AI21 Studio provides API access to Jurassic-1 large-language-models. Our models power text generation and comprehension features in thousands of live applications.
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
Studio by AI21 Labs API enables the crafting of human-like text using advanced language models. It can generate content, answer questions, summarize text, or even customize language models for specific tasks. When integrated into Pipedream, this API becomes part of powerful automations that can process and generate textual content dynamically, reacting to various triggers such as incoming emails, form submissions, or scheduled events.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
studio_by_ai21_labs: {
type: "app",
app: "studio_by_ai21_labs",
}
},
async run({steps, $}) {
const data = {
"text": `Pipedream is the fastest way to automate any process that connects APIs. Build and run workflows with code-level control when you need it, and no code when you don't. The Pipedream platform includes a serverless runtime and workflow service, source-available triggers and actions for hundreds of integrated apps, and one-click OAuth and key-based authentication for more than 1000 APIs (use tokens directly in code or with pre-built actions).`,
}
return await axios($, {
method: "post",
url: `https://api.ai21.com/studio/v1/experimental/summarize`,
headers: {
Authorization: `Bearer ${this.studio_by_ai21_labs.$auth.api_key}`,
"Content-Type": `application/json`,
},
data,
})
},
})
Develop, run and deploy your Python code in Pipedream workflows. Integrate seamlessly between no-code steps, with connected accounts, or integrate Data Stores and manipulate files within a workflow.
This includes installing PyPI packages, within your code without having to manage a requirements.txt
file or running pip
.
Below is an example of using Python to access data from the trigger of the workflow, and sharing it with subsequent workflow steps:
def handler(pd: "pipedream"):
# Reference data from previous steps
print(pd.steps["trigger"]["context"]["id"])
# Return data for use in future steps
return {"foo": {"test":True}}