1001fx - NoCode functionsInstall

Overview

The "Ask OpenAI" operation under the "ai" resource in this custom n8n node allows users to send a prompt to an OpenAI language model (such as text-davinci-003) and receive a generated completion. This is useful for automating tasks that require natural language understanding or generation, such as drafting emails, summarizing text, generating code snippets, or answering questions.

Practical examples:

• Automatically generate product descriptions from bullet points.
• Summarize customer support tickets.
• Create creative content like poems or stories based on user input.
• Answer user queries using AI within automated workflows.

Properties

Output

• The node outputs a JSON object containing the response from the OpenAI API.
• The structure typically includes fields such as:
  • id: Identifier for the request.
  • object: Type of object returned.
  • created: Timestamp of creation.
  • model: Model used for the completion.
  • choices: Array of completions, each with a text field containing the generated output.
  • usage: Token usage statistics.

Example output:

{
  "id": "cmpl-abc123",
  "object": "text_completion",
  "created": 1670000000,
  "model": "text-davinci-003",
  "choices": [
    {
      "text": "This is the AI-generated response.",
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 16,
    "total_tokens": 26
  }
}

If the API returns an error, the output will contain an error field with details.

Dependencies

• External Service: Requires access to the 1001fx API, which acts as a proxy to OpenAI.
• API Key: You must configure the "1001fxApi" credential in n8n with a valid API key.
• n8n Configuration: No additional configuration is required beyond setting up the credential.

Troubleshooting

Common issues:

• Invalid API Key: If the API key is missing or incorrect, you'll receive an authentication error. Ensure your "1001fxApi" credential is set up correctly.
• Exceeded Token Limit: If the sum of your prompt and max tokens exceeds the model's context length, the API may return an error. Reduce the prompt size or max tokens.
• Model Not Supported: If you select a model not supported by the backend, you may get an error. Currently, only "text-davinci-003" is available.
• Malformed Input: If required properties are missing (e.g., no prompt), the node will throw an error indicating missing parameters.

Error messages:

• "error": "Invalid API key" – Check your credentials.
• "error": "Maximum context length exceeded" – Adjust your prompt or max tokens.
• "error": "Missing required parameter: prompt" – Ensure all required fields are filled.

Links and References

• OpenAI Documentation
• n8n Credentials Documentation
• 1001fx API