Summarize Text with OpenAI (ChatGPT) API on New Transcription Completed from AssemblyAI API

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

Trigger workflow on

New Transcription Completed from the AssemblyAI API

Next, do this

Summarize Text 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 AssemblyAI 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 Transcription Completed trigger
1. Connect your AssemblyAI account
2. Configure timer
Configure the Summarize Text action
1. Connect your OpenAI (ChatGPT) account
2. Select a Model
3. Optional- Configure Max Tokens
4. Optional- Configure Temperature
5. Optional- Configure Top P
6. Optional- Configure N
7. Optional- Configure Stop
8. Optional- Configure Presence Penalty
9. Optional- Configure Frequency Penalty
10. Optional- Configure User
11. Configure Text
12. Optional- Select a Summary Length
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 Transcription Completed on AssemblyAI

Description:Emit new event when a transcribed audio file from AssemblyAI is ready. [See the documentation](https://www.assemblyai.com/docs/api-reference/transcripts/list)

Version:0.1.0

Key:assemblyai-new-transcription-completed

View on GitHub

AssemblyAI Overview#

The AssemblyAI API provides powerful speech recognition and natural language processing capabilities. It allows users to transcribe audio, analyze sentiment, detect topics, and more. In Pipedream, you can leverage these features to create automated workflows that process audio and text data. Connect AssemblyAI to various apps and services, trigger actions based on the API's output, and build robust, serverless data pipelines.

Trigger Code#

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

export default {
  name: "New Transcription Completed",
  description: "Emit new event when a transcribed audio file from AssemblyAI is ready. [See the documentation](https://www.assemblyai.com/docs/api-reference/transcripts/list)",
  key: "assemblyai-new-transcription-completed",
  version: "0.1.0",
  type: "source",
  dedupe: "unique",
  props: {
    assemblyai,
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
  },
  hooks: {
    async deploy() {
      const { transcripts } = await this.assemblyai.listTranscripts({
        params: {
          status: "completed",
          limit: 25,
        },
      });
      if (!transcripts.length) {
        return;
      }
      this._setLastId(transcripts[0].id);
      await this.emitTranscripts(transcripts);
    },
  },
  methods: {
    _getLastId() {
      return this.db.get("lastId");
    },
    _setLastId(lastId) {
      this.db.set("lastId", lastId);
    },
    emitEvent(transcript) {
      const meta = this.generateMeta(transcript);
      this.$emit(transcript, meta);
    },
    async emitTranscripts(transcripts) {
      for (const transcript of transcripts.reverse()) {
        const data = await this.assemblyai.getTranscript({
          transcriptId: transcript.id,
        });
        this.emitEvent(data);
      }
    },
    generateMeta(transcript) {
      return {
        id: transcript.id,
        summary: `New Transcript ID ${transcript.id}`,
        ts: Date.now(),
      };
    },
  },
  async run() {
    const lastId = this._getLastId();
    const transcripts = await this.assemblyai.paginateTranscripts({
      params: {
        status: "completed",
        after_id: lastId,
      },
    });
    if (!transcripts.length) {
      return;
    }

    this._setLastId(transcripts[0].id);

    await this.emitTranscripts(transcripts);
  },
};

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

Trigger Authentication#

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

About AssemblyAI#

Access powerful AI models to transcribe and understand speech via a simple API.

Action#

Summarize Text on OpenAI (ChatGPT)

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

Version:0.1.8

Key:openai-summarize

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 common from "../common/common-helper.mjs";
import constants from "../../common/constants.mjs";

export default {
  ...common,
  name: "Summarize Text",
  version: "0.1.8",
  key: "openai-summarize",
  description: "Summarizes text using the Chat API. [See the documentation](https://platform.openai.com/docs/api-reference/chat)",
  type: "action",
  props: {
    ...common.props,
    text: {
      label: "Text",
      description: "The text to summarize",
      type: "string",
    },
    length: {
      label: "Summary Length",
      description: "The length of the summary",
      type: "string",
      optional: true,
      options: constants.SUMMARIZE_LENGTH,
    },
  },
  methods: {
    ...common.methods,
    systemInstructions() {
      return "Your goal is to summarize the text the user provides. Please follow the length guidelines presented in the prompt.";
    },
    maxLength() {
      return this.length
        ? ` in one ${this.length}`
        : "";
    },
    userMessage() {
      return `Summarize the following text${this.maxLength()}: ${this.text}`;
    },
    formatOutput({
      messages, response,
    }) {
      if (!messages || !response) {
        throw new Error("Invalid API output, please reach out to https://pipedream.com/support");
      }
      const output = {
        messages,
      };
      if (this.n > 1) {
        output.summaries = response.choices?.map(({ message }) => message.content);
      } else {
        output.summary = response.choices?.[0]?.message?.content;
      }
      return output;
    },
  },
};

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.
Model	`modelId`	`string`	Select a value from the drop down menu.
Max Tokens	`maxTokens`	`integer`	The maximum number of tokens to generate in the completion.
Temperature	`temperature`	`string`	Optional. What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.
Top P	`topP`	`string`	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
N	`n`	`integer`	How many completions to generate for each prompt
Stop	`stop`	`string[]`	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
Presence Penalty	`presencePenalty`	`string`	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
Frequency Penalty	`frequencyPenalty`	`string`	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
User	`user`	`string`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more here
Text	`text`	`string`	The text to summarize
Summary Length	`length`	`string`	Select a value from the drop down menu:`wordsentenceparagraphpage`

Summarize Text with OpenAI (ChatGPT) API on New Transcription Completed from AssemblyAI API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), AssemblyAI 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