Steamship#
Steamship is the fastest way to add AI to your software.
Think of Steamship as both a package manager and package hosting for AI. Each Steamship package runs in the cloud on a managed stack.
Steamship in 30 seconds#
Build Agents which run in the cloud.
Use Plugins for common operations like generating text with GPT, converting a CSV to text, or generating an image from text. Steamship manages asynchronicity and retries.
Store data in Files, Blocks, and Tags. This allows you to query or search it later.
Deploy as a Package, creating a scalable API for your front end.
Create as many instances of the Package as you want, each with its own data.
The best way to start is to make a simple package:
Start from a template#
Clone one of our starter packages (https://github.com/steamship-packages):
git clone https://github.com/steamship-packages/empty-package.git
Create a virtual environment and install dependencies:
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
pip install -r requirements.dev.txt
and start editing src/api.py
.
Start from scratch#
First, install our SDK and CLI (ideally in a virtual environment):
python3 -m venv venv
source venv/bin/activate
pip install steamship
Now copy this into api.py
:
from steamship.invocable import post, PackageService
class MyPackage(PackageService):
@post("hello_world")
def hello_world(self, name: str = None) -> str:
return f"Hello, {name}"
Next Steps#
Contents#
- Configuration
- Agents
- Packages
- Plugins
- Data
- Embedding Search Index
- Inserting Data
- Querying Data
- Developer Reference
- Python Client Reference
- License
- Authors