Skip to main content

Anthropic

Integrating Anthropic with ToolJet enables the creation of interactive chatbots that analyze past messages to generate context-aware responses. These bots can also be customized with defined roles, making them suitable for tasks such as customer support, serving as virtual assistants, or enabling personalized conversations.

NOTE

Before following this guide, it is assumed that you have already completed the process of Using Marketplace plugins.

Connection​

To connect with Anthropic, you will need the API Key, which can be generated from Anthropic Console.

Anthropic Configuration

Supported Operations​

Chat​

This operation processes the user's input and generates appropriate, context-aware responses, simulating a natural, human-like conversation. It can handle multiple interactions while maintaining the flow of dialogue, enabling dynamic and engaging conversations.

note

The Chat (Deprecated) operation is still available for existing queries. Instead of Message History and User message, it takes the whole conversation in a single Message field: a JSON array of objects with role and content.

Required Parameters

  • Model: The model to use for generating the chat response. The default is claude-opus-5. The available models are:

    • claude-fable-5-1
    • claude-fable-5
    • claude-opus-5-5
    • claude-opus-5
    • claude-sonnet-5
    • claude-sonnet-4-5-20250929
    • claude-sonnet-4-20250514
    • claude-opus-4-5-20251101
    • claude-opus-4-1-20250805
    • claude-opus-4-20250514
    • claude-haiku-4-5
    • claude-3-5-haiku-20241022 (Deprecated)
    • claude-3-5-sonnet-20241022 (Discontinued)
    • claude-3-opus-20240229 (Discontinued)
    • claude-3-sonnet-20240229 (Discontinued)
    • claude-3-haiku-20240307 (Discontinued)

  • User message: The message the model replies to. ToolJet sends it as the last user message, after Message History. The query fails if this field is empty.

  • Max Size: Maximum tokens used in response. If left empty, 256 is used. The value is capped per model: 128000 for claude-fable-5-1, claude-fable-5, claude-opus-5-5, claude-opus-5 and claude-sonnet-5, 64000 for claude-haiku-4-5, and 2048 for all other models.

Optional Parameters

  • System prompt: Defines the role and context of the model to evaluate messages and generate a response.

  • Message History: Earlier turns of the conversation, as a JSON array of objects with role (user or assistant) and content, for example [{ "role": "user", "content": "Hello Claude!" }, { "role": "assistant", "content": "Hello! How can I assist you today?" }]. If the value isn't valid JSON, ToolJet ignores it and sends only the User message.

  • Temperature: Controls the randomness of the response. Accepts values between 0 and 1. If left empty, 0.5 is used.

note

claude-fable-5-1, claude-fable-5, claude-opus-5-5, claude-opus-5 and claude-sonnet-5 don't accept a temperature, so the Temperature field isn't shown for these models.

Anthropic Query
Response Example
[
  {
    "type": "text",
    "text": "AI has numerous significant benefits in healthcare. Here are some key advantages:nn1. Diagnosis and Disease Detectionn- Faster and more accurate diagnosis through image analysis (X-rays, MRIs, CT scans)n- Early detection of diseases like cancern- Pattern recognition in patient symptoms and medical historynn2. Treatment Planningn- Personalized treatment recommendationsn- Drug interaction predictionsn- Treatment outcome forecastingn- Precision medicine based on patient datann3. Administrative Tasksn- Automated appointment schedulingn- Medical record managementn- Billing and insurance processingn- Reducing paperwork and administrative burdennn4. Patient Caren- Remote patient monitoringn- Virtual health assistantsn- Personalized care recommendationsn- Medication adherence trackingnn5. Research and Drug Developmentn- Accelerated drug discoveryn- Clinical trial matchingn- Analysis of medical research datan- Identification of new treatment approachesnn6. Preventive Caren- Risk prediction and assessmentn- Population health managementn- Lifestyle recommendationsn- Early intervention opportunitiesnn7. Cost Reductionn- Improved efficiencyn- Reduced medical errorsn- Better resource allocationn- Streamlined operationsnn8. Accessibilityn- 24/7 availability of basic healthcare informationn- Improved access to healthcare in remote areasn- Reduced wait timesn- Better distribution of medical expertisennThese benefits continue to expand as AI technology advances and becomes more integrated into healthcare systems."
  }
]