Chat with Google PaLM API on New or Modified Comments (Instant) from Google Drive API

Pipedream makes it easy to connect APIs for Google PaLM, Google Drive and 2,200+ other apps remarkably fast.

Trigger workflow on

New or Modified Comments (Instant) from the Google Drive API

Next, do this

Chat with the Google PaLM 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 Google Drive trigger and Google PaLM action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New or Modified Comments (Instant) trigger
1. Connect your Google Drive account
2. Select a Drive
3. Configure Push notification renewal schedule
4. Select a File
Configure the Chat action
1. Connect your Google PaLM account
2. Configure Prompt Text
3. Optional- Configure Previous Messages
4. Optional- Configure Temperature
5. Optional- Configure Context
6. Optional- Configure Candidate Count
7. Optional- Configure Top K
8. Optional- Configure Top P
9. Optional- Configure Max Output Tokens
10. Optional- Configure Stop Sequences
11. Optional- Select one or more Harm Categories
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 or Modified Comments (Instant) on Google Drive

Description:Emit new event when a comment is created or modified in the selected file

Version:1.0.2

Key:google_drive-new-or-modified-comments

View on GitHub

Google Drive Overview#

The Google Drive API on Pipedream allows you to automate various file management tasks, such as creating, reading, updating, and deleting files within your Google Drive. You can also share files, manage permissions, and monitor changes to files and folders. This opens up possibilities for creating workflows that seamlessly integrate with other apps and services, streamlining document handling, backup processes, and collaborative workflows.

Trigger Code#

// This source processes changes to any files in a user's Google Drive,
// implementing strategy enumerated in the Push Notifications API docs:
// https://developers.google.com/drive/api/v3/push and here:
// https://developers.google.com/drive/api/v3/manage-changes
//
// This source has two interfaces:
//
// 1) The HTTP requests tied to changes in the user's Google Drive
// 2) A timer that runs on regular intervals, renewing the notification channel as needed

import common from "../common-webhook.mjs";
import { GOOGLE_DRIVE_NOTIFICATION_CHANGE } from "../../common/constants.mjs";

export default {
  ...common,
  key: "google_drive-new-or-modified-comments",
  name: "New or Modified Comments (Instant)",
  description:
    "Emit new event when a comment is created or modified in the selected file",
  version: "1.0.2",
  type: "source",
  // Dedupe events based on the "x-goog-message-number" header for the target channel:
  // https://developers.google.com/drive/api/v3/push#making-watch-requests
  dedupe: "unique",
  props: {
    ...common.props,
    fileId: {
      propDefinition: [
        common.props.googleDrive,
        "fileId",
        (c) => ({
          drive: c.drive,
        }),
      ],
      description: "The file to watch for comments",
    },
  },
  hooks: {
    async deploy() {
      await this.processChanges([
        {
          id: this.fileId,
        },
      ]);
    },
    async activate() {
      await common.hooks.activate.bind(this)();
      this._setInitTime(Date.now());
    },
    async deactivate() {
      await common.hooks.deactivate.bind(this)();
      this._setInitTime(null);
    },
  },
  methods: {
    ...common.methods,
    _getInitTime() {
      return this.db.get("initTime");
    },
    _setInitTime(initTime) {
      this.db.set("initTime", initTime);
    },
    _getLastCommentTimeForFile(fileId) {
      return this.db.get(fileId) || this._getInitTime();
    },
    _updateLastCommentTimeForFile(fileId, commentTime) {
      this.db.set(fileId, commentTime);
    },
    getUpdateTypes() {
      return [
        GOOGLE_DRIVE_NOTIFICATION_CHANGE,
      ];
    },
    generateMeta(data, headers) {
      const {
        id: commentId,
        content: summary,
        modifiedTime: tsString,
      } = data;
      const ts = Date.parse(tsString);
      const eventId = headers && headers["x-goog-message-number"];

      return {
        id: `${commentId}-${eventId || ts}`,
        summary,
        ts,
      };
    },
    getChanges(headers) {
      if (!headers) {
        return {
          change: { },
        };
      }
      return {
        change: {
          state: headers["x-goog-resource-state"],
          resourceURI: headers["x-goog-resource-uri"],
          // Additional details about the changes. Possible values: content,
          // parents, children, permissions.
          changed: headers["x-goog-changed"],
        },
      };
    },
    async processChanges(changedFiles, headers) {
      const changes = this.getChanges(headers);
      if (changedFiles?.length) {
        changedFiles = changedFiles.filter(({ id }) => id === this.fileId);
      }

      for (const file of changedFiles) {
        const lastCommentTimeForFile = this._getLastCommentTimeForFile(file.id);
        let maxModifiedTime = lastCommentTimeForFile;
        const commentsStream = this.googleDrive.listComments(
          file.id,
          lastCommentTimeForFile,
        );

        for await (const comment of commentsStream) {
          const commentTime = Date.parse(comment.modifiedTime);
          if (commentTime <= lastCommentTimeForFile) {
            continue;
          }

          const eventToEmit = {
            comment,
            ...changes,
          };
          const meta = this.generateMeta(comment, headers);
          this.$emit(eventToEmit, meta);

          maxModifiedTime = Math.max(maxModifiedTime, commentTime);
          this._updateLastCommentTimeForFile(file.id, maxModifiedTime);
        }
      }
    },
  },
};

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
Google Drive	`googleDrive`	`app`	This component uses the Google Drive app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
N/A	`http`	`$.interface.http`	This component uses `$.interface.http` to generate a unique URL when the component is first instantiated. Each request to the URL will trigger the `run()` method of the component.
Drive	`drive`	`string`	Select a value from the drop down menu.
Push notification renewal schedule	`timer`	`$.interface.timer`	The Google Drive API requires occasional renewal of push notification subscriptions. This runs in the background, so you should not need to modify this schedule.
File	`fileId`	`string`	Select a value from the drop down menu.

Trigger Authentication#

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

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

https://www.googleapis.com/auth/drive

About Google Drive#

Google Drive is a file storage and synchronization service which allows you to create and share your work online, and access your documents from anywhere.

Action#

Chat on Google PaLM

Description:Chat using Google PaLM. [See the docs here](https://developers.generativeai.google/api/python/google/generativeai/chat)

Version:0.0.2

Key:google_palm_api-chat

View on GitHub

Google PaLM Overview#

The Google PaLM API is a cutting-edge language model that allows developers to integrate advanced natural language understanding into their applications. On Pipedream, you can harness this power to create serverless workflows that react to various triggers and perform actions based on the insights and outputs from PaLM. Whether it's generating content, summarizing text, or understanding user intent, PaLM's capabilities can be integrated into Pipedream workflows to automate complex tasks involving language.

Action Code#

import app from "../../google_palm_api.app.mjs";
import constants from "../../common/constants.mjs";

export default {
  key: "google_palm_api-chat",
  name: "Chat",
  description: "Chat using Google PaLM. [See the docs here](https://developers.generativeai.google/api/python/google/generativeai/chat)",
  version: "0.0.2",
  type: "action",
  props: {
    app,
    promptText: {
      type: "string",
      label: "Prompt Text",
      description: "The text to be used as a prompt for the chat",
    },
    previousMessages: {
      type: "string[]",
      label: "Previous Messages",
      description: "The previous messages in the chat. If provided, will override the chat history",
      optional: true,
    },
    temperature: {
      type: "string",
      label: "Temperature",
      description: `The temperature to use for the chat. Values can range from [0.0,1.0], inclusive.
        A value closer to 1.0 will produce responses that are more varied and creative, while a value closer to 0.0 will typically result in more straightforward responses from the model.
        Defaults to \`0.5\``,
      optional: true,
    },
    context: {
      type: "string",
      label: "Context",
      description: "Text that should be provided to the model first, to ground the response",
      optional: true,
    },
    candidateCount: {
      type: "integer",
      label: "Candidate Count",
      description: "The maximum number of generated response messages to return. This value must be between [1, 8], inclusive. If unset, this will default to 1. Note: Only unique candidates are returned. Higher temperatures are more likely to produce unique candidates. Setting temperature=0.0 will always return 1 candidate regardless of the candidate_count.",
      optional: true,
      default: 1,
      min: 1,
      max: 8,
    },
    topK: {
      type: "string",
      label: "Top K",
      description: "The API uses combined nucleus and top-k sampling. top_k sets the maximum number of tokens to sample from on each step.",
      optional: true,
    },
    topP: {
      type: "string",
      label: "Top P",
      description: "  The API uses combined nucleus and top-k sampling. top_p configures the nucleus sampling. It sets the maximum cumulative probability of tokens to sample from. For example, if the sorted probabilities are [0.5, 0.2, 0.1, 0.1, 0.05, 0.05] a top_p of 0.8 will sample as [0.625, 0.25, 0.125, 0, 0, 0]. Typical values are in the [0.9, 1.0] range.",
      optional: true,
    },
    maxOutputTokens: {
      type: "integer",
      label: "Max Output Tokens",
      description: "Maximum number of tokens to include in a candidate. Must be greater than zero. If unset, will default to 64.",
      optional: true,
    },
    stopSequences: {
      type: "string",
      label: "Stop Sequences",
      description: "A set of up to 5 character sequences that will stop output generation. If specified, the API will stop at the first appearance of a stop sequence. The stop sequence will not be included as part of the response.",
      optional: true,
    },
    harmCategories: {
      type: "string[]",
      label: "Harm Categories",
      description: "To set safety settings, select the harm categories to set a threshold for",
      optional: true,
      options() {
        return constants.HARM_CATEGORIES.map(({
          value, label,
        }) => ({
          value,
          label,
        }));
      },
      reloadProps: true,
    },
  },
  async additionalProps() {
    const props = {};
    if (!this.harmCategories?.length) {
      return props;
    }
    for (const category of this.harmCategories) {
      props[`${category}_threshold`] = {
        type: "string",
        label: `${category} - Harm Block Threshold`,
        description: `Select the harm block threshold to set for the category ${category}`,
        options: this.getThresholdOptions(),
      };
    }
    return props;
  },
  methods: {
    getThresholdOptions() {
      return constants.HARM_BLOCK_THRESHOLD.map(({
        value, label,
      }) => ({
        value,
        label,
      }));
    },
    async chat({
      promptText,
      previousMessages,
      temperature,
      context,
      candidateCount,
      topK,
      topP,
      maxOutputTokens,
      stopSequences,
      safetySettings,
    }) {
      return this.app.chat({
        temperature,
        prompt: {
          context,
          messages: [
            ...previousMessages.map((message) => ({
              content: message,
            })),
            {
              content: promptText,
            },
          ],
        },
        candidate_count: candidateCount,
        top_k: topK
          ? +topK
          : undefined,
        top_p: topP
          ? +topP
          : undefined,
        max_output_tokens: maxOutputTokens,
        stop_sequences: stopSequences,
        safety_settings: safetySettings,
      });
    },
  },
  async run({ $ }) {
    const safetySettings = [];
    if (this.harmCategories?.length) {
      for (const category of this.harmCategories) {
        const threshold = constants.HARM_BLOCK_THRESHOLD.find(({ value }) => value === this[`${category}_threshold`]);
        safetySettings.push({
          category: (constants.HARM_CATEGORIES.find(({ value }) => value === category)).numValue,
          threshold: threshold?.numValue,
        });
      }
    }

    const response = await this.chat({
      promptText: this.promptText,
      previousMessages: this.previousMessages || [],
      temperature: parseFloat(this.temperature || "0.5"),
      context: this.context,
      candidteaCount: this.candidateCount,
      topK: this.topK,
      topP: this.topP,
      maxOutputTokens: this.maxOutputTokens,
      stopSequences: this.stopSequences,
      safetySettings,
    });
    $.export("$summary", "Successfully received response from Google PaLM");
    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
Google PaLM	`app`	`app`	This component uses the Google PaLM app.
Prompt Text	`promptText`	`string`	The text to be used as a prompt for the chat
Previous Messages	`previousMessages`	`string[]`	The previous messages in the chat. If provided, will override the chat history
Temperature	`temperature`	`string`	The temperature to use for the chat. Values can range from [0.0,1.0], inclusive. A value closer to 1.0 will produce responses that are more varied and creative, while a value closer to 0.0 will typically result in more straightforward responses from the model. Defaults to `0.5`
Context	`context`	`string`	Text that should be provided to the model first, to ground the response
Candidate Count	`candidateCount`	`integer`	The maximum number of generated response messages to return. This value must be between [1, 8], inclusive. If unset, this will default to 1. Note: Only unique candidates are returned. Higher temperatures are more likely to produce unique candidates. Setting temperature=0.0 will always return 1 candidate regardless of the candidate_count.
Top K	`topK`	`string`	The API uses combined nucleus and top-k sampling. top_k sets the maximum number of tokens to sample from on each step.
Top P	`topP`	`string`	The API uses combined nucleus and top-k sampling. top_p configures the nucleus sampling. It sets the maximum cumulative probability of tokens to sample from. For example, if the sorted probabilities are [0.5, 0.2, 0.1, 0.1, 0.05, 0.05] a top_p of 0.8 will sample as [0.625, 0.25, 0.125, 0, 0, 0]. Typical values are in the [0.9, 1.0] range.
Max Output Tokens	`maxOutputTokens`	`integer`	Maximum number of tokens to include in a candidate. Must be greater than zero. If unset, will default to 64.
Stop Sequences	`stopSequences`	`string`	A set of up to 5 character sequences that will stop output generation. If specified, the API will stop at the first appearance of a stop sequence. The stop sequence will not be included as part of the response.
Harm Categories	`harmCategories`	`string[]`	Select a value from the drop down menu.

Action Authentication#

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

Generate an API key or join the PaLM waitlist here, then enter your API key below.

About Google PaLM#

Build generative AI applications with Google's PaLM 2 model.

More Ways to Connect Google PaLM + Google Drive#

Other Popular Integrations#

Chat with Google PaLM API on Changes to Specific Files from Google Drive API

Google Drive + Google PaLM

Chat with Google PaLM API on New or Modified Comments (Instant) from Google Drive API

Pipedream makes it easy to connect APIs for Google PaLM, Google Drive and 2,200+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,200+apps by most popular

1
-
24
of
2,200+
apps by most popular