> ## Documentation Index
> Fetch the complete documentation index at: https://portkey-docs-add-third-party-integration-issues-fixes.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# ToolJet

> ToolJet is a low-code platform that lets you build apps by connecting APIs and data sources, with Portkey integration adding AI features like chat interfaces and automation.

This guide provides a **streamlined process** for integrating **Portkey AI** into ToolJet using the ToolJet Marketplace Plugin. Follow this guide to add **AI-powered capabilities** such as chat completions and automations into your ToolJet apps, helping developers create powerful, low-code applications backed by Portkey's AI for chat-based interfaces and automated workflows.

## Prerequisites

* **Portkey API Key** and **Virtual Key** from your Portkey dashboard.
* **ToolJet Account** with access to the **Marketplace Plugin feature**.
* Basic familiarity with ToolJet UI components.

<Card title="Watch Demo" icon="play" href="https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://www.youtube.com/watch%3Fv%3DVGb7HGRkam0&ved=2ahUKEwjpm8Low6mJAxUmRmwGHT0dCswQwqsBegQIChAF&usg=AOvVaw1JLV0bmHiZJ6h9k9B6jwHK">
  Watch this demo for a quick walkthrough on ToolJet's UI components.
</Card>

<Note>
  Before following this guide, ensure that you have completed the setup for using marketplace plugins in ToolJet.
</Note>

## Step-by-Step Onboarding

<Steps>
  <Step title="Install the Portkey Plugin from ToolJet Marketplace">
    1. Go to **ToolJet Dashboard > Plugins > Marketplace**.
    2. Search for **Portkey Plugin**.
    3. Click **Install** to add the plugin to your project.

    <Note>
      If Portkey has already been added to your marketplace, you can skip this step.
    </Note>
  </Step>

  <Step title="Configure the Portkey Plugin">
    1. Navigate to **Data Sources** in your ToolJet workspace.
    2. Open **Plugins**.
    3. Click **Add Portkey**.

    <Frame>
      <img src="https://mintcdn.com/portkey-docs-add-third-party-integration-issues-fixes/pMv-_yAsIXahFOL3/images/supported-llm/1.Configure_Plugin.png?fit=max&auto=format&n=pMv-_yAsIXahFOL3&q=85&s=040d8d63d145eccca9bd14f38da08562" width="2934" height="1674" data-path="images/supported-llm/1.Configure_Plugin.png" />
    </Frame>
  </Step>

  <Step title="Add Portkey as a Datasource">
    1. Enter the following details:

    * **Authorization:** Your Portkey API Key
    * **Default Virtual Key:** Your Portkey Virtual Key

    2. **Test** the connection to ensure the keys are configured correctly.

    <Frame>
      <img src="https://mintcdn.com/portkey-docs-add-third-party-integration-issues-fixes/pMv-_yAsIXahFOL3/images/supported-llm/2.Portkey%20datasource.png?fit=max&auto=format&n=pMv-_yAsIXahFOL3&q=85&s=b2a6d99975f4bf5da5b1aef2f8bc90ec" width="1448" height="1488" data-path="images/supported-llm/2.Portkey datasource.png" />
    </Frame>
  </Step>

  <Step title="Use Portkey in Your ToolJet App">
    1. Go to **Queries > Add Datasource > Select Portkey Plugin**.
    2. From the dropdown, **Select an Operation** (details in the next section).
    3. **Run the query** to verify it responds correctly.

    <Frame>
      <img src="https://mintcdn.com/portkey-docs-add-third-party-integration-issues-fixes/pMv-_yAsIXahFOL3/images/supported-llm/3.Use%20in%20ToolJet.png?fit=max&auto=format&n=pMv-_yAsIXahFOL3&q=85&s=ed2cf52fad88fb180ad18a9dc1cb1fa1" width="2934" height="1674" data-path="images/supported-llm/3.Use in ToolJet.png" />
    </Frame>
  </Step>

  <Step title="Link the Query to UI Components (Example)">
    1. Add **Text Input** and **Button** widgets to your app's interface.
    2. Configure the Button's **onClick action** to **Execute Query** using the Portkey API.
    3. Use a **Text Box** widget to display the query results.
  </Step>

  <Step title="Test and Deploy">
    1. Use **Preview Mode** to test the interaction between your app's UI and the Portkey API.
    2. Deploy the app from the ToolJet dashboard.
  </Step>
</Steps>

## Supported Operations

Portkey supports the following operations within ToolJet:

<Tabs>
  <Tab title="Completion">
    #### Completion

    Generates text completions based on a given prompt.

    **Parameters:**

    * **Prompt:** Input text to generate completions for.
    * **Model:** The AI model to use.
    * **Max Tokens:** Maximum number of tokens to generate.
    * **Temperature:** Controls randomness.
    * **Stop Sequences:** Sequences where the API stops generating further tokens.
    * **Metadata:** Additional metadata for the request.
    * **Other Parameters:** Additional request parameters.

    <Frame>
      <img src="https://mintcdn.com/portkey-docs-add-third-party-integration-issues-fixes/pMv-_yAsIXahFOL3/images/supported-llm/4.completion.png?fit=max&auto=format&n=pMv-_yAsIXahFOL3&q=85&s=2cb8d57bf0aa2eb1f1ac56a7db7ea67d" width="1646" height="1252" data-path="images/supported-llm/4.completion.png" />
    </Frame>

    <Accordion title="Response Example">
      ```javascript theme={null}
      {
        "id": "cmpl-9vNUfM8OP0SwSqXcnPwkqzR7ep8Sy",
        "object": "text_completion",
        "created": 1723462033,
        "model": "gpt-3.5-turbo-instruct",
        "choices": [
        {
        "text": "nn"Experience the perfect brew at Bean There."",
        "index": 0,
        "logprobs": null,
        "finish_reason": "stop"
        }
        ],
        "usage": {
        "prompt_tokens": 13,
        "completion_tokens": 10,
        "total_tokens": 23
        }
        }
      ```
    </Accordion>
  </Tab>

  <Tab title="Chat">
    #### Chat

    Generates chat completions based on a series of messages.

    **Parameters:**

    * **Messages:** Array of message objects representing the conversation.
    * **Model:** The AI model to use.
    * **Max Tokens:** Maximum number of tokens to generate.
    * **Temperature:** Controls randomness.
    * **Stop Sequences:** Sequences where the API stops generating further tokens.
    * **Metadata:** Additional metadata for the request.
    * **Other Parameters:** Additional request parameters.

    <Frame>
      <img src="https://mintcdn.com/portkey-docs-add-third-party-integration-issues-fixes/pMv-_yAsIXahFOL3/images/supported-llm/5.chat.png?fit=max&auto=format&n=pMv-_yAsIXahFOL3&q=85&s=418deb94e251fa01b3ecabf2af36e03c" width="1634" height="1248" data-path="images/supported-llm/5.chat.png" />
    </Frame>

    <Accordion title="Response Example">
      ```javascript Response Example theme={null}
      {
        "id": "chatcmpl-9vNIlfllXOPEmroKFajK2nlJHzhXA",
        "object": "chat.completion",
        "created": 1723461295,
        "model": "gpt-3.5-turbo-0125",
        "choices": [
            {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "The capital of France is Paris.",
                "refusal": null
            },
            "logprobs": null,
            "finish_reason": "stop"
            }
        ],
        "usage": {
            "prompt_tokens": 24,
            "completion_tokens": 7,
            "total_tokens": 31
        },
        "system_fingerprint": null
        }
      ```
    </Accordion>
  </Tab>

  <Tab title="Prompt Completion">
    #### Prompt Completion

    Generates completions based on a pre-defined prompt.

    **Parameters:**

    * **Prompt ID:** The ID of the pre-defined prompt.
    * **Variables:** Variables to use in the prompt.
    * **Parameters:** Additional parameters for the completion.
    * **Metadata:** Additional metadata for the request.

    <Frame>
      <img src="https://mintcdn.com/portkey-docs-add-third-party-integration-issues-fixes/pMv-_yAsIXahFOL3/images/supported-llm/6.prompt-completion.png?fit=max&auto=format&n=pMv-_yAsIXahFOL3&q=85&s=1db98a35ac1dfd78754366683c8a9375" width="1660" height="1230" data-path="images/supported-llm/6.prompt-completion.png" />
    </Frame>

    <Accordion title="Response Example">
      ```javascript Response Example theme={null}
      {
        "id": "chatcmpl-9w6D8jZciWVf1DzkgqNZK14KUvA4d",
        "object": "chat.completion",
        "created": 1723633926,
        "model": "gpt-4o-mini-2024-07-18",
        "choices": [
            {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "The Industrial Revolution, starting in the late 18th century, transformed production from hand methods to machine-based processes, introducing new manufacturing techniques, steam power, and machine tools. It marked a shift from bio-fuels to coal, with the textile industry leading the way. This period resulted in significant population growth, increased average income, and improved living standards.",
                "refusal": null
            },
            "logprobs": null,
            "finish_reason": "stop"
            }
        ],
        "usage": {
            "prompt_tokens": 145,
            "completion_tokens": 71,
            "total_tokens": 216
        },
        "system_fingerprint": "fp_48196bc67a"
        }
      ```
    </Accordion>
  </Tab>

  <Tab title="Create Embedding">
    #### Create Embedding

    Generates embeddings for a given input.

    **Parameters:**

    * **Input:** Text to create embeddings for.
    * **Model:** The AI model to use for embeddings.
    * **Metadata:** Additional metadata for the request.

    <Frame>
      <img src="https://mintcdn.com/portkey-docs-add-third-party-integration-issues-fixes/pMv-_yAsIXahFOL3/images/supported-llm/7.embedding.png?fit=max&auto=format&n=pMv-_yAsIXahFOL3&q=85&s=f8c54fb91eca1e72677e4528621cf660" width="1654" height="838" data-path="images/supported-llm/7.embedding.png" />
    </Frame>

    <Accordion title="Response Example">
      ```javascript Response Example theme={null}
        {
        "object": "list",
        "data": [
            {
            "object": "embedding",
            "index": 0,
            "embedding": [
                -0.02083237,
                -0.016892163,
                -0.0045676464,
                -0.05084554,
                -0.025968939,
                0.029597048,
                0.029987168,
                0.02907689,
                0.0105982395,
                -0.024356445,
                -0.00935636,
                0.0066352785,
                0.034018397,
                -0.042002838,
                0.03856979,
                -0.014681488,
                ...,
                0.024707552
            ]
            }
        ],
        "model": "text-embedding-3-small",
        "usage": {
            "prompt_tokens": 9,
            "total_tokens": 9
        }
        }
      ```
    </Accordion>
  </Tab>
</Tabs>

<Info>
  For all operations, you can optionally specify:

  * **Config:** Configuration options for the request.
  * **Virtual Key:** Override the default virtual key with a specific one.
</Info>

## Troubleshooting

#### - Authentication Error

Double-check your **API key** and **configuration**.

#### - Slow Response

Adjust the **temperature** or **max\_tokens** to optimize performance.

#### - CORS Issues

Ensure your API settings allow access from **ToolJet's domain**.