With Generative AI Lab 5.2, you can harness the potential of synthetic documents generated by LLMs such as ChatGPT. This integration allows you to easily create diverse and customizable synthetic text for your annotation tasks, enabling you to balance any entity skewness in your data and to train and evaluate your models more efficiently.
Generative AI Lab offers seamless integration with ChatGPT, enabling on-the-fly text generation. Additionally, Generative AI Labs provides the flexibility to manage multiple service providers key pairs for robust and flexible integration. These service providers can be assigned to specific projects, simplifying resource management. During the integration process, Each Service Provider Key can be validated via the UI (User Interface), ensuring seamless integration.
Once the service provider integration is completed, it can be utilized in projects that can benefit from the robust capabilities of this new integration. Text generation becomes straightforward and effortless. Provide a prompt adapted to your data needs (you can test it via the ChatGPT app and copy/paste it to Generative AI Lab when ready) to initiate the generation process and obtain the required tasks. Users can further control the results by setting the “Temperature” and the “Number of text to generate.” The “Temperature” parameter governs the “creativity” or randomness of the LLM-generated text. Higher temperature values (e.g., 0.7) yield more diverse and creative outputs, whereas lower values (e.g., 0.2) produce more deterministic and focused outputs.
The Generative AI Lab integration delivers the generated text in a dedicated UI that allows users to review, edit, and tag it in place. After an initial verification and editing, the generated texts can be imported into the project as Tasks, serving as annotation tasks for model training. Additionally, the generated texts can be downloaded locally in CSV format, facilitating their reuse in other projects.
Generative AI Labs will soon support integration with additional service providers, further empowering our users with more powerful capabilities for even more efficient and robust model generation.
Generate synthetic tasks using Azure OpenAI
Azure OpenAI can also be used to generate synthetic tasks. Here’s a quick guide:
Setting up and Validating the New Service Provider:
- From the task page, click on the “Import” button and navigate to the “Generate Synthetic Task” page.
- Provide an appropriate prompt in the “Write Prompt” text box and click on the settings icon located on the right side of the page.
- Enter the API endpoint URL and secret key, then click on “validate.”
- After validating the connection, set the desired temperature and the number of tasks to generate.
- Click on the “Generate” button to create synthetic tasks.
By default “synthetic” tag is added for imported synthetic tasks
In previous versions, users had to manually add tags to synthetically generated tasks or else tasks imported into the task page lacked any associated tags. Starting with version 6.5.0, when tasks are imported, they now come with synthetic tags already associated with them during import in the task page.
This improvement saves time by eliminating the need for manual tag assignment and ensures that imported tasks are accurately tagged from the start, improving organization and searchability. Also, this enhancement streamlines the workflow for managing and organizing synthetic tasks, making it easier to work with large datasets as well.