app.py

import streamlit as st
from llama_index.core import Settings
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, StorageContext
from llama_index.embeddings.gemini import GeminiEmbedding
from llama_index.llms.gemini import Gemini
from llama_index.core import Document
import google.generativeai as genai
import os
import PyPDF2
from io import BytesIO
from llama_index.embeddings.fastembed import FastEmbedEmbedding



# Configure Google Gemini
Settings.embed_model = FastEmbedEmbedding(model_name="BAAI/bge-small-en-v1.5")

Settings.llm = Gemini(api_key=os.getenv("GOOGLE_API_KEY"), temperature=0.1, model_name="models/gemini-pro")

def write_to_file(content, filename="./files/test.pdf"):
    with open(filename, "wb") as f:
        f.write(content)

def ingest_documents():
    reader = SimpleDirectoryReader("./files/")
    documents = reader.load_data()
    print(documents)
    return documents

def load_data(documents):
    index = VectorStoreIndex.from_documents(documents)
    return index

# Generate legal document summary
def generate_summary(index, document_text):
    query_engine = index.as_query_engine()
    response = query_engine.query(f"""
    You are a skilled legal analyst. Your task is to provide a comprehensive summary of the given legal document.
    Analyze the following document and summarize it:
    {document_text}
    
    Please cover the following aspects:
    1. Document type and purpose
    2. Key parties involved
    3. Main clauses and provisions
    4. Important dates and deadlines
    5. Potential legal implications
    6. Any notable or unusual elements
    
    Provide a clear, concise, and professional summary
    """)
    return response.response

# Streamlit app
def main():
    st.title("Legal Document Summarizer")
    st.write("Upload a legal document, and let our AI summarize it!")

    # File uploader
    uploaded_file = st.file_uploader("Choose a legal document file", type=["txt", "pdf"])

    if uploaded_file is not None:
        # Read file contents
        if uploaded_file.type == "application/pdf":
            pdf_reader = PyPDF2.PdfReader(BytesIO(uploaded_file.getvalue()))
            document_text = ""
            for page in pdf_reader.pages:
                document_text += page.extract_text()
        else:
            document_text = uploaded_file.getvalue().decode("utf-8")

        # Write content to file
        write_to_file(uploaded_file.getvalue())

        st.write("Analyzing legal document...")

        # Ingest documents using SimpleDirectoryReader
        documents = ingest_documents()

        # Load data and generate summary
        index = load_data(documents)
        summary = generate_summary(index, document_text)

        st.write("## Legal Document Summary")
        st.write(summary)

if __name__ == "__main__":
    main()