Generate Chat Completion with Ollama API on New Deployment from Vercel API

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

Trigger workflow on

New Deployment from the Vercel API

Next, do this

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

Select this integration
Configure the New Deployment trigger
1. Connect your Vercel account
2. Configure timer
3. Optional- Select a Project
4. Optional- Select a State
5. Optional- Configure Max
Configure the Generate Chat Completion action
1. Connect your Ollama account
2. Select a Model Name
3. Configure Messages
4. Optional- Configure Tools
5. Optional- Configure Advanced Options
6. Optional- Configure Stream
7. Optional- Configure Keep Alive
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 Deployment on Vercel

Description:Emit new event when a deployment is created

Version:0.0.3

Key:vercel_token_auth-new-deployment

View on GitHub

Vercel Overview#

The Vercel API empowers developers to automate, manage, and interact with their Vercel projects and deployments directly through code. With the Vercel API on Pipedream, you can harness the power of serverless functions to create dynamic and responsive workflows. Automate deployment processes, sync deployment statuses with other tools, trigger notifications based on deployment events, or manage your domains and aliases—all within the seamless integration landscape of Pipedream.

Trigger Code#

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

export default {
  key: "vercel_token_auth-new-deployment",
  name: "New Deployment",
  description: "Emit new event when a deployment is created",
  version: "0.0.3",
  type: "source",
  dedupe: "unique",
  props: {
    vercelTokenAuth,
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    project: {
      propDefinition: [
        vercelTokenAuth,
        "project",
      ],
    },
    state: {
      propDefinition: [
        vercelTokenAuth,
        "state",
      ],
    },
    max: {
      propDefinition: [
        vercelTokenAuth,
        "max",
      ],
    },
  },
  hooks: {
    async deploy() {
      await this.processEvent(10);
    },
  },
  methods: {
    _getFrom() {
      return this.db.get("from");
    },
    _setFrom(from) {
      this.db.set("from", from);
    },
    generateMeta(deployment) {
      const {
        uid,
        name,
        state,
        created,
      } = deployment;
      return {
        id: uid,
        summary: `${name ?? uid} ${state}`,
        ts: created,
      };
    },
    async processEvent(max) {
      const params = {
        projectId: this.project,
        state: this.state,
      };
      let from = this._getFrom();
      if (from) {
        params.from = from;
      }
      const deployments = await this.vercelTokenAuth.listDeployments(params, max);
      for (const deployment of deployments) {
        if (!from || deployment.created > from) {
          from = deployment.created;
        }
        const meta = this.generateMeta(deployment);
        this.$emit(deployment, meta);
      }
      this._setFrom(from);
    },
  },
  async run() {
    await this.processEvent(this.max);
  },
};

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
Vercel	`vercelTokenAuth`	`app`	This component uses the Vercel app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`
Project	`project`	`string`	Select a value from the drop down menu.
State	`state`	`string`	Select a value from the drop down menu:`BUILDINGERRORINITIALIZINGQUEUEDREADYCANCELED`
Max	`max`	`integer`	Maximum number of results to return

Trigger Authentication#

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

Vercel encourages users to connect their account with Pipedream using Personal Access Tokens, which can be managed in your Vercel account here.

To learn more, refer to Vercel's documentation.

About Vercel#

Vercel is the platform for frontend developers, providing the speed and reliability innovators need to create at the moment of inspiration.

Action#

Generate Chat Completion on Ollama

Description:Generates the next message in a chat with a provided model. [See the documentation](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-chat-completion).

Version:0.0.1

Key:ollama-generate-chat-completion

View on GitHub

Action Code#

import app from "../../ollama.app.mjs";
import utils from "../../common/utils.mjs";

export default {
  key: "ollama-generate-chat-completion",
  name: "Generate Chat Completion",
  description: "Generates the next message in a chat with a provided model. [See the documentation](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-chat-completion).",
  version: "0.0.1",
  type: "action",
  props: {
    app,
    model: {
      propDefinition: [
        app,
        "model",
      ],
    },
    messages: {
      type: "string[]",
      label: "Messages",
      description: "The messages of the chat, this can be used to keep a chat memory. Each row should be set as a JSON format string. Eg. `{\"role\": \"user\", \"content\": \"Hello\"}`. The message object has the following fields:\n- `role`: the role of the message, either `system`, `user`, `assistant`, or `tool`.\n- `content`: The content of the message.\n- `images` (optional): a list of images to include in the message (for multimodal models such as `llava`).\n- `tool_calls`(optional): a list of tools the model wants to use.",
    },
    tools: {
      type: "string[]",
      label: "Tools",
      description: "A list of tools the model can use. Each row should be set as a JSON format string.",
      optional: true,
    },
    options: {
      propDefinition: [
        app,
        "options",
      ],
    },
    stream: {
      propDefinition: [
        app,
        "stream",
      ],
    },
    keepAlive: {
      propDefinition: [
        app,
        "keepAlive",
      ],
    },
  },
  methods: {
    generateChatCompletion(args = {}) {
      return this.app.post({
        path: "/chat",
        ...args,
      });
    },
  },
  async run({ $ }) {
    const {
      generateChatCompletion,
      model,
      messages,
      tools,
      options,
      stream,
      keepAlive,
    } = this;

    const response = await generateChatCompletion({
      $,
      data: {
        model,
        messages: utils.parseArray(messages),
        tools: utils.parseArray(tools),
        options: utils.parseOptions(options),
        stream,
        keep_alive: keepAlive,
      },
    });

    $.export("$summary", "Successfully generated chat completion.");
    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
Ollama	`app`	`app`	This component uses the Ollama app.
Model Name	`model`	`string`	Select a value from the drop down menu.
Messages	`messages`	`string[]`	The messages of the chat, this can be used to keep a chat memory. Each row should be set as a JSON format string. Eg. `{"role": "user", "content": "Hello"}`. The message object has the following fields: `role`: the role of the message, either `system`, `user`, `assistant`, or `tool`. `content`: The content of the message. `images` (optional): a list of images to include in the message (for multimodal models such as `llava`). `tool_calls`(optional): a list of tools the model wants to use.
Tools	`tools`	`string[]`	A list of tools the model can use. Each row should be set as a JSON format string.
Advanced Options	`options`	`object`	Additional model parameters listed in the documentation for the Modelfile such as `temperature`
Stream	`stream`	`boolean`	If `false` the response will be returned as a single response object, rather than a stream of objects.
Keep Alive	`keepAlive`	`string`	Controls how long the model will stay loaded into memory following the request (default: 5m).