Create Chat Completion with DeepSeek API on Changes to Specific Files from Google Drive API

Pipedream makes it easy to connect APIs for DeepSeek, Google Drive and 2,700+ other apps remarkably fast.

Trigger workflow on

Changes to Specific Files from the Google Drive API

Next, do this

Create Chat Completion with the DeepSeek 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 DeepSeek action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the Changes to Specific Files trigger
1. Connect your Google Drive account
2. Optional- Configure Drive
3. Configure Push notification renewal schedule
4. Select one or more Files
5. Configure intervalAlert
6. Optional- Configure Minimum Interval Per File
7. Select one or more Types of updates
Configure the Create Chat Completion action
1. Connect your DeepSeek account
2. Configure Messages
3. Optional- Configure Frequency Penalty
4. Optional- Configure Max Tokens
5. Optional- Configure Presence Penalty
6. Optional- Select a Response Format Type
7. Optional- Configure Stop Sequences
8. Optional- Configure Stream
9. Optional- Configure Stream Include Usage
10. Optional- Configure Temperature
11. Optional- Configure Top P
12. Optional- Configure Tools
13. Optional- Configure Tool Choice
14. Optional- Configure Log Probs
15. Optional- Configure Top Log Probabilities
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#

Changes to Specific Files on Google Drive

Description:Watches for changes to specific files, emitting an event when a change is made to one of those files. To watch for changes to [shared drive](https://support.google.com/a/users/answer/9310351) files, use the **Changes to Specific Files (Shared Drive)** source instead.

Version:0.2.6

Key:google_drive-changes-to-specific-files

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#

import cronParser from "cron-parser";
import sampleEmit from "./test-event.mjs";
import includes from "lodash/includes.js";
import { v4 as uuid } from "uuid";
import { MY_DRIVE_VALUE } from "../../common/constants.mjs";
import changesToSpecificFiles from "../changes-to-specific-files-shared-drive/changes-to-specific-files-shared-drive.mjs";

/**
 * This source uses the Google Drive API's
 * {@link https://developers.google.com/drive/api/v3/reference/files/watch files: watch}
 * endpoint to subscribe to changes to specific files in the user's drive.
 */
export default {
  ...changesToSpecificFiles,
  key: "google_drive-changes-to-specific-files",
  name: "Changes to Specific Files",
  description: "Watches for changes to specific files, emitting an event when a change is made to one of those files. To watch for changes to [shared drive](https://support.google.com/a/users/answer/9310351) files, use the **Changes to Specific Files (Shared Drive)** source instead.",
  version: "0.2.6",
  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: {
    ...changesToSpecificFiles.props,
    drive: {
      type: "string",
      label: "Drive",
      description: "Defaults to `My Drive`. To use a [Shared Drive](https://support.google.com/a/users/answer/9310351), use the **Changes to Specific Files (Shared Drive)** source instead.",
      optional: true,
      default: MY_DRIVE_VALUE,
    },
    updateTypes: {
      propDefinition: [
        changesToSpecificFiles.props.googleDrive,
        "updateTypes",
      ],
    },
  },
  hooks: {
    ...changesToSpecificFiles.hooks,
    async activate() {
      // Called when a component is created or updated. Handles all the logic
      // for starting and stopping watch notifications tied to the desired
      // files.

      // You can pass the same channel ID in watch requests for multiple files, so
      // our channel ID is fixed for this component to simplify the state we have to
      // keep track of.
      const channelID = uuid();

      // Subscriptions are keyed on Google's resourceID, "an opaque value that
      // identifies the watched resource". This value is included in request
      // headers, allowing us to look up the watched resource.
      let subscriptions = this._getSubscriptions() || {};

      const files = this.files;
      for (const fileID of files) {
        const {
          expiration,
          resourceId,
        } = await this.googleDrive.activateFileHook(
          channelID,
          this.http.endpoint,
          fileID,
        );
        // The fileID must be kept with the subscription metadata so we can
        // renew the watch request for this specific file when it expires.
        subscriptions[resourceId] = {
          expiration,
          fileID,
        };
      }

      // Save metadata on the subscription so we can stop / renew later
      this._setSubscriptions(subscriptions);
      this._setChannelID(channelID);
    },
    async deactivate() {
      const channelID = this._getChannelID();
      if (!channelID) {
        console.log(
          "Channel not found, cannot stop notifications for non-existent channel",
        );
        return;
      }

      const subscriptions = this._getSubscriptions() || {};
      for (const resourceId of Object.keys(subscriptions)) {
        await this.googleDrive.stopNotifications(channelID, resourceId);
      }

      // Reset DB state
      this._setSubscriptions({});
      this._setChannelID(null);
    },
  },
  methods: {
    ...changesToSpecificFiles.methods,
    _getSubscriptions() {
      return this.db.get("subscriptions") || {};
    },
    _setSubscriptions(subscriptions) {
      this.db.set("subscriptions", subscriptions);
    },
    _getNextTimerEventTimestamp(event) {
      if (event.cron) {
        return cronParser
          .parseExpression(event.cron)
          .next()
          .getTime();
      }
      if (event.interval_seconds) {
        return Date.now() + event.interval_seconds * 1000;
      }
    },
    async renewFileSubscriptions(event) {
      const subscriptions = this._getSubscriptions() || {};
      const channelID = this._getChannelID();
      const newChannelID = uuid();

      const nextRunTimestamp = this._getNextTimerEventTimestamp(event);

      for (const [
        currentResourceId,
        metadata,
      ] of Object.entries(subscriptions)) {
        const { fileID } = metadata;

        const subscription = {
          ...metadata,
          resourceId: currentResourceId,
        };
        const {
          expiration,
          resourceId,
        } = await this.googleDrive.renewFileSubscription(
          subscription,
          this.http.endpoint,
          channelID,
          newChannelID,
          fileID,
          nextRunTimestamp,
        );
        subscriptions[resourceId] = {
          expiration,
          fileID,
        };
      }
      this._setSubscriptions(subscriptions);
      this._setChannelID(newChannelID);
    },
  },
  async run(event) {
    // This function is polymorphic: it can be triggered as a cron job, to make sure we renew
    // watch requests for specific files, or via HTTP request (the change payloads from Google)

    // Component was invoked by timer
    if (event.timestamp) {
      return this.renewFileSubscriptions(event);
    }

    const channelID = this._getChannelID();
    let subscriptions = this._getSubscriptions() || {};

    const { headers } = event;

    if (
      !headers["x-goog-resource-state"] ||
      !headers["x-goog-resource-id"] ||
      !headers["x-goog-resource-uri"] ||
      !headers["x-goog-message-number"]
    ) {
      console.log("Request missing necessary headers: ", headers);
      return;
    }

    const incomingChannelID = headers["x-goog-channel-id"];
    if (incomingChannelID !== channelID) {
      console.log(
        `Channel ID of ${incomingChannelID} not equal to deployed component channel of ${channelID}`,
      );
      return;
    }

    if (subscriptions[headers["x-goog-resource-id"]] === undefined) {
      console.log(
        `Resource ID of ${headers["x-goog-resource-id"]} not currently being tracked. Exiting`,
      );
      return;
    }

    if (!includes(this.updateTypes, headers["x-goog-resource-state"])) {
      console.log(
        `Update type ${headers["x-goog-resource-state"]} not in list of updates to watch: `,
        this.updateTypes,
      );
      return;
    }

    // We observed false positives where a single change to a document would trigger two changes:
    // one to "properties" and another to "content,properties". But changes to properties
    // alone are legitimate, most users just won't want this source to emit in those cases.
    // If x-goog-changed is _only_ set to "properties", only move on if the user set the prop
    if (
      !this.watchForPropertiesChanges &&
      headers["x-goog-changed"] === "properties"
    ) {
      console.log(
        "Change to properties only, which this component is set to ignore. Exiting",
      );
      return;
    }

    const file = await this.googleDrive.getFileMetadata(
      headers["x-goog-resource-uri"],
    );

    if (!file || !Object.keys(file).length) {
      console.log("No file metadata returned, nothing to emit");
      return;
    }

    const [
      checkedFile,
    ] = this.checkMinimumInterval([
      file,
    ]);
    if (checkedFile) {
      this.processChange(file, headers);
    }
  },
  sampleEmit,
};

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`	Defaults to `My Drive`. To use a Shared Drive, use the Changes to Specific Files (Shared Drive) source instead.
Files	`files`	`string[]`	Select a value from the drop down menu.
Minimum Interval Per File	`perFileInterval`	`integer`	How many minutes to wait until the same file can emit another event. If set to `0`, this interval is disabled and all events will be emitted.
Types of updates	`updateTypes`	`string[]`	Select a value from the drop down menu:`{ "label": "'sync' - A channel was successfully created. You can expect to start receiving notifications for it.", "value": "sync" }{ "label": "'add' - A resource was created or shared.", "value": "add" }{ "label": "'remove' - An existing resource was deleted or unshared.", "value": "remove" }{ "label": "'update' - One or more properties (metadata) of a resource have been updated.", "value": "update" }{ "label": "'trash' - A resource has been moved to the trash.", "value": "trash" }{ "label": "'untrash' - A resource has been removed from the trash.", "value": "untrash" }{ "label": "'change' - One or more changelog items have been added.", "value": "change" }`

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#

Create Chat Completion on DeepSeek

Description:Creates a chat completion using the DeepSeek API. [See the documentation](https://api-docs.deepseek.com/api/create-chat-completion)

Version:0.0.1

Key:deepseek-create-chat-completion

View on GitHub

Action Code#

import { RESPONSE_FORMAT_TYPE_OPTIONS } from "../../common/constants.mjs";
import { parseObject } from "../../common/util.mjs";
import deepseek from "../../deepseek.app.mjs";

export default {
  key: "deepseek-create-chat-completion",
  name: "Create Chat Completion",
  description: "Creates a chat completion using the DeepSeek API. [See the documentation](https://api-docs.deepseek.com/api/create-chat-completion)",
  version: "0.0.1",
  type: "action",
  props: {
    deepseek,
    messages: {
      type: "string[]",
      label: "Messages",
      description: "The messages for the chat conversation as JSON strings. Each message should be a JSON string like '{\"role\": \"user\", \"content\": \"Hello!\"}'. [See the documentation](https://api-docs.deepseek.com/api/create-chat-completion) for further details.",
    },
    frequencyPenalty: {
      type: "string",
      label: "Frequency Penalty",
      description: "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.",
      optional: true,
    },
    maxTokens: {
      type: "integer",
      label: "Max Tokens",
      description: "Integer between 1 and 8192. The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. If `max_tokens` is not specified, the default value 4096 is used.",
      optional: true,
    },
    presencePenalty: {
      type: "string",
      label: "Presence Penalty",
      description: "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.",
      optional: true,
    },
    responseFormatType: {
      type: "string",
      label: "Response Format Type",
      description: "The format that the model must output. Setting to JSON Object enables JSON Output, which guarantees the message the model generates is valid JSON.",
      options: RESPONSE_FORMAT_TYPE_OPTIONS,
      optional: true,
    },
    stop: {
      type: "string[]",
      label: "Stop Sequences",
      description: "Up to 16 sequences where the API will stop generating further tokens.",
      optional: true,
    },
    stream: {
      type: "boolean",
      label: "Stream",
      description: "If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available, with the stream terminated by a `data: [DONE]` message.",
      optional: true,
      reloadProps: true,
    },
    streamIncludeUsage: {
      type: "string",
      label: "Stream Include Usage",
      description: "If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value.",
      optional: true,
      hidden: true,
    },
    temperature: {
      type: "string",
      label: "Temperature",
      description: "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or Top P but not both.",
      optional: true,
    },
    topP: {
      type: "string",
      label: "Top P",
      description: "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.",
      optional: true,
    },
    tools: {
      type: "string[]",
      label: "Tools",
      description: "A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.",
      optional: true,
    },
    toolChoice: {
      type: "string",
      label: "Tool Choice",
      description: "Controls which (if any) tool is called by the model. [See the documentation](https://api-docs.deepseek.com/api/create-chat-completion) for further details.",
      optional: true,
    },
    logprobs: {
      type: "boolean",
      label: "Log Probs",
      description: "Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`.",
      optional: true,
    },
    topLogprobs: {
      type: "string",
      label: "Top Log Probabilities",
      description: "An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.",
      optional: true,
    },
  },
  async additionalProps(props) {
    props.streamIncludeUsage.hidden = !this.stream;
    return {};
  },
  async run({ $ }) {
    const response = await this.deepseek.createModelResponse({
      $,
      data: {
        messages: parseObject(this.messages),
        model: "deepseek-chat",
        frequency_penalty: this.frequencyPenalty && parseInt(this.frequencyPenalty),
        max_tokens: this.maxTokens,
        presence_penalty: this.presencePenalty && parseInt(this.presencePenalty),
        response_format: this.responseFormatType
          ? {
            type: this.responseFormatType,
          }
          : null,
        stop: parseObject(this.stop),
        stream: this.stream,
        stream_options: this.stream
          ? {
            include_usage: this.streamIncludeUsage,
          }
          : null,
        temperature: this.temperature && parseInt(this.temperature),
        top_p: this.topP && parseInt(this.topP),
        tools: parseObject(this.tools),
        tool_choice: parseObject(this.toolChoice),
        logprobs: this.logprobs,
        top_logprobs: this.topLogprobs && parseInt(this.topLogprobs),
      },
    });
    $.export("$summary", "Chat completion created");
    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
DeepSeek	`deepseek`	`app`	This component uses the DeepSeek app.
Messages	`messages`	`string[]`	The messages for the chat conversation as JSON strings. Each message should be a JSON string like '{"role": "user", "content": "Hello!"}'. See the documentation for further details.
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.
Max Tokens	`maxTokens`	`integer`	Integer between 1 and 8192. The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. If `max_tokens` is not specified, the default value 4096 is used.
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.
Response Format Type	`responseFormatType`	`string`	Select a value from the drop down menu:`{ "label": "Text", "value": "text" }{ "label": "JSON Object", "value": "json_object" }`
Stop Sequences	`stop`	`string[]`	Up to 16 sequences where the API will stop generating further tokens.
Stream	`stream`	`boolean`	If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available, with the stream terminated by a `data: [DONE]` message.
Temperature	`temperature`	`string`	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or Top P but not both.
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.
Tools	`tools`	`string[]`	A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.
Tool Choice	`toolChoice`	`string`	Controls which (if any) tool is called by the model. See the documentation for further details.
Log Probs	`logprobs`	`boolean`	Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`.
Top Log Probabilities	`topLogprobs`	`string`	An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

Action Authentication#

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

About DeepSeek#

DeepSeek is an AI-powered tool that helps developers quickly find, understand, and optimize code using natural language search and contextual suggestions. It integrates seamlessly with your workflow, offering insights into your codebase to improve productivity and code quality. Perfect for teams and solo developers, DeepSeek simplifies code navigation and accelerates development.

More Ways to Connect DeepSeek + Google Drive#

Other Popular Integrations#

Get User Balance with DeepSeek API on New Presentation (Instant) from Google Drive API

Google Drive + DeepSeek

Create Chat Completion with DeepSeek API on Changes to Specific Files from Google Drive API

Pipedream makes it easy to connect APIs for DeepSeek, Google Drive 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