Build & Deploy Full-stack AI from Replit
Featured Replits
Click to run, clone, and make your own.
Self Ask with Search
Host a self-ask with search endpoint.
Persistent Chatbot
Host your own LangChain-based chatbot that remembers user input over sessions.
Summarize YouTube Videos
Summarize the audio track of YouTube videos with LangChain and Steamship.
Question Answering with Sources
Use persistent embeddings to answer questions with sources.
Simple LangChain Prompting
Example of a LangChain-based prompt API on Steamship.
- Set your Steamship API key in Replit
- Get your API key here, then add it as a secret named
STEAMSHIP_API_KEYin Replit. - Find the Python class in api.py
- Your API lives inside
api.py. The template already contains a working prompt that runs with user input. - Click Replit's Run button to try it
- Your API is just Python. You can run it right and see the results right from your editor.
- Deploy to share with the world
- When you deploy your API, we"ll generate a web interface and HTTP endpoints for you.
Name your package and set your version
In your project"s
steamship.jsonfile, set thehandlefield to a unique name. Only lowercase letters and dashes, please!Set your version
In your project"s
steamship.jsonfile, set theversionfield using semver-style (1.2.3).Run 'ship deploy'
Your Replit comes with a pre-configured shell. Open the shell and type
ship deploy.Share the results
When deployment succeeds, you'll see a URL that lets anyone try your API on the web or use it over HTTP.