Chat with Google PaLM API on New event when the content of the URL changes. from HTTP / Webhook API

Pipedream makes it easy to connect APIs for Google PaLM, HTTP / Webhook and 2,400+ other apps remarkably fast.

Trigger workflow on

New event when the content of the URL changes. from the HTTP / Webhook 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 HTTP / Webhook 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 event when the content of the URL changes. trigger
1. Connect your HTTP / Webhook account
2. Configure Watching timer
3. Configure HTTP Request Configuration
4. Configure Emit body only
5. Configure Emit as array
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 event when the content of the URL changes. on HTTP / Webhook

Description:Emit new event when the content of the URL changes.

Version:0.0.2

Key:http-watch-url

View on GitHub

HTTP / Webhook Overview#

Build, test, and send HTTP requests without code using your Pipedream workflows. The HTTP / Webhook action is a tool to build HTTP requests with a Postman-like graphical interface.

Point and click HTTP requests

Define the target URL, HTTP verb, headers, query parameters, and payload body without writing custom code.

$A screenshot of Pipedream's HTTP Request Configuration interface with a GET request type selected. The request URL is set to 'https://api.openai.com/v1/models'. The 'Auth' tab is highlighted, indicating that authentication is required for this request. In the headers section, there are two headers configured: 'User-Agent' is set to 'pipedream/1', and 'Authorization' is set to 'Bearer {{openai_api_key}}', showing how the OpenAI account's API key is dynamically inserted into the headers to handle authentication automatically.$

Here's an example workflow that uses the HTTP / Webhook action to send an authenticated API request to OpenAI.

Focus on integrating, not authenticating

This action can also use your connected accounts with third-party APIs. Selecting an integrated app will automatically update the request’s headers to authenticate with the app properly, and even inject your token dynamically.

Pipedream integrates with thousands of APIs, but if you can’t find a Pipedream integration simply use Environment Variables in your request headers to authenticate with.

Compatible with no code actions or Node.js and Python

The HTTP/Webhook action exports HTTP response data for use in subsequent workflow steps, enabling easy data transformation, further API calls, database storage, and more.

Response data is available for both coded (Node.js, Python) and no-code steps within your workflow.

Trigger Code#

import http from "../../http.app.mjs";
import hash from "object-hash";
import { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } from "@pipedream/platform";

export default {
  key: "http-watch-url",
  name: "New event when the content of the URL changes.",
  description: "Emit new event when the content of the URL changes.",
  version: "0.0.2",
  type: "source",
  dedupe: "unique",
  props: {
    http,
    timer: {
      type: "$.interface.timer",
      label: "Watching timer",
      description: "How often to watch the URL.",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    httpRequest: {
      type: "http_request",
      label: "HTTP Request Configuration",
      description: "HTTP Request Configuration",
      default: {
        method: "GET",
      },
    },
    emitBodyOnly: {
      label: "Emit body only",
      description: "If set as true the emitted item will contain only the response body, otherwise, it will include the request status code.",
      type: "boolean",
      default: true,
    },
    emitAsArray: {
      label: "Emit as array",
      description: "If the request responds with an array, this source will emit changes individually for each item of the array.",
      type: "boolean",
      default: false,
    },
  },
  methods: {
    getMeta(data, status) {
      if (this.emitBodyOnly) {
        return data;
      }
      return {
        data,
        status,
      };
    },
    emitArray(event, response) {
      if (!Array.isArray(response.data)) {
        return this.emitAny(event, response);
      }
      for (const item of response.data) {
        const meta = this.getMeta(item, response.status);
        this.emit(event, meta);
      }
    },
    emitAny(event, response) {
      const meta = this.getMeta(response.data, response.status);
      this.emit(event, meta);
    },
    emit(event, meta) {
      const ts = event.timestamp || Math.round(Date.now() / 1000);
      this.$emit(meta, {
        id: hash(meta),
        summary: `Requested at ${ts}`,
        ts,
      });
    },
  },
  async run(event) {
    const response = await this.httpRequest.execute();
    if (this.emitAsArray) {
      this.emitArray(event, response);
    } else {
      this.emitAny(event, response);
    }
  },
};

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
HTTP / Webhook	`http`	`app`	This component uses the HTTP / Webhook app.
Watching timer	`timer`	`$.interface.timer`	How often to watch the URL.
HTTP Request Configuration	`httpRequest`	`http_request`	HTTP Request Configuration
Emit body only	`emitBodyOnly`	`boolean`	If set as true the emitted item will contain only the response body, otherwise, it will include the request status code.
Emit as array	`emitAsArray`	`boolean`	If the request responds with an array, this source will emit changes individually for each item of the array.

Trigger Authentication#

The HTTP / Webhook API does not require authentication.

About HTTP / Webhook#

Get a unique URL where you can send HTTP or webhook requests

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 + HTTP / Webhook#

Other Popular Integrations#

Chat with Google PaLM API on New Requests from HTTP / Webhook API

HTTP / Webhook + Google PaLM

Try it

Chat with Google PaLM API on New Requests (Payload Only) from HTTP / Webhook API

HTTP / Webhook + Google PaLM

Try it

Generate Embeddings with Google PaLM API on New Requests from HTTP / Webhook API

HTTP / Webhook + Google PaLM

Try it

Generate Embeddings with Google PaLM API on New Requests (Payload Only) from HTTP / Webhook API

HTTP / Webhook + Google PaLM

Try it

Generate Embeddings with Google PaLM API on New event when the content of the URL changes. from HTTP / Webhook API

HTTP / Webhook + Google PaLM

Try it

Popular Triggers#

New Requests from the HTTP / Webhook API

Get a URL and emit the full HTTP event on every request (including headers and query parameters). You can also configure the HTTP response code, body, and more.

Try it

New Requests (Payload Only) from the HTTP / Webhook API

Get a URL and emit the HTTP body as an event on every request

Try it

New event when the content of the URL changes. from the HTTP / Webhook API

Emit new event when the content of the URL changes.

Try it