Categorization
Categorization classifies documents based on configurable criteria. Any extracts the text of the document, then sends it to the AI, which analyzes it to work out a category. The category returned by the AI is then stored in a metadata.
This module is used in the content import, archive import and synchronization flows.
Setting up the AI service is described on the Mistral integration page.
- Server access configuration: server access module that holds the location of the service and its authentication information, centralized for every application. It must hold the configuration of an AI server.
- A.I. model: AI model chosen in the list.
- Maximum tokens supported by this model: limit of the selected engine, retrieved automatically.
- Limit the number of tokens sent: caps the size of the text sent to the AI. A token stands for about 4 characters in French and 5 in English.
- Maximum tokens sent: limit in tokens (cannot exceed the maximum supported by the engine).
- Configure temperature: sets the variability of the AI answers: high, it diversifies them. Low, it makes them more predictable.
- Temperature: number between 0 and 10 (7 by default).
- A.I. language: language used to communicate with the engine, chosen in the list or "Language of content". In the latter case, the engine works out the language of the document and uses the matching context and category definitions.
- Context and instructions for A.I.: context passed to the AI. For instance: "Contents related to recruitment, payroll management, and customer registrations".
- Metadata for category: metadata the category is saved into.
- Default category: category assigned when the AI cannot work one out.
- Categories: each row of the table stands for a unique category, with an optional internationalized definition (if Language of content).
- Category: name of the category.
- Definition: definition of the category. A common-sense category (Contract, Invoice, resume) needs none. A finer category does, so the AI understands its context. If the AI is uncertain, the default category is used. For instance: "Contract with a client company for which our company will look for candidates for positions open at the client, stating the price per posted position and the compensation terms of the recruitment agents when a candidate is placed with them".
The "Test model" button opens a window to pass a text and get the result live with the model and the module as configured.
Flows
This module can be used in the following flows: