LLMWhisperer is a technology that presents data from complex documents to LLMs in a way that they can best understand.
Convert your PDF/scanned documents to text format which can be used by LLMs. See the documentation
Create a new document in a collection of your choice. See the docs here
Get the status of the whisper process. This can be used to check the status of the conversion process when the conversion is done in async mode. See the documentation
Generate highlight locations for a search term in the document. See the documentation
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
llmwhisperer: {
type: "app",
app: "llmwhisperer",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://llmwhisperer-api.unstract.com/v1/get-usage-info`,
headers: {
"unstract-key": `${this.llmwhisperer.$auth.api_key}`,
},
})
},
})
The MongoDB API provides powerful capabilities to interact with a MongoDB database, allowing you to perform CRUD (Create, Read, Update, Delete) operations, manage databases, and execute sophisticated queries. With Pipedream, you can harness these abilities to automate tasks, sync data across various apps, and react to events in real-time. It’s a combo that’s particularly potent for managing data workflows, syncing application states, or triggering actions based on changes to your data.
import mongodb from 'mongodb'
export default defineComponent({
props: {
mongodb: {
type: "app",
app: "mongodb",
},
collection: {
type: "string"
},
filter: {
type: "object"
}
},
async run({steps, $}) {
const MongoClient = mongodb.MongoClient
const {
database,
hostname,
username,
password,
} = this.mongodb.$auth
const url = `mongodb+srv://${username}:${password}@${hostname}/test?retryWrites=true&w=majority`
const client = await MongoClient.connect(url, {
useNewUrlParser: true,
useUnifiedTopology: true
})
const db = client.db(database)
const results = await db.collection(this.collection).find(this.filter).toArray();
$.export('results', results);
await client.close()
},
})