Introduction
To run agents in production, we need to:
- Serve them using an application like FastApi, Django or Streamlit.
- Manage their sessions, memory and knowlege in a database.
- Monitor, evaluate and improve their performance.
Phidata not only makes building Agents easy but also provides templates that can be deployed to AWS with 1 command. Here’s how they work:
- Create your codebase using a template:
phi ws create - Run your application locally:
phi ws up - Run your application on AWS:
phi ws up prd:aws
We strongly believe that data used by AI applications should be stored securely inside your VPC.
We fully support BYOC (Bring Your Own Cloud) and encourage you to use your own AWS account.
Templates
We recommend starting with the agent-app template and adding your own agents.
Agent App
Run agents using FastApi, Streamlit and store memory and knowlege in Postgres
Agent Api
Run agents using FastApi and store memory and knowlege in Postgres
Introduction
To run agents in production, we need to:
- Serve them using an application like FastApi, Django or Streamlit.
- Manage their sessions, memory and knowlege in a database.
- Monitor, evaluate and improve their performance.
Phidata not only makes building Agents easy but also provides templates that can be deployed to AWS with 1 command. Here’s how they work:
- Create your codebase using a template:
phi ws create - Run your application locally:
phi ws up - Run your application on AWS:
phi ws up prd:aws
We strongly believe that data used by AI applications should be stored securely inside your VPC.
We fully support BYOC (Bring Your Own Cloud) and encourage you to use your own AWS account.
Templates
We recommend starting with the agent-app template and adding your own agents.
Agent App
Run agents using FastApi, Streamlit and store memory and knowlege in Postgres
Agent Api
Run agents using FastApi and store memory and knowlege in Postgres