Summarize with OpenAI Passthrough API on New Daily Summary Report Created from RescueTime API

Pipedream makes it easy to connect APIs for OpenAI Passthrough, RescueTime and 2,800+ other apps remarkably fast.

Trigger workflow on

New Daily Summary Report Created from the RescueTime API

Next, do this

Summarize with the OpenAI Passthrough 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 RescueTime trigger and OpenAI Passthrough action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Daily Summary Report Created trigger
1. Connect your RescueTime account
2. Configure timer
Configure the Summarize action
1. Connect your OpenAI Passthrough account
2. Select a Model ID
3. Configure Text
4. Optional- Select a Summary Length
5. Optional- Configure Focus Area
6. Optional- Configure Temperature
7. Optional- Configure Maximum Length
8. Optional- Configure Top P
9. Optional- Configure Frequency Penalty
10. Optional- Configure Presence Penalty
11. Optional- Configure Prior Message History
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 Daily Summary Report Created on RescueTime

Description:Emit new event each time a new daily summary report is available. [See the docs here](https://www.rescuetime.com/rtx/developers#daily-summary-feed-reference)

Version:0.0.1

Key:rescuetime-new-daily-summary-report-created

View on GitHub

RescueTime Overview#

The RescueTime API provides access to detailed data about how you spend your time on digital devices, including time spent on apps and websites. With this API on Pipedream, you can create custom workflows that trigger actions based on your productivity data. For instance, you can set up alerts for excessive social media usage or automate weekly productivity reports. Pipedream's platform enables these automations by connecting RescueTime to hundreds of other apps, allowing for intricate workflows that can enhance personal productivity and time management.

Trigger Code#

import rescuetime from "../../rescuetime.app.mjs";
const TIMER_INTERVAL_MILLISECONDS = 24 * 60 * 60 * 1000; // 24 hours

export default {
  key: "rescuetime-new-daily-summary-report-created",
  name: "New Daily Summary Report Created",
  description: "Emit new event each time a new daily summary report is available. [See the docs here](https://www.rescuetime.com/rtx/developers#daily-summary-feed-reference)",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  props: {
    rescuetime,
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: TIMER_INTERVAL_MILLISECONDS,
      },
    },
  },
  methods: {
    generateMeta(report) {
      return {
        id: report.id,
        summary: `New Daily Summary Report created with ID ${report.id}`,
        ts: Date.now(),
      };
    },
  },
  async run() {
    const reports = await this.rescuetime.getDailySummaryFeed();
    for (const report of reports) {
      const meta = this.generateMeta(report);
      this.$emit(report, meta);
    }
  },
};

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

Trigger Authentication#

RescueTime uses OAuth authentication. When you connect your RescueTime account, Pipedream will open a popup window where you can sign into RescueTime and grant Pipedream permission to connect to your account. Pipedream securely stores and automatically refreshes the OAuth tokens so you can easily authenticate any RescueTime API.

Pipedream requests the following authorization scopes when you connect your account:

time_datacategory_dataproductivity_dataalert_datahighlight_datafocustime_data

About RescueTime#

A personal analytics service that shows you how you spend your time and provides tools to help you be more productive.

Action#

Summarize on OpenAI Passthrough

Description:Summarizes text using the OpenAI API. [See the documentation](https://platform.openai.com/docs/api-reference/chat)

Version:0.0.1

Key:openai-passthrough-summarize

View on GitHub

Action Code#

const SUMMARIZE_LENGTH = {
  SHORT: {
    label: "Short",
    value: "short",
  },
  MEDIUM: {
    label: "Medium",
    value: "medium",
  },
  LONG: {
    label: "Long",
    value: "long",
  },
}

export default {
  name: "Summarize",
  version: "0.0.1",
  key: "openai-passthrough-summarize",
  description:
    "Summarizes text using the OpenAI API. [See the documentation](https://platform.openai.com/docs/api-reference/chat)",
  type: "action",
  props: {
    app: {
      type: "app",
      app: "openai_passthrough",
    },
    modelId: {
      label: "Model ID",
      type: "string",
      options: ["gpt-4.1", "o4-mini", "o3", "gpt-3.5-turbo"],
    },
    text: {
      label: "Text",
      type: "string",
      description: "The text to summarize.",
    },
    summaryLength: {
      label: "Summary Length",
      type: "string",
      description: "The desired length of the summary.",
      options: Object.values(SUMMARIZE_LENGTH),
      default: SUMMARIZE_LENGTH.MEDIUM.value,
      optional: true,
    },
    focusArea: {
      label: "Focus Area",
      type: "string",
      description: "Specific aspects of the text to focus on in the summary.",
      optional: true,
    },
    temperature: {
      type: "string",
      label: "Temperature",
      description:
        "Controls randomness: 0 is deterministic, higher values (up to 2) make output more random",
      default: "1",
      optional: true,
    },
    maxTokens: {
      type: "integer",
      label: "Maximum Length",
      description: "The maximum number of tokens to generate in the summary",
      optional: true,
    },
    topP: {
      type: "string",
      label: "Top P",
      description:
        "Alternative to temperature, nucleus sampling considers the results of the tokens with top_p probability mass",
      default: "1",
      optional: true,
    },
    frequencyPenalty: {
      type: "string",
      label: "Frequency Penalty",
      description:
        "Decreases the likelihood of repeating the same line verbatim",
      default: "0",
      optional: true,
    },
    presencePenalty: {
      type: "string",
      label: "Presence Penalty",
      description: "Increases the likelihood of talking about new topics",
      default: "0",
      optional: true,
    },
    messages: {
      label: "Prior Message History",
      type: "string[]",
      description:
        "_Advanced_. Because [the models have no memory of past requests](https://platform.openai.com/docs/guides/chat/introduction), all relevant information must be supplied via the conversation. You can provide [an array of messages](https://platform.openai.com/docs/guides/chat/introduction) from prior conversations here. If this param is set, the action ignores the values passed to **System Instructions**, appends the new **Text** to summarize to the end of this array, and sends it to the API.",
      optional: true,
    },
  },
  async run({ $ }) {
    const messages = []

    // Add system message with summary instructions
    let systemInstructions = "You are a skilled summarizer. Create a"
    
    // Customize instructions based on summary length
    switch (this.summaryLength) {
      case SUMMARIZE_LENGTH.SHORT.value:
        systemInstructions += " brief and concise"
        break
      case SUMMARIZE_LENGTH.LONG.value:
        systemInstructions += " detailed and thorough"
        break
      default:
        systemInstructions += " comprehensive but focused"
    }
    
    systemInstructions += " summary of the following content."
    
    // Add focus area if provided
    if (this.focusArea) {
      systemInstructions += ` Focus particularly on aspects related to: ${this.focusArea}.`
    }

    // Use provided message history or create a new conversation
    if (this.messages && this.messages.length > 0) {
      messages.push(...this.messages)
    } else {
      // Add system message
      messages.push({
        role: "system",
        content: systemInstructions,
      })
    }
    
    // Add the text to summarize as the user message
    messages.push({
      role: "user",
      content: this.text,
    })
    
    // Prepare request parameters
    const params = {
      model: this.modelId,
      messages: messages,
    }
    
    // Add optional parameters if provided
    if (this.temperature !== undefined) params.temperature = +this.temperature
    if (this.maxTokens !== undefined) params.max_tokens = this.maxTokens
    if (this.topP !== undefined) params.top_p = +this.topP
    if (this.frequencyPenalty !== undefined)
      params.frequency_penalty = +this.frequencyPenalty
    if (this.presencePenalty !== undefined)
      params.presence_penalty = +this.presencePenalty
    
    // Call the OpenAI API using the Pipedream service
    const response = await $.services.openai.completions.create(params)
    
    // Extract the summary from the response
    const summary = response.choices[0].message.content
    
    // Export a summary for the user
    $.export("$summary", "Generated summary from OpenAI")
    
    // Return the summary and the full response
    return {
      summary,
      raw_response: 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 Passthrough	`app`	`app`	This component uses the OpenAI Passthrough app.
Model ID	`modelId`	`string`	Select a value from the drop down menu:`gpt-4.1o4-minio3gpt-3.5-turbo`
Text	`text`	`string`	The text to summarize.
Summary Length	`summaryLength`	`string`	Select a value from the drop down menu:`{ "label": "Short", "value": "short" }{ "label": "Medium", "value": "medium" }{ "label": "Long", "value": "long" }`
Focus Area	`focusArea`	`string`	Specific aspects of the text to focus on in the summary.
Temperature	`temperature`	`string`	Controls randomness: 0 is deterministic, higher values (up to 2) make output more random
Maximum Length	`maxTokens`	`integer`	The maximum number of tokens to generate in the summary
Top P	`topP`	`string`	Alternative to temperature, nucleus sampling considers the results of the tokens with top_p probability mass
Frequency Penalty	`frequencyPenalty`	`string`	Decreases the likelihood of repeating the same line verbatim
Presence Penalty	`presencePenalty`	`string`	Increases the likelihood of talking about new topics
Prior Message History	`messages`	`string[]`	Advanced. Because the models have no memory of past requests, all relevant information must be supplied via the conversation. You can provide an array of messages from prior conversations here. If this param is set, the action ignores the values passed to System Instructions, appends the new Text to summarize to the end of this array, and sends it to the API.