cd path/to/ADKCallLeadSum
python3 -m venv venv

This project analyzes transcripts of lead calls to determine if the call is successful or denied, and creates a Streamlit analysis dashboard for visualization and insights.

• Isa Ruiz
• Hugo Granillo
• Jesus Casasanta
• Daniel Escobar

ADKCallLeadSum/
├── README.md
├── requirements.txt
├── LICENSE
├── venv/                    # Virtual environment (created locally)
├── backend/
│   └── transcript_analyze_agent/
│       ├── __init__.py
│       ├── agent.py         # ADK agent for call analysis
│       ├── batch_analyzer_agent.py  # Automated batch analysis
│       └── resetDatabase.py # Database reset utility
├── database/
│   └── callsDatabase.json   # Call transcripts database
└── frontend/
    └── Dashboard.py         # Streamlit dashboard

Navigate to the project directory and create a virtual environment:

cd /Users/nielsmac/Desktop/ADKCallLeadSum/ADKCallLeadSum
python3 -m venv venv

Activate the virtual environment (do this every time you work on the project):

source venv/bin/activate

You should see (venv) at the beginning of your terminal prompt, indicating the virtual environment is active.

With the virtual environment activated, install all required dependencies:

pip install -r requirements.txt

Note: The venv/ directory is gitignored, so each team member needs to create their own virtual environment and install dependencies locally.

Check that all packages were installed correctly:

pip list

When you're finished working on the project, deactivate the virtual environment:

deactivate

# Navigate to project
cd path/to/ADKCallLeadSum

# Activate virtual environment
source venv/bin/activate

# Install dependencies (first time only)
pip install -r requirements.txt

# Run ADK Agent
cd backend && adk run multi_tool_agent

# OR Run Streamlit Frontend
streamlit run frontend/Dashboard.py

# Deactivate when done
deactivate

For detailed backend setup and usage instructions, see: backend/README.md

Quick Start:

source venv/bin/activate
adk run backend/transcript_analyze_agent

For detailed frontend setup and usage instructions, see: frontend/README.md

Quick Start:

source venv/bin/activate
streamlit run frontend/Dashboard.py

Agent Development Kit CLI tools.

Options:

• --version Show the version and exit.
• --help Show this message and exit.

Commands:

• api_server Starts a FastAPI server for agents.
• conformance Conformance testing tools for ADK.
• create Creates a new app in the current folder with prepopulated agent template.
• deploy Deploys agent to hosted environments.
• eval Evaluates an agent given the eval sets.
• run Runs an interactive CLI for a certain agent.
• web Starts a FastAPI server with Web UI for agents.

# Run interactive CLI for your agent
adk run multi_tool_agent

# Start web UI for your agent
adk web multi_tool_agent

# Create a new agent template
adk create new_agent_name

# Check ADK version
adk --version

This project uses the following main libraries:

• Streamlit: Web app framework
• Google ADK: Agent Development Kit
• yfinance: Yahoo Finance data
• psutil: System utilities
• litellm: LLM integration
• google-generativeai: Google's Generative AI
• python-dotenv: Environment variables

• Incorporate Call Recording Integration through Twillio and Add it to the data base for further analysis.
• Create call report for Sales Representatives and send it on their. corresponding email
• Provide success/fail lead data to improve business decision ok the marketing aspect
• implement and agent to send an email to marketing team with summary of performance in a specific time or Sale Rep