Create Completion with Cerebras API on Card Due Date Reminder from Pipedream API

Pipedream makes it easy to connect APIs for Cerebras, Pipedream and 2,500+ other apps remarkably fast.

Trigger workflow on

Card Due Date Reminder from the Pipedream API

Next, do this

Create Completion with the Cerebras API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a Pipedream trigger and Cerebras action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the Card Due Date Reminder trigger
1. Connect your Pipedream account
2. Connect your Pipedream account
3. Select a Board
4. Select a Time Before
Configure the Create Completion action
1. Connect your Cerebras account
2. Select a Model
3. Configure Prompt
4. Optional- Configure Stream
5. Optional- Configure Return Raw Tokens
6. Optional- Configure Max Tokens
7. Optional- Configure Min Tokens
8. Optional- Configure Seed
9. Optional- Configure Stop
10. Optional- Configure Temperature
11. Optional- Configure Top P
12. Optional- Configure Echo
13. Optional- Configure User
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

Card Due Date Reminder on Pipedream

Description:Emit new event at a specified time before a card is due.

Version:0.1.1

Key:trello-card-due-date-reminder

View on GitHub

Pipedream Overview#

Pipedream is an API that allows you to build applications that can connect to
various data sources and processes them in real-time. You can use Pipedream to
create applications that can perform ETL (Extract, Transform, and Load) tasks,
as well as to create data-driven workflows.

Some examples of applications you can build using the Pipedream API include:

An application that can extract data from a database, transform it, and then
load it into another database.
An application that can monitor a data source for changes, and then trigger a
workflow in response to those changes.
An application that can poll an API for new data, and then process that data
in real-time.

Trigger Code#

import taskScheduler from "../../../pipedream/sources/new-scheduled-tasks/new-scheduled-tasks.mjs";
import trello from "../../trello.app.mjs";
import ms from "ms";
import constants from "../../common/constants.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  key: "trello-card-due-date-reminder",
  name: "Card Due Date Reminder", /* eslint-disable-line pipedream/source-name */
  description: "Emit new event at a specified time before a card is due.",
  version: "0.1.1",
  type: "source",
  dedupe: "unique",
  props: {
    pipedream: taskScheduler.props.pipedream,
    trello,
    db: "$.service.db",
    http: "$.interface.http",
    board: {
      propDefinition: [
        trello,
        "board",
      ],
    },
    timeBefore: {
      type: "string",
      label: "Time Before",
      description: "How far before the due time the event should trigger. For example, `5 minutes`, `10 minutes`, `1 hour`.",
      default: "5 minutes",
      options: constants.NOTIFICATION_TIMES,
      reloadProps: true,
    },
  },
  async additionalProps() {
    const props = {};
    if (this.timeBefore) {
      props.timer = {
        type: "$.interface.timer",
        description: "Poll the API to schedule alerts for any newly created events",
        default: {
          intervalSeconds: ms(this.timeBefore) / 1000,
        },
      };
    }
    return props;
  },
  hooks: {
    async deactivate() {
      const ids = this._getScheduledEventIds();
      if (!ids?.length) {
        return;
      }
      for (const id of ids) {
        if (await this.deleteEvent({
          body: {
            id,
          },
        })) {
          console.log("Cancelled scheduled event");
        }
      }
      this._setScheduledEventIds();
    },
  },
  methods: {
    ...taskScheduler.methods,
    generateMeta({
      id, name: summary,
    }, now) {
      return {
        id,
        summary,
        ts: now,
      };
    },
    _getScheduledEventIds() {
      return this.db.get("scheduledEventIds");
    },
    _setScheduledEventIds(ids) {
      this.db.set("scheduledEventIds", ids);
    },
    _getScheduledCardIds() {
      return this.db.get("scheduledCardIds");
    },
    _setScheduledCardIds(ids) {
      this.db.set("scheduledCardIds", ids);
    },
    _hasDeployed() {
      const result = this.db.get("hasDeployed");
      this.db.set("hasDeployed", true);
      return result;
    },
    emitEvent(card, now) {
      const meta = this.generateMeta(card, now);
      this.$emit(card, meta);
    },
  },
  async run(event) {
    const now = event.timestamp * 1000;

    // self subscribe only on the first time
    if (!this._hasDeployed()) {
      await this.selfSubscribe();
    }

    let scheduledEventIds = this._getScheduledEventIds() || [];

    // incoming scheduled event
    if (event.$channel === this.selfChannel()) {
      const remainingScheduledEventIds = scheduledEventIds.filter((id) => id !== event["$id"]);
      this._setScheduledEventIds(remainingScheduledEventIds);
      this.emitEvent(event, now);
      return;
    }

    // schedule new events
    const scheduledCardIds = this._getScheduledCardIds() || {};
    const cards = await this.trello.getCards({
      boardId: this.board,
    });

    for (const card of cards) {
      const dueDate = card.due
        ? new Date(card.due)
        : null;
      if (!dueDate || dueDate.getTime() < Date.now()) {
        delete scheduledCardIds[card.id];
        continue;
      }

      const later = new Date(dueDate.getTime() - ms(this.timeBefore));

      if (scheduledCardIds[card.id]) {
        // reschedule if card's due date has changed
        if (card.due !== scheduledCardIds[card.id].dueDate) {
          await this.deleteEvent({
            body: {
              id: scheduledCardIds[card.id].eventId,
            },
          });
          scheduledEventIds = scheduledEventIds
            .filter((id) => id !== scheduledCardIds[card.id].eventId);
        } else {
          continue;
        }
      }

      const scheduledEventId = this.emitScheduleEvent(card, later);
      scheduledEventIds.push(scheduledEventId);
      scheduledCardIds[card.id] = {
        eventId: scheduledEventId,
        dueDate: card.due,
      };
    }
    this._setScheduledEventIds(scheduledEventIds);
    this._setScheduledCardIds(scheduledCardIds);
  },
  sampleEmit,
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
Pipedream	`pipedream`	`app`	This component uses the Pipedream app.
Pipedream	`trello`	`app`	This component uses the Pipedream app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
N/A	`http`	`$.interface.http`	This component uses `$.interface.http` to generate a unique URL when the component is first instantiated. Each request to the URL will trigger the `run()` method of the component.
Board	`board`	`string`	Select a value from the drop down menu.
Time Before	`timeBefore`	`string`	Select a value from the drop down menu:`5 minutes10 minutes15 minutes30 minutes1 hour2 hours3 hours6 hours12 hours1 day2 days3 days1 week`

Trigger Authentication#

Pipedream uses API keys for authentication. When you connect your Pipedream account, Pipedream securely stores the keys so you can easily authenticate to Pipedream APIs in both code and no-code steps.

About Pipedream#

Integration platform for developers

Action#

Create Completion on Cerebras

Description:Create a completion with Cerebras AI. [See the documentation](https://inference-docs.cerebras.ai/api-reference/completions)

Version:0.0.1

Key:cerebras-create-completion

View on GitHub

Action Code#

import cerebras from "../../cerebras.app.mjs";
import { parseObject } from "../../common/utils.mjs";
import { ConfigurationError } from "@pipedream/platform";

export default {
  name: "Create Completion",
  key: "cerebras-create-completion",
  description: "Create a completion with Cerebras AI. [See the documentation](https://inference-docs.cerebras.ai/api-reference/completions)",
  version: "0.0.1",
  type: "action",
  props: {
    cerebras,
    model: {
      propDefinition: [
        cerebras,
        "model",
      ],
    },
    prompt: {
      type: "string",
      label: "Prompt",
      description: "The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays",
    },
    stream: {
      propDefinition: [
        cerebras,
        "stream",
      ],
    },
    returnRawTokens: {
      type: "boolean",
      label: "Return Raw Tokens",
      description: "Return raw tokens instead of text",
      optional: true,
      default: false,
    },
    maxTokens: {
      type: "integer",
      label: "Max Tokens",
      description: "The maximum number of tokens that can be generated in the completion. The total length of input tokens and generated tokens is limited by the model's context length",
      optional: true,
    },
    minTokens: {
      type: "integer",
      label: "Min Tokens",
      description: "The minimum number of tokens to generate for a completion. If not specified or set to 0, the model will generate as many tokens as it deems necessary. Setting to -1 sets to max sequence length",
      optional: true,
    },
    seed: {
      propDefinition: [
        cerebras,
        "seed",
      ],
    },
    stop: {
      propDefinition: [
        cerebras,
        "stop",
      ],
    },
    temperature: {
      propDefinition: [
        cerebras,
        "temperature",
      ],
    },
    topP: {
      propDefinition: [
        cerebras,
        "topP",
      ],
    },
    echo: {
      type: "boolean",
      label: "Echo",
      description: "Echo back the prompt in addition to the completion. Incompatible with return_raw_tokens=True",
      optional: true,
      default: false,
    },
    user: {
      propDefinition: [
        cerebras,
        "user",
      ],
    },
  },
  async run({ $ }) {
    const {
      model,
      prompt,
      stream,
      returnRawTokens,
      maxTokens,
      minTokens,
      seed,
      stop,
      temperature,
      topP,
      echo,
      user,
    } = this;

    if (returnRawTokens && echo) {
      throw new ConfigurationError("The 'echo' option is incompatible with 'returnRawTokens=true'. Please disable one of these options.");
    }

    const response = await this.cerebras.completion({
      $,
      data: {
        model,
        prompt: parseObject(prompt),
        stream,
        return_raw_tokens: returnRawTokens,
        max_tokens: maxTokens,
        min_tokens: minTokens,
        seed,
        stop,
        temperature,
        top_p: topP,
        echo,
        user,
      },
    });

    $.export("$summary", "Successfully created completion");
    return response;
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
Cerebras	`cerebras`	`app`	This component uses the Cerebras app.
Model	`model`	`string`	Select a value from the drop down menu.
Prompt	`prompt`	`string`	The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays
Stream	`stream`	`boolean`	If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available
Return Raw Tokens	`returnRawTokens`	`boolean`	Return raw tokens instead of text
Max Tokens	`maxTokens`	`integer`	The maximum number of tokens that can be generated in the completion. The total length of input tokens and generated tokens is limited by the model's context length
Min Tokens	`minTokens`	`integer`	The minimum number of tokens to generate for a completion. If not specified or set to 0, the model will generate as many tokens as it deems necessary. Setting to -1 sets to max sequence length
Seed	`seed`	`integer`	If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result
Stop	`stop`	`string`	Up to 4 sequences, separated by commas, where the API will stop generating further tokens. The returned text will not contain the stop sequence
Temperature	`temperature`	`string`	What sampling temperature to use, between 0 and 1.5. Higher values (e.g., 0.8) will make the output more random, while lower values (e.g., 0.2) will make it more focused and deterministic
Top P	`topP`	`string`	An alternative to sampling with temperature, called nucleus sampling, where the model considers the tokens with top_p probability mass
Echo	`echo`	`boolean`	Echo back the prompt in addition to the completion. Incompatible with return_raw_tokens=True
User	`user`	`string`	A unique identifier representing your end-user, which can help Cerebras to monitor and detect abuse

Action Authentication#

Cerebras uses API keys for authentication. When you connect your Cerebras account, Pipedream securely stores the keys so you can easily authenticate to Cerebras APIs in both code and no-code steps.

About Cerebras#

Blazing-fast, scalable, and simple AI infrastructure—built for real-time applications and enterprise adoption.

More Ways to Connect Cerebras + Pipedream#

Other Popular Integrations#

Create Completion with Cerebras API on New Scheduled Tasks from Pipedream API

Pipedream + Cerebras

Try it

Create Chat Completion with Cerebras API on New Scheduled Tasks from Pipedream API

Pipedream + Cerebras

Try it

List Models with Cerebras API on New Scheduled Tasks from Pipedream API

Pipedream + Cerebras

Try it

List Models with Cerebras API on Card Due Date Reminder from Pipedream API

Pipedream + Cerebras

Try it

Create Chat Completion with Cerebras API on Card Due Date Reminder from Pipedream API

Pipedream + Cerebras

Try it

Popular Triggers#

New Scheduled Tasks from the Pipedream API

Exposes an HTTP API for scheduling messages to be emitted at a future time

Try it

New Upcoming Event Alert from the Pipedream API

Emit new event based on a time interval before an upcoming event in the calendar. This source uses Pipedream's Task Scheduler. See the documentation for more information and instructions for connecting your Pipedream account.

Try it

Card Due Date Reminder from the Pipedream API

Emit new event at a specified time before a card is due.

Try it

New Upcoming Calendar Event from the Pipedream API

Emit new event when a Calendar event is upcoming, this source is using reminderMinutesBeforeStart property of the event to determine the time it should emit.

Try it