Update app.py

app.py

@@ -5,46 +5,99 @@ import faiss
 import numpy as np
 from transformers import pipeline
 
+
 dataset = load_dataset("lex_glue", "scotus")
-corpus_data = dataset['train'].select(range(200))
-corpus = [doc['text'] for doc in corpus_data]
+corpus = [doc['text'] for doc in dataset['train'].select(range(200))]  
+
 
 embedder = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
 corpus_embeddings = embedder.encode(corpus, convert_to_numpy=True)
 
+
 dimension = corpus_embeddings.shape[1]
 index = faiss.IndexFlatL2(dimension)
 index.add(corpus_embeddings)
 
+
 gen_pipeline = pipeline("text2text-generation", model="facebook/bart-large-cnn")
 
+
 def rag_query(user_question):
     question_embedding = embedder.encode([user_question])
-    _, indices = index.search(np.array(question_embedding), k=3)
-    valid_indices = [i for i in indices[0] if i < len(corpus)]
-    context = " ".join([corpus[i] for i in valid_indices])
+    k = 3  
+    if index.ntotal < k:
+        k = index.ntotal  
+    _, indices = index.search(np.array(question_embedding), k=k)
+
+    if len(indices[0]) == 0:
+        return "Sorry, no relevant documents were found."
+
+    context = " ".join([corpus[i] for i in indices[0] if i < len(corpus)])
+
     prompt = f"Question: {user_question}\nContext: {context}\nAnswer:"
     result = gen_pipeline(prompt, max_length=250, do_sample=False)[0]['generated_text']
     return result
 
-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
+
+def chatbot_interface(query):
+    return rag_query(query)
+
+
+css = """
+    .gradio-container {
+        background-color: #f0f4f8;
+        font-family: Arial, sans-serif;
+    }
+    .gradio-input {
+        background-color: #ffffff;
+        border-radius: 5px;
+        border: 1px solid #d1d1d1;
+        font-size: 16px;
+        padding: 10px;
+    }
+    .gradio-button {
+        background-color: #4CAF50;
+        color: white;
+        border-radius: 5px;
+        border: none;
+        padding: 10px 20px;
+        font-size: 16px;
+    }
+    .gradio-button:hover {
+        background-color: #45a049;
+    }
+    .gradio-output {
+        background-color: #ffffff;
+        border-radius: 5px;
+        padding: 15px;
+        font-size: 16px;
+        border: 1px solid #d1d1d1;
+    }
+    .gradio-title {
+        font-size: 28px;
+        font-weight: bold;
+        color: #333333;
+        text-align: center;
+        margin-bottom: 20px;
+    }
+    .gradio-description {
+        font-size: 16px;
+        color: #666666;
+        text-align: center;
+        margin-bottom: 30px;
+    }
+"""
+
 
 iface = gr.Interface(
     fn=chatbot_interface,
-    inputs=[
-        gr.Textbox(lines=2, placeholder="Enter your legal question here...", label="Your Question"),
-        gr.State([])  # Session state to store history
-    ],
-    outputs=[
-        gr.Textbox(label="Chat History", lines=20, interactive=False),
-        gr.State()
-    ],
+    inputs="text",
+    outputs="text",
     title="🧑‍⚖️ Legal Assistant Chatbot",
-    description="Ask legal questions based on case data (LexGLUE - SCOTUS subset). The bot retrieves context and generates an answer."
+    description="Ask legal questions based on case data (LexGLUE - SCOTUS subset). Get answers derived from relevant court case texts.",
+    theme="compact",
+    css=css
 )
 
+
 iface.launch()