Create app.py

app.py

@@ -0,0 +1,58 @@
+import streamlit as st
+from transformers import pipeline
+import pandas as pd
+import re
+
+# Load the Question Answering model
+qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
+
+# Load SOP Dataset
+@st.cache
+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
+    return 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 = []
+    for index, row in dataset.iterrows():
+        if re.search(question, row["text"], re.IGNORECASE):
+            relevant_contexts.append(row["text"])
+    return relevant_contexts
+
+# Streamlit UI
+st.title("SOP Question Answering AI")
+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"])
+    else:
+        st.warning("Please select a context or refine your question.")