Build generative AI applications with Google's PaLM 2 model.
Write custom Node.js code and use any of the 400k+ npm packages available. Refer to the Pipedream Node docs to learn more.
Generate embeddings using Google PaLM. See the docs here
The Google PaLM API is a cutting-edge language model that allows developers to integrate advanced natural language understanding into their applications. On Pipedream, you can harness this power to create serverless workflows that react to various triggers and perform actions based on the insights and outputs from PaLM. Whether it's generating content, summarizing text, or understanding user intent, PaLM's capabilities can be integrated into Pipedream workflows to automate complex tasks involving language.
import { v1beta2 } from "@google-ai/generativelanguage";
import { GoogleAuth } from "google-auth-library";
export default defineComponent({
props: {
google_palm_api: {
type: "app",
app: "google_palm_api",
}
},
async run({ steps, $ }) {
const client = new v1beta2.TextServiceClient({
authClient: new GoogleAuth().fromAPIKey(this.google_palm_api.$auth.palm_api_key),
});
const text = "Repeat after me: one, two,";
const model = "models/text-bison-001";
return await client
.generateText({
model,
prompt: {
text,
},
})
},
})
Develop, run and deploy your Node.js code in Pipedream workflows, using it between no-code steps, with connected accounts, or integrate Data Stores and File Stores.
This includes installing NPM packages, within your code without having to manage a package.json
file or running npm install
.
Below is an example of installing the axios
package in a Pipedream Node.js code step. Pipedream imports the axios
package, performs the API request, and shares the response with subsequent workflow steps:
// To use previous step data, pass the `steps` object to the run() function
export default defineComponent({
async run({ steps, $ }) {
// Return data to use it in future steps
return steps.trigger.event
},
})