Post Completion with xAI API on New Package Version from npm API

Pipedream makes it easy to connect APIs for xAI, npm and 2,400+ other apps remarkably fast.

Trigger workflow on

New Package Version from the npm API

Next, do this

Post Completion with the xAI 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 npm trigger and xAI action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Package Version trigger
1. Connect your npm account
2. Configure timer
3. Configure Package
Configure the Post Completion action
1. Connect your xAI account
2. Select a Model
3. Configure Prompt
4. Optional- Configure Echo
5. Optional- Configure Frequency Penalty
6. Optional- Configure Log Probabilities
7. Optional- Configure Max Tokens
8. Optional- Configure Completion Number
9. Optional- Configure Presence Penalty
10. Optional- Configure Seed
11. Optional- Configure Stream
12. Optional- Configure Suffix
13. Optional- Configure Temperature
14. Optional- Configure Nucleus Sampling
15. Optional- Configure User
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 Package Version on npm

Description:Emit new event when a new version of an npm package is published. [See the documentation](https://github.com/npm/registry/blob/main/docs/responses/package-metadata.md)

Version:0.0.1

Key:npm-new-package-version

View on GitHub

Trigger Code#

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

export default {
  key: "npm-new-package-version",
  name: "New Package Version",
  description: "Emit new event when a new version of an npm package is published. [See the documentation](https://github.com/npm/registry/blob/main/docs/responses/package-metadata.md)",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  props: {
    app,
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    packageName: {
      type: "string",
      label: "Package",
      description: "Enter an npm package name. Leave blank for all",
      default: "@pipedream/platform",
    },
  },
  async run() {
    const {
      app,
      packageName,
    } = this;

    const response = await app.getPackageMetadata({
      debug: true,
      packageName,
    });

    const { "dist-tags": { latest: latestVersion } } = response;

    this.$emit(response, {
      id: latestVersion,
      summary: `New Package Version ${latestVersion}`,
      ts: Date.parse(response.modified),
    });
  },
};

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
npm	`app`	`app`	This component uses the npm app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`
Package	`packageName`	`string`	Enter an npm package name. Leave blank for all

Trigger Authentication#

The npm API does not require authentication.

About npm#

Node package manager

Action#

Post Completion on xAI

Description:Create a language model response for a given prompt. [See the documentation](https://docs.x.ai/api/endpoints#completions)

Version:0.0.2

Key:x_ai-post-completion

View on GitHub

Action Code#

import app from "../../x_ai.app.mjs";

export default {
  key: "x_ai-post-completion",
  name: "Post Completion",
  description: "Create a language model response for a given prompt. [See the documentation](https://docs.x.ai/api/endpoints#completions)",
  version: "0.0.2",
  type: "action",
  props: {
    app,
    model: {
      propDefinition: [
        app,
        "model",
      ],
    },
    prompt: {
      propDefinition: [
        app,
        "prompt",
      ],
    },
    echo: {
      propDefinition: [
        app,
        "echo",
      ],
    },
    frequencyPenalty: {
      propDefinition: [
        app,
        "frequencyPenalty",
      ],
    },
    logprobs: {
      propDefinition: [
        app,
        "logprobs",
      ],
    },
    maxTokens: {
      propDefinition: [
        app,
        "maxTokens",
      ],
    },
    n: {
      propDefinition: [
        app,
        "n",
      ],
    },
    presencePenalty: {
      propDefinition: [
        app,
        "presencePenalty",
      ],
    },
    seed: {
      propDefinition: [
        app,
        "seed",
      ],
    },
    stream: {
      propDefinition: [
        app,
        "stream",
      ],
    },
    suffix: {
      propDefinition: [
        app,
        "suffix",
      ],
    },
    temperature: {
      propDefinition: [
        app,
        "temperature",
      ],
    },
    topP: {
      propDefinition: [
        app,
        "topP",
      ],
    },
    user: {
      propDefinition: [
        app,
        "user",
      ],
    },
  },

  async run({ $ }) {
    const response = await this.app.postCompletion({
      $,
      data: {
        model: this.model,
        prompt: this.prompt,
        echo: this.echo,
        frequency_penalty: Number(this.frequencyPenalty),
        logprobs: this.logprobs,
        max_tokens: this.maxTokens,
        n: this.n,
        presence_penalty: Number(this.presencePenalty),
        seed: this.seed,
        stream: this.stream,
        suffix: this.suffix,
        temperature: Number(this.temperature),
        top_p: Number(this.topP),
        user: this.user,
      },
    });
    $.export("$summary", `Successfully sent prompt to the model '${this.model}'`);
    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
xAI	`app`	`app`	This component uses the xAI app.
Model	`model`	`string`	Select a value from the drop down menu.
Prompt	`prompt`	`string`	Prompt for the request
Echo	`echo`	`boolean`	Option to include the original prompt in the response along with the generated completion
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
Log Probabilities	`logprobs`	`boolean`	Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens
Max Tokens	`maxTokens`	`integer`	Limits the number of tokens that can be produced in the output
Completion Number	`n`	`integer`	Determines how many completion sequences to produce for each prompt. Be cautious with its use due to high token consumption
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
Seed	`seed`	`integer`	If specified, our system will make a best effort to sample deterministically
Stream	`stream`	`boolean`	Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available
Suffix	`suffix`	`string`	Optional string to append after the generated text
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
Nucleus Sampling	`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
User	`user`	`string`	A unique identifier representing your end-user, which can help xAI to monitor and detect abuse