The Agent Api let’s us serve agents using a FastApi server and store memory and knowledge in a Postgres database. Run it locally using docker or deploy to production on AWS.

​
Setup

1

Create a virtual environment

python3 -m venv ~/.venvs/aienv
source ~/.venvs/aienv/bin/activate
2

Install phidata

pip install -U "phidata[aws]"
3

Install docker

Install docker desktop to run your app locally
4

Export your OpenAI key

export OPENAI_API_KEY=sk-***
You can get an API key from here.

​
Create your codebase

Create your codebase using the agent-api template 
phi ws create -t agent-api -n agent-api
This will create a folder agent-api with the following structure: 
agent-api                     # root directory
├── agents                  # add your Agents here
├── api                     # add fastApi routes here
├── db                      # add database tables here
├── Dockerfile              # Dockerfile for the application
├── pyproject.toml          # python project definition
├── requirements.txt        # python dependencies generated by pyproject.toml
├── scripts                 # helper scripts
├── utils                   # shared utilities
└── workspace               # phidata workspace directory
    ├── dev_resources.py    # dev resources running locally
    ├── prd_resources.py    # production resources running on AWS
    ├── secrets             # secrets
    └── settings.py         # phidata workspace settings

​
Serve your Agents using FastApi

FastApi is an exceptional framework for building RestApis. Its fast, well-designed and loved by everyone using it. Most production applications are built using a front-end framework like next.js backed by a RestAPI, where FastApi shines. Your codebase comes pre-configured with FastApi and PostgreSQL, along with some sample routes. Start your workspace using: 
phi ws up
Press Enter to confirm and give a few minutes for the image to download (only the first time). Verify container status and view logs on the docker dashboard.
  • Open localhost:8000/docs to view the API Endpoints.
  • Test the /v1/playground/agent/run endpoint with
{
  "message": "howdy",
  "agent_id": "example-agent",
  "stream": true
}

​
Building your AI Product

The agent-app comes with common endpoints that you can use to build your AI product. This API is developed in close collaboration with real AI Apps and are a great starting point. The general workflow is:
  • Your front-end/product will call the /v1/playground/agent/run to run Agents.
  • Using the session_id returned, your product can continue and serve chats to its users.

​
Delete local resources

Play around and stop the workspace using: 
phi ws down

​
Next

Congratulations on running your AI API locally. Next Steps: