Chat 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

Chat 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 Chat action
1. Connect your OpenAI Passthrough account
2. Select a Model ID
3. Configure User Message
4. Optional- Configure System Instructions
5. Optional- Configure Prior Message History
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- Select a Response Format
12. Optional- Configure JSON Schema
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#

Chat on OpenAI Passthrough

Description:The Chat API, using the `gpt-3.5-turbo` or `gpt-4` model. [See the documentation](https://platform.openai.com/docs/api-reference/chat)

Version:0.0.2

Key:openai-passthrough-chat

View on GitHub

Action Code#

const CHAT_RESPONSE_FORMAT = {
  TEXT: {
    label: "Text",
    value: "text",
  },
  JSON_OBJECT: {
    label: "JSON Object",
    value: "json_object",
  },
  JSON_SCHEMA: {
    label: "JSON Schema",
    value: "json_schema",
  },
}

export default {
  name: "Chat",
  version: "0.0.2",
  key: "openai-passthrough-chat",
  description:
    "The Chat API, using the `gpt-3.5-turbo` or `gpt-4` model. [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"],
    },
    userMessage: {
      label: "User Message",
      type: "string",
      description:
        "The user messages provide instructions to the assistant. They can be generated by the end users of an application, or set by a developer as an instruction.",
    },
    systemInstructions: {
      label: "System Instructions",
      type: "string",
      description:
        'The system message helps set the behavior of the assistant. For example: "You are a helpful assistant." [See these docs](https://platform.openai.com/docs/guides/chat/instructing-chat-models) for tips on writing good instructions.',
      optional: true,
    },
    messages: {
      label: "Prior Message History",
      type: "string[]",
      description:
        "_Advanced_. Because [the models have no memory of past chat 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** and **Assistant Response**, appends the new **User Message** to the end of this array, and sends it to the API.",
      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 completion",
      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,
    },
    responseFormat: {
      type: "string",
      label: "Response Format",
      description:
        "- **Text**: Returns unstructured text output.\n- **JSON Schema**: Enables you to define a [specific structure for the model's output using a JSON schema](https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses).",
      options: Object.values(CHAT_RESPONSE_FORMAT),
      default: CHAT_RESPONSE_FORMAT.TEXT.value,
      optional: true,
    },
    jsonSchema: {
      type: "string",
      label: "JSON Schema",
      description:
        "If responseFormat is jsonSchema: Define the schema that the model's output must adhere to. [See the documentation here](https://platform.openai.com/docs/guides/structured-outputs/supported-schemas).",
      optional: true,
    },
  },
  async run({ $ }) {
    const messages = []

    // Add system message if provided
    if (this.systemInstructions) {
      messages.push({
        role: "system",
        content: this.systemInstructions,
      })
    }

    // Use provided message history or create a new conversation
    if (this.messages && this.messages.length > 0) {
      messages.push(...this.messages)
    }

    // Add the user message
    messages.push({
      role: "user",
      content: this.userMessage,
    })

    // 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

    // Handle response format if specified
    if (
      this.responseFormat === CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value &&
      this.jsonSchema
    ) {
      params.response_format = {
        type: "json_object",
        schema: JSON.parse(this.jsonSchema),
      }
    } else if (this.responseFormat === CHAT_RESPONSE_FORMAT.JSON_OBJECT.value) {
      params.response_format = { type: "json_object" }
    }

    // Call the OpenAI API using the Pipedream service
    const response = await $.services.openai.completions.create(params)

    // Extract and process the response
    const assistantMessage = response.choices[0].message.content

    // Export a summary for the user
    $.export("$summary", "Generated response from OpenAI")

    // Return the assistant message and the full response
    return {
      message: assistantMessage,
      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`
User Message	`userMessage`	`string`	The user messages provide instructions to the assistant. They can be generated by the end users of an application, or set by a developer as an instruction.
System Instructions	`systemInstructions`	`string`	The system message helps set the behavior of the assistant. For example: "You are a helpful assistant." See these docs for tips on writing good instructions.
Prior Message History	`messages`	`string[]`	Advanced. Because the models have no memory of past chat 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 and Assistant Response, appends the new User Message to the end of this array, and sends it to the API.
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 completion
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
Response Format	`responseFormat`	`string`	Select a value from the drop down menu:`{ "label": "Text", "value": "text" }{ "label": "JSON Object", "value": "json_object" }{ "label": "JSON Schema", "value": "json_schema" }`
JSON Schema	`jsonSchema`	`string`	If responseFormat is jsonSchema: Define the schema that the model's output must adhere to. See the documentation here