Configuring the model

1. Select the settings icon in the Build tab.
2. Then, in the side panel, expand the Advanced options if you want to view all the pre-configured fields:

• Model mode - Choose between the Standard image-only model or a model that combines both text and image to improve performance on documents containing multiple tables. Table enrichment can impact performance on certain documents with very complex tabular elements.
• Version - Specific version of LLM to use. Currently, only GPT-4o is available.​
• Temperature - The sampling temperature to use. Select a number between 0.0 and 2.0. Higher values make the output more random​.
• Top P - Samples only from tokens with the top_p probability mass​. Select a number between 0.0 and 1.0.
• Seed - If specified, repeated requests with the same seed and parameters should return the same result​.
• Frequency penalty - Select a number between -2.0 and 2.0. Positive values reduce the probability of the model repeating tokens that have already appeared in the text.
• Prompt override - Overrides the default system prompt with a new value. This option is disabled by default. Once enabled, the Append task instructions prompt and Append field instructions prompt options are enabled as well for configuration.