Create Chat Completion with Cerebras API

Pipedream makes it easy to connect APIs for Cerebras and 2,500+ other apps remarkably fast.

Trigger workflow on

HTTP requests, schedules and app events

Next, do this

Create Chat Completion with the Cerebras 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#

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

Configure the Create Chat Completion action
1. Connect your Cerebras account
2. Select a Model
3. Configure Message
4. Optional- Configure Max Completion Tokens
5. Optional- Configure Stream
6. Optional- Configure Seed
7. Optional- Configure Stop
8. Optional- Configure Temperature
9. Optional- Configure Top P
10. Optional- Select a Tool Choice
11. Optional- Configure Tools
12. Optional- Configure User
13. Optional- Configure Log Probabilities
14. Optional- Configure Top Log Probabilities
Select a trigger to run your workflow on HTTP requests, schedules or app events
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Integrations#

Create Chat Completion with Cerebras API on New Requests (Payload Only) from HTTP / Webhook API

HTTP / Webhook + Cerebras

Try it

Create Chat Completion with Cerebras API on New Submission from Typeform API

Typeform + Cerebras

Try it

Create Chat Completion with Cerebras API on New Submission (Instant) from Jotform API

Jotform + Cerebras

Try it

Create Chat Completion with Cerebras API on New Scheduled Tasks from Pipedream API

Pipedream + Cerebras

Try it

Create Chat Completion with Cerebras API on New Download Counts from npm API

npm + Cerebras

Try it

Details#

This is a pre-built, source-available component from Pipedream's GitHub repo. The component is 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.

Create Chat Completion on Cerebras

Description:Create a chat completion with Cerebras AI. [See the documentation](https://inference-docs.cerebras.ai/api-reference/chat-completions)

Version:0.0.1

Key:cerebras-create-chat-completion

View on GitHub

Code#

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

export default {
  name: "Create Chat Completion",
  key: "cerebras-create-chat-completion",
  description: "Create a chat completion with Cerebras AI. [See the documentation](https://inference-docs.cerebras.ai/api-reference/chat-completions)",
  version: "0.0.1",
  type: "action",
  props: {
    cerebras,
    model: {
      propDefinition: [
        cerebras,
        "model",
      ],
    },
    message: {
      type: "string",
      label: "Message",
      description: "The message to send to the model",
    },
    maxCompletionTokens: {
      type: "integer",
      label: "Max Completion Tokens",
      description: "The maximum number of tokens that can be generated in the completion. The total length of input tokens and generated tokens is limited by the model's context length.",
      optional: true,
    },
    stream: {
      propDefinition: [
        cerebras,
        "stream",
      ],
    },
    seed: {
      propDefinition: [
        cerebras,
        "seed",
      ],
    },
    stop: {
      propDefinition: [
        cerebras,
        "stop",
      ],
    },
    temperature: {
      propDefinition: [
        cerebras,
        "temperature",
      ],
    },
    topP: {
      propDefinition: [
        cerebras,
        "topP",
      ],
    },
    toolChoice: {
      type: "string",
      label: "Tool Choice",
      description: "Controls which (if any) tool is called by the model",
      optional: true,
      options: [
        "none",
        "auto",
        "required",
      ],
    },
    tools: {
      type: "object",
      label: "Tools",
      description: "A list of tools the model may call. [See the documentation](https://inference-docs.cerebras.ai/api-reference/chat-completions#tool-choice) for more information",
      optional: true,
    },
    user: {
      propDefinition: [
        cerebras,
        "user",
      ],
    },
    logprobs: {
      type: "boolean",
      label: "Log Probabilities",
      description: "Whether to return log probabilities of the output tokens or not",
      optional: true,
      default: false,
    },
    topLogprobs: {
      type: "integer",
      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",
      optional: true,
    },
  },
  async run({ $ }) {
    const {
      model,
      message,
      maxCompletionTokens,
      stream,
      seed,
      stop,
      temperature,
      topP,
      toolChoice,
      tools,
      user,
      logprobs,
      topLogprobs,
    } = this;

    const response = await this.cerebras.chatCompletion({
      $,
      data: {
        model,
        messages: [
          {
            role: "user",
            content: message,
          },
        ],
        max_completion_tokens: maxCompletionTokens,
        stream,
        seed,
        stop,
        temperature,
        top_p: topP,
        tool_choice: toolChoice,
        tools,
        user,
        logprobs,
        top_logprobs: topLogprobs,
      },
    });

    $.export("$summary", "Successfully created chat completion");
    return response;
  },
};

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
Cerebras	`cerebras`	`app`	This component uses the Cerebras app.
Model	`model`	`string`	Select a value from the drop down menu.
Message	`message`	`string`	The message to send to the model
Max Completion Tokens	`maxCompletionTokens`	`integer`	The maximum number of tokens that can be generated in the completion. The total length of input tokens and generated tokens is limited by the model's context length.
Stream	`stream`	`boolean`	If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available
Seed	`seed`	`integer`	If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result
Stop	`stop`	`string`	Up to 4 sequences, separated by commas, where the API will stop generating further tokens. The returned text will not contain the stop sequence
Temperature	`temperature`	`string`	What sampling temperature to use, between 0 and 1.5. Higher values (e.g., 0.8) will make the output more random, while lower values (e.g., 0.2) will make it more focused and deterministic
Top P	`topP`	`string`	An alternative to sampling with temperature, called nucleus sampling, where the model considers the tokens with top_p probability mass
Tool Choice	`toolChoice`	`string`	Select a value from the drop down menu:`noneautorequired`
Tools	`tools`	`object`	A list of tools the model may call. See the documentation for more information
User	`user`	`string`	A unique identifier representing your end-user, which can help Cerebras to monitor and detect abuse
Log Probabilities	`logprobs`	`boolean`	Whether to return log probabilities of the output tokens or not
Top Log Probabilities	`topLogprobs`	`integer`	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