Actions20
- Assistant Actions
- Embedding Actions
- File Actions
- Report Actions
- Text Actions
- Thread Actions
Assistant → Create Assistant
AI-generatedOverview
This node integrates with the OpenAI Analytics API to create and manage AI assistants. Specifically, the "Create Assistant" operation allows users to define a new assistant with customizable parameters such as name, description, system instructions, model selection, and advanced features like code interpretation, file retrieval, and function calling.
Typical use cases include:
- Creating specialized AI assistants tailored for specific tasks or domains.
- Automating workflows that require conversational AI with custom instructions and capabilities.
- Enhancing AI responses by attaching relevant files or enabling advanced interaction modes.
For example, a user might create an assistant named "Customer Support Bot" using the GPT-4o model, with system instructions guiding it to handle customer queries, optionally enabling file search to reference product manuals.
Properties
| Name | Meaning |
|---|---|
| Authentication | Choose between using dedicated OpenAI Analytics API credentials or existing OpenAI API credentials. |
| Assistant Name | The name of the assistant to be created (required). |
| Description | A textual description of the assistant's purpose or characteristics (optional). |
| System Instructions | Custom system-level instructions that guide the assistant's behavior (optional). |
| Model | The AI model used by the assistant, selectable from available completion models (required). |
| Tools | Notice field indicating tools the assistant can use (informational only). |
| Use Code Interpreter | Boolean flag to enable or disable the code interpreter feature for the assistant. |
| Use Retrieval (File Search) | Boolean flag to enable or disable file retrieval capability, allowing the assistant to search attached files. |
| Use Function Calling | Boolean flag to enable or disable function calling capability for the assistant. |
| Function Definitions | JSON array defining functions that the assistant can call; only shown if function calling is enabled. |
| Response Format | Specifies the format of the assistant's response: Auto (default), Text, or JSON Object. |
| Advanced Settings | Boolean flag to enable advanced generation parameters. |
| Temperature | Controls randomness in responses; ranges from 0 (deterministic) to 2 (very random). Only shown if advanced settings are enabled. |
| Top P | Controls diversity via nucleus sampling; value between 0 and 1. Only shown if advanced settings are enabled. |
| Metadata | JSON-formatted metadata associated with the assistant. Only shown if advanced settings are enabled. |
| Use File Attachments | Boolean flag indicating whether to attach files to the assistant. |
| File IDs | List of file IDs to attach to the assistant; only visible if file attachments are enabled. |
Output
The node outputs a JSON object representing the newly created assistant. This typically includes details such as the assistant's ID, name, description, model, enabled features, and any other metadata returned by the OpenAI Analytics API.
No binary data output is indicated for this operation.
Dependencies
- Requires valid API credentials for either the OpenAI Analytics API or the standard OpenAI API.
- The node dynamically loads available models and files via the OpenAI API.
- Network access to OpenAI endpoints is necessary.
- No additional environment variables beyond credential configuration are required.
Troubleshooting
- Credential Errors: If the node fails to load credentials, ensure that the correct API key credential is configured and selected in the "Authentication" property.
- Model Loading Issues: If no models appear in the dropdown, verify API access and permissions.
- Invalid JSON in Function Definitions or Metadata: When entering JSON arrays or objects, ensure proper syntax to avoid parsing errors.
- File Attachment Problems: If files do not attach correctly, confirm that the file IDs are valid and accessible with the provided credentials.
- API Rate Limits or Network Errors: These may cause operation failures; check network connectivity and API usage quotas.