Update app.py

app.py

@@ -5,40 +5,44 @@ import faiss
 import numpy as np
 from transformers import pipeline
 
-# Load dataset
 dataset = load_dataset("lex_glue", "scotus")
-corpus = [doc['text'] for doc in dataset['train'].select(range(200))]  # just 200 to keep it light
+corpus = [doc['text'] for doc in dataset['train'].select(range(200))]
 
-# Embedding model
 embedder = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
 corpus_embeddings = embedder.encode(corpus, convert_to_numpy=True)
 
-# Build FAISS index
 dimension = corpus_embeddings.shape[1]
 index = faiss.IndexFlatL2(dimension)
 index.add(corpus_embeddings)
 
-# Text generation model
 gen_pipeline = pipeline("text2text-generation", model="facebook/bart-large-cnn")
 
-# RAG-like query function
 def rag_query(user_question):
     question_embedding = embedder.encode([user_question])
     _, indices = index.search(np.array(question_embedding), k=3)
     context = " ".join([corpus[i] for i in indices[0]])
-
     prompt = f"Question: {user_question}\nContext: {context}\nAnswer:"
     result = gen_pipeline(prompt, max_length=250, do_sample=False)[0]['generated_text']
     return result
 
-# Gradio UI
-def chatbot_interface(query):
-    return rag_query(query)
-
-iface = gr.Interface(fn=chatbot_interface,
-                     inputs="text",
-                     outputs="text",
-                     title="🧑‍⚖️ Legal Assistant Chatbot",
-                     description="Ask legal questions based on case data (LexGLUE - SCOTUS subset)")
+def chatbot_interface(query, history):
+    response = rag_query(query)
+    history.append((query, response))
+    chat_history = "\n\n".join([f"👤 You: {q}\n🧑‍⚖️ Bot: {a}" for q, a in history])
+    return chat_history, history
+
+iface = gr.Interface(
+    fn=chatbot_interface,
+    inputs=[
+        gr.Textbox(lines=2, placeholder="Enter your legal question here...", label="Your Question"),
+        gr.State([])  # Keeps history
+    ],
+    outputs=[
+        gr.Textbox(label="Chat History", lines=20, interactive=False),
+        gr.State()
+    ],
+    title="🧑‍⚖️ Legal Assistant Chatbot",
+    description="Ask legal questions based on case data (LexGLUE - SCOTUS subset). The bot will retrieve relevant context and answer your question."
+)
 
 iface.launch()