Create app.py

app.py

@@ -0,0 +1,50 @@
+# Import Libraries
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from sentence_transformers import SentenceTransformer
+from datasets import load_dataset
+import faiss
+import numpy as np
+import streamlit as st
+
+# Load the Legal Guidance Dataset
+dataset = load_dataset("lex_glue", "ecthr_a")
+texts = dataset['train']['text'][:100]  # Limiting to 100 samples for faster processing
+
+# Initialize Models for Retrieval and Summarization
+sbert_model = SentenceTransformer("all-mpnet-base-v2")  # Model for encoding legal guidance texts
+t5_tokenizer = AutoTokenizer.from_pretrained("t5-small")  # Tokenizer for summarization
+t5_model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")  # Summarization model
+
+# Encode Documents with SBERT and Build FAISS Index
+case_embeddings = sbert_model.encode(texts, convert_to_tensor=True, show_progress_bar=True)
+index = faiss.IndexFlatL2(case_embeddings.shape[1])
+index.add(np.array(case_embeddings.cpu()))
+
+# Function to Retrieve Similar Cases
+def retrieve_cases(query, top_k=3):
+    query_embedding = sbert_model.encode(query, convert_to_tensor=True)
+    _, indices = index.search(np.array([query_embedding.cpu()]), top_k)
+    return [(texts[i], i) for i in indices[0]]
+
+# Function to Summarize the Retrieved Text
+def summarize_text(text):
+    inputs = t5_tokenizer("summarize: " + text, return_tensors="pt", max_length=512, truncation=True)
+    outputs = t5_model.generate(inputs["input_ids"], max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
+    return t5_tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Streamlit UI for LawyerGuide App
+def main():
+    st.title("LawyerGuide App: Legal Guidance for False Accusations")
+    query = st.text_input("Describe your situation or legal concern:")
+    top_k = st.slider("Number of similar cases to retrieve:", 1, 5, 3)
+    
+    if st.button("Get Guidance"):
+        results = retrieve_cases(query, top_k=top_k)
+        for i, (case_text, index) in enumerate(results):
+            st.subheader(f"Guidance {i+1}")
+            st.write("Relevant Text:", case_text)
+            summary = summarize_text(case_text)
+            st.write("Summary of Legal Guidance:", summary)
+
+if __name__ == "__main__":
+    main()