> For the complete documentation index, see [llms.txt](https://docs.docbits.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.docbits.com/end-user-and-partner-section/end-user-section/validation-screen/supplier-specific-ai-model-for-field-and-table-extraction.md). # Selecting a Supplier-Specific AI Model for Field and Table Extraction In the tools section of the **Validation screen**, you can choose the AI model used for **Field Extraction** and **Table Extraction**.\ This entry point changes the override for the current extraction-template context. The preference is stored by organization and template (`tfidf_id`); the supplier association does not guarantee that every template or historical document for that supplier changes. With no override, the applicable organization setting is used. To change the model, open the options menu by clicking the **More options** (three dots) button on the right side of the screen, then choose one of the available models:
The menu currently provides **Full**, **Fast**, **Nexus**, **Nexus Flash**, **Auto** and **Auto Nexus**. Check the current UI information and subscription terms for availability and charges. Do not assume that one option is always the most accurate or fastest, or that every organization defaults to Fast. Selecting a different model can require confirmation and restart extraction. Check the document and scope before confirming. Opening the menu alone does not change the setting; no model was selected or confirmed for these illustrations.

Options menu for the illustrated extraction-template context, using a synthetic example invoice.

The AI Model dropdown with six options and a synthetic example invoice; no model change is shown.

If extraction results are unsatisfactory, compare other available models using approved test documents and check the extracted values, processing time and charges. A switch may reprocess a document and does not guarantee improvement. To configure the **organization default** or review **template-specific overrides**, please refer to the corresponding documentation [**here**](/administration-and-setup/settings/document-processing/classification-and-extraction/ai-model.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.docbits.com/end-user-and-partner-section/end-user-section/validation-screen/supplier-specific-ai-model-for-field-and-table-extraction.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.