re.IGNORECASE):
-            relevant_contexts.append(row["text"])
-    return relevant_contexts
+        # 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")
@@ -31,28 +37,21 @@ st.markdown("Ask any question about Standard Operating Procedures:")
 
 # User input
 question = st.text_area("Enter your question:", "")
-specific_context = st.checkbox("Use specific SOP context?")
-
-context = None
-if specific_context:
-    st.write("Choose a context:")
-    context = st.selectbox("SOP Contexts", dataset["text"])
-else:
-    if question:
-        st.write("Searching for relevant contexts...")
-        relevant_contexts = find_relevant_contexts(question, dataset)
-        if relevant_contexts:
-            context = st.selectbox("Relevant SOP Contexts", relevant_contexts)
-        else:
-            st.warning("No relevant contexts found. Try refining your question.")
 
 # Generate answer
 if st.button("Get Answer"):
-    if context:
-        with st.spinner("Finding the answer..."):
-            result = qa_pipeline(question=question, context=context)
-            st.success("Answer:")
-            st.write(result["answer"])
-            st.write("Confidence Score:", result["score"])
+    if question:
+        with st.spinner("Finding the best context..."):
+            # Automatically find the most relevant context
+            context = find_best_context(question, dataset)
+
+            if context:
+                with st.spinner("Answering your question..."):
+                    result = qa_pipeline(question=question, context=context)
+                    st.success("Answer:")
+                    st.write(result["answer"])
+                    st.write("Confidence Score:", result["score"])
+            else:
+                st.warning("No relevant context found. Please try rephrasing your question.")
     else:
-        st.warning("Please select a context or refine your question.")
+        st.warning("Please enter a question.")