Skip to content

Latest commit

 

History

History
110 lines (84 loc) · 3.15 KB

README.md

File metadata and controls

110 lines (84 loc) · 3.15 KB
Raw

open-research-ANA 🔍

This demo showcases ANA (Agent Native Application), a research canvas app that combines Human-in-the-Loop capabilities with Tavily's real-time search and CopilotKit's agentic interface.

Powered by LangGraph, it simplifies complex research tasks, making them more interactive and efficient.

Explore the CopilotKit docs »

tavily-demo

Quick Start 🚀

1. Prerequisites

This projects uses the following tools:

2. API Keys Needed

Running locally, you'll need the following API keys:

3. Start the Agent

There are two main components to this project: the agent and the frontend. First, we'll start the agent. If you are using Copilot Cloud and LangGraph Platform, you can skip this step.

cd agent

# Create and populate .env
cat << EOF > .env
OPENAI_API_KEY=your_key
TAVILY_API_KEY=your_key
LANGSMITH_API_KEY=your_key
EOF

# Start the agent
langgraph up

# Note the API URL from the output (e.g., http://localhost:8000)

4. Start the Frontend

Next, we'll start the frontend.

cd frontend
pnpm install

# Create and populate .env
cat << EOF > .env
LOCAL_DEPLOYMENT_URL=http://localhost:8000  # URL from langgraph up
OPENAI_API_KEY=your_key
LANGSMITH_API_KEY=your_key
NEXT_PUBLIC_COPILOT_CLOUD_API_KEY=your_key
EOF

# Start the app
pnpm run dev

Using with Copilot Cloud ☁️

You can use either a local agent or a LangGraph Platform deployment with Copilot Cloud. Copilot Cloud is a free to start hosted runtime for CopilotKit that allows you easily integrate your LangGraph Platform endpoints into your CopilotKit agent.

Option 1: Local Agent

  1. Create a tunnel to your local agent:
npx @copilotkit/cli tunnel 8000

Option 2: LangGraph Platform

  1. Deploy your agent using LangGraph Platform
  2. Use the deployment URL provided

Register the Endpoint

For either option:

  1. Go to Copilot Cloud
  2. Add a new Remote Endpoint
  3. Enter your tunnel URL or LangGraph Platform deployment URL
  4. Provide your LANGSMITH_API_KEY
  5. Test and Save

Deployment Options 🛠️

Local Development (Default)

pnpm run dev

Remote Agent

# Deploy agent using LangGraph Platform
# Set DEPLOYMENT_URL in frontend/.env
pnpm run remote-lgc-dev

Documentation 📚