Summarize with OpenAI Passthrough API on New Change in Envelope Status from Docusign API

Pipedream makes it easy to connect APIs for OpenAI Passthrough, Docusign and 2,700+ other apps remarkably fast.

Trigger workflow on

New Change in Envelope Status from the Docusign 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 Docusign 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 Change in Envelope Status trigger
1. Connect your Docusign account
2. Select a Account
3. Configure Polling Interval
4. Select one or more Status
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 Change in Envelope Status on Docusign

Description:Emit new event when an envelope's status is updated

Version:0.0.1

Key:docusign-new-change-in-envelope-status

View on GitHub

Docusign Overview#

The DocuSign API enables you to integrate electronic signature workflows into your applications, automate the process of sending and receiving documents for signatures, and securely manage related data. Leveraging Pipedream's platform, you can build powerful automations that streamline how contracts and agreements are handled, enhance compliance, and improve overall efficiency.

Trigger Code#

import docusign from "../../docusign.app.mjs";
import common from "./common.mjs";

export default {
  ...common,
  key: "docusign-new-change-in-envelope-status",
  version: "0.0.1",
  name: "New Change in Envelope Status",
  description: "Emit new event when an envelope's status is updated",
  type: "source",
  props: {
    docusign,
    account: {
      propDefinition: [
        docusign,
        "account",
      ],
    },
    ...common.props,
  },
};

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
Docusign	`docusign`	`app`	This component uses the Docusign app.
Account	`account`	`string`	Select a value from the drop down menu.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Polling Interval	`timer`	`$.interface.timer`	Pipedream will poll the Docusign API on this schedule
Status	`status`	`string[]`	Select a value from the drop down menu:`anycompletedcreateddeclineddeleteddeliveredprocessingsentsignedtimedoutvoided`

Trigger Authentication#

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

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

signatureextendedopenid

About Docusign#

Electronic Signature and Agreement Cloud

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.