Building an Agent API

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

Create a virtual environment

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

python3 -m venv aienv
aienv/scripts/activate

Install phidata

pip install -U "phidata[aws]"

pip install -U "phidata[aws]"

Install docker

Install docker desktop to run your app locally

Export your OpenAI key

export OPENAI_API_KEY=sk-***

setx 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

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

phi ws up dev:docker

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

phi ws down --env dev --infra docker

phi ws down dev:docker

Congratulations on running your AI API locally. Next Steps:

Run your Agent API on AWS
Read how to update workspace settings
Read how to create a git repository for your workspace
Read how to manage the development application
Read how to format and validate your code
Read how to add python libraries
Chat with us on discord

Templates

How to

Workspace

Apps

Resources

Building an Agent API

Setup

Create your codebase

Serve your Agents using FastApi

Building your AI Product

Delete local resources

Next

​Setup

​Create your codebase

​Serve your Agents using FastApi

​Building your AI Product

​Delete local resources

​Next

Setup

Create your codebase

Serve your Agents using FastApi

Building your AI Product

Delete local resources

Next