AI Legal Agent Team

import tempfile
import os
from agno.knowledge.knowledge import Knowledge

def process_document(uploaded_file, vector_db):
    """
    Process document, create embeddings and store in Qdrant.
    
    Args:
        uploaded_file: Streamlit uploaded file object
        vector_db: Initialized Qdrant instance
        
    Returns:
        Knowledge: Initialized knowledge base
    """
    # Save uploaded file temporarily
    with tempfile.NamedTemporaryFile(
        delete=False, 
        suffix='.pdf'
    ) as temp_file:
        temp_file.write(uploaded_file.getvalue())
        temp_file_path = temp_file.name
    
    # Create knowledge base
    knowledge_base = Knowledge(vector_db=vector_db)
    
    # Add document to knowledge base
    knowledge_base.add_content(path=temp_file_path)
    
    # Clean up temporary file
    os.unlink(temp_file_path)
    
    return knowledge_base

# Analysis configurations for different use cases
analysis_configs = {
    "Contract Review": {
        "query": "Review this contract and identify key terms, "
                "obligations, and potential issues.",
        "agents": ["Contract Analyst"],
        "description": "Detailed contract analysis focusing on "
                      "terms and obligations"
    },
    "Legal Research": {
        "query": "Research relevant cases and precedents "
                "related to this document.",
        "agents": ["Legal Researcher"],
        "description": "Research on relevant legal cases "
                      "and precedents"
    },
    "Risk Assessment": {
        "query": "Analyze potential legal risks and "
                "liabilities in this document.",
        "agents": ["Contract Analyst", "Legal Strategist"],
        "description": "Combined risk analysis and "
                      "strategic assessment"
    },
    "Compliance Check": {
        "query": "Check this document for regulatory "
                "compliance issues.",
        "agents": ["Legal Researcher", "Contract Analyst", 
                  "Legal Strategist"],
        "description": "Comprehensive compliance analysis"
    },
    "Custom Query": {
        "query": None,
        "agents": ["Legal Researcher", "Contract Analyst", 
                  "Legal Strategist"],
        "description": "Custom analysis using all available agents"
    }
}

import streamlit as st

st.title("AI Legal Agent Team 👨‍⚖️")

# Sidebar - API Configuration
with st.sidebar:
    st.header("🔑 API Configuration")
    
    openai_key = st.text_input(
        "OpenAI API Key",
        type="password"
    )
    
    qdrant_key = st.text_input(
        "Qdrant API Key",
        type="password"
    )
    
    qdrant_url = st.text_input(
        "Qdrant URL"
    )
    
    st.divider()
    
    # Document upload
    st.header("📄 Document Upload")
    uploaded_file = st.file_uploader(
        "Upload Legal Document",
        type=['pdf']
    )
    
    st.divider()
    
    # Analysis options
    st.header("🔍 Analysis Options")
    analysis_type = st.selectbox(
        "Select Analysis Type",
        [
            "Contract Review",
            "Legal Research",
            "Risk Assessment",
            "Compliance Check",
            "Custom Query"
        ]
    )

# Main content
if st.button("Analyze"):
    # Process document and run analysis
    response = legal_team.run(query)
    
    # Display results in tabs
    tabs = st.tabs(["Analysis", "Key Points", "Recommendations"])
    
    with tabs[0]:
        st.markdown("### Detailed Analysis")
        st.markdown(response.content)
    
    with tabs[1]:
        st.markdown("### Key Points")
        # Extract key points
    
    with tabs[2]:
        st.markdown("### Recommendations")
        # Generate recommendations