Update app.py

app.py

@@ -40,6 +40,20 @@ def prepare_dataset(dataset_name):
     documents = dataset['train']['text'][:100]  # Use a subset for demo purposes
     titles = dataset['train']['title'][:100]  # Get corresponding titles
 
+# Function for case retrieval and summarization
+def retrieve_cases(query):
+    # Implement a simple keyword-based search for demo purposes
+    return [(doc, title) for doc, title in zip(documents, titles) if query.lower() in doc.lower()]
+
+def summarize_cases(cases):
+    summaries = []
+    for case in cases:
+        input_ids = t5_tokenizer.encode(case[0], return_tensors="pt", max_length=512, truncation=True)
+        outputs = t5_model.generate(input_ids, max_length=60, min_length=30, length_penalty=2.0, num_beams=4, early_stopping=True)
+        summary = t5_tokenizer.decode(outputs[0], skip_special_tokens=True)
+        summaries.append(summary)
+    return summaries
+
 # Streamlit App Code
 st.title("Legal Case Summarizer")
 st.write("Select a dataset and enter keywords to retrieve and summarize relevant cases.")
@@ -62,7 +76,7 @@ if st.button("Retrieve and Summarize Cases"):
                 summary = summaries[i]
                 st.write(f"### Case {i + 1}")
                 st.write(f"**Title:** {title}")
-                st.write(f"**Case Text:** {case}")
+                st.write(f"**Case Text:** {case[0]}")
                 st.write(f"**Summary:** {summary}")
         else:
             st.write("No cases found for the given query.")