Create Vector Store with OpenAI (ChatGPT) API on New Time Entry Started from McTime API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), McTime and 2,700+ other apps remarkably fast.

Trigger workflow on

New Time Entry Started from the McTime API

Next, do this

Create Vector Store with the OpenAI (ChatGPT) 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 McTime trigger and OpenAI (ChatGPT) action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Time Entry Started trigger
1. Connect your McTime account
2. Configure timer
Configure the Create Vector Store action
1. Connect your OpenAI (ChatGPT) account
2. Optional- Select one or more File IDs
3. Optional- Configure Name
4. Optional- Configure Expiration Days
5. Optional- Configure Metadata
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#

New Time Entry Started on McTime

Description:Emit new event each time a new time entry is started

Version:0.0.1

Key:mctime-new-time-entry-started

View on GitHub

McTime Overview#

The McTime API provides functionality for tracking and managing time-related data. With McTime integrated into Pipedream, you can automate processes involving employee scheduling, time tracking, and payroll. Leverage Pipedream's ability to connect with hundreds of apps to link time data with project management tools, accounting software, and communication platforms, streamlining workflow efficiencies and reducing manual timekeeping errors.

Trigger Code#

import { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } from "@pipedream/platform";
import mctime from "../../mctime.app.mjs";

export default {
  key: "mctime-new-time-entry-started",
  name: "New Time Entry Started",
  description: "Emit new event each time a new time entry is started",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  props: {
    mctime,
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
  },
  methods: {
    _getLastStarted() {
      return this.db.get("lastStarted");
    },
    _setLastStarted(lastStarted) {
      this.db.set("lastStarted", lastStarted);
    },
    generateMeta(data) {
      const {
        id, from,
      } = data;
      return {
        id,
        summary: `New Time Entry: ${id}`,
        ts: Date.parse(from),
      };
    },
    getDateTimeWithOffset(date) {
      date = new Date(date);
      const offsetMinutes = date.getTimezoneOffset();
      const offsetHours = Math.abs(Math.floor(offsetMinutes / 60));
      const offsetMinutesRemainder = Math.abs(offsetMinutes % 60);
      const offsetSign = offsetMinutes > 0
        ? "-"
        : "+";
      const offsetFormatted = offsetSign + (offsetHours < 10
        ? "0"
        : "") + offsetHours + ":" + (offsetMinutesRemainder < 10
        ? "0"
        : "") + offsetMinutesRemainder;
      const isoString = date.toISOString().split(".")[0];
      return isoString + offsetFormatted;
    },
  },
  async run() {
    const currentDate = new Date();
    const to = this.getDateTimeWithOffset(currentDate);
    let lastStarted = this._getLastStarted()
      || this.getDateTimeWithOffset(currentDate.setDate(currentDate.getDate() - 7)); // if no lastStarted get date from one week ago
    const params = {
      to,
      from: lastStarted,
      page: 1,
    };
    let total;
    do {
      const { items } = await this.mctime.getTimeEntries({
        params,
      });
      const timeEntries = items[0].data.timeEntries;
      for (const timeEntry of timeEntries) {
        for (const time of timeEntry.times) {
          if (Date.parse(time.from) > Date.parse(lastStarted)) {
            lastStarted = time.from;
          }
          const meta = this.generateMeta(time);
          this.$emit(time, meta);
        }
      }
      total = timeEntries?.length;
      params.page++;
    } while (total);
    this._setLastStarted(lastStarted);
  },
};

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
McTime	`mctime`	`app`	This component uses the McTime app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`

Trigger Authentication#

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

About McTime#

McTime's time recording helps small and large teams to record and evaluate project hours or absences. Fully automatic time recording included!

Action#

Create Vector Store on OpenAI (ChatGPT)

Description:Create a vector store. [See the documentation](https://platform.openai.com/docs/api-reference/vector-stores/create)

Version:0.0.5

Key:openai-create-vector-store

View on GitHub

OpenAI (ChatGPT) Overview#

OpenAI provides a suite of powerful AI models through its API, enabling developers to integrate advanced natural language processing and generative capabilities into their applications. Here’s an overview of the services offered by OpenAI's API:

Use Python or Node.js code to make fully authenticated API requests with your OpenAI account:

Action Code#

import openai from "../../openai.app.mjs";

export default {
  key: "openai-create-vector-store",
  name: "Create Vector Store",
  description: "Create a vector store. [See the documentation](https://platform.openai.com/docs/api-reference/vector-stores/create)",
  version: "0.0.5",
  type: "action",
  props: {
    openai,
    fileIds: {
      propDefinition: [
        openai,
        "fileId",
      ],
      type: "string[]",
      label: "File IDs",
      description: "An array of File IDs that the vector store should use",
      optional: true,
      reloadProps: true,
    },
    name: {
      type: "string",
      label: "Name",
      description: "Name of the vector store",
      optional: true,
    },
    expiryDays: {
      type: "integer",
      label: "Expiration Days",
      description: "The number of days after the `last_active_at` time that the vector store will expire",
      optional: true,
    },
    metadata: {
      type: "object",
      label: "Metadata",
      description: "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format",
      optional: true,
    },
  },
  additionalProps() {
    const props = {};
    if (!this.fileIds?.length) {
      return props;
    }

    props.chunkingStrategy = {
      type: "string",
      label: "Chunking Strategy",
      description: "The chunking strategy used to chunk the file(s)",
      options: [
        "auto",
        "static",
      ],
      optional: true,
      reloadProps: true,
    };

    if (this?.chunkingStrategy === "static") {
      props.maxChunkSizeTokens = {
        type: "integer",
        label: "Max Chunk Size Tokens",
        description: "The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`.",
        default: 800,
        optional: true,
      };
      props.chunkOverlapTokens = {
        type: "integer",
        label: "Chunk Overlap Tokens",
        description: "The number of tokens that overlap between chunks. The default value is `400`. Note that the overlap must not exceed half of max_chunk_size_tokens.",
        default: 400,
        optional: true,
      };
    }

    return props;
  },
  async run({ $ }) {
    const response = await this.openai.createVectorStore({
      $,
      data: {
        file_ids: this.fileIds,
        name: this.name,
        expires_after: this.expiryDays && {
          anchor: "last_active_at",
          days: this.expiryDays,
        },
        chunking_strategy: this.chunkingStrategy && {
          type: this.chunkingStrategy,
          static: this.chunkingStrategy === "static"
            ? {
              max_chunk_size_tokens: this.maxChunkSizeTokens,
              chunk_overlap_tokens: this.chunkOverlapTokens,
            }
            : undefined,
        },
        metadata: this.metadata,
      },
    });
    $.export("$summary", `Successfully created vector store with ID: ${response.id}`);
    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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
File IDs	`fileIds`	`string[]`	Select a value from the drop down menu.
Name	`name`	`string`	Name of the vector store
Expiration Days	`expiryDays`	`integer`	The number of days after the `last_active_at` time that the vector store will expire
Metadata	`metadata`	`object`	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format

Create Vector Store with OpenAI (ChatGPT) API on New Time Entry Started from McTime API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), McTime and 2,700+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,700+apps by most popular

1
-
24
of
2,700+
apps by most popular