• Open data
• LLM (Large Language Model)
  • Setting prompts
• Highlights
• Agent

This section allows you to configure the options for features using artificial intelligence: data enrichment with open data, generation of a transformation function, display of highlights and DigDash Agent.

Open data

Here you can activate the open data functionality:

• Check the Enable the open data functionality box.
  ➡ The Enrich with open data command is then available in the data model context menu.
  

It is also possible to automatically detect whether open data compatible with your data is available, when your data model is created. To do this:

• Check the Enable open data functionality when creating a data model box .
  ➡ If open data compatible with your data is available, it will be offered to you when you create your data model (after clicking on the Finish button when configuring the data model in the Studio).

The field The identifier of the role containing the open data models contains the identifier of the role dedicated to Digdash Open Data models.

LLM (Large Language Model)

Here you can activate and specify the LLM (large language model) used by the AI wizard for the generation of transformation functions.

1. Tick the Activate LLM box.
2. Select the LLM Provider from the drop-down list.

3. Fill in the following information:

   	OpenAI	Google Gemini	Ollama
   Server URL	https://api.openai.com	https://generativelanguage.googleapis.com/v1beta/models/nom_du_modèle The URL contains the model used by Gemini. Thus, model_name should be replaced by the name of the chosen model. For example: https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-latest:generateContent Click on the following link to consult the list of available models: https://ai.google.dev/gemini-api/docs/models/gemini?hl=fr	Enter the server URL in the following format: http://[server]:[port] For example : http://lab1234.lan.digdash.com:11434
   API key	Enter your API key. See the paragraph Configuring an OpenAI API key if necessary.	Enter your API key. See the paragraph Configuring a Gemini API key if necessary.	Ollama does not require an API key.
   Model	Enter the name of the chosen model. For example, gpt-3.5-turbo. Click on the following link to consult the list of available models: https://platform.openai.com/docs/models	The model is not entered here but directly in the server URL. The field must remain empty.	Enter the model identifier. We recommend the following models: Codestral 22B: LLM specialising in code generation (small, high-performance model). With the level of quantization level Q4_K_M, the identifier is codestral:22b-v0.1-q4_K_M Llama 3.3 70B : General-purpose LLM for code-generating tasks. With the quantization level Q4_K_M, the identifier is llama3.3:70b-instruct-q4_K_M Click on the following link to consult the list of available models: https://ollama.com/search

4. Click on Save.

To return to the default values, click Reset.

Setting prompts

The prompts (or instructions) used by default for generating data transformations are stored in the /home/digdash/webapps/ddenterpriseapi/WEB-INF/classes/resources/llm directory . There is a prompt for each provider. ❗These prompts MUST NOT be changed.

You can define a custom prompt on the same model, keeping the last lines :

request: #/*REQUEST_CLIENT*/#

In order to be taken into account, it must be named custom.prompt and placed in the /home/digdash/appdata/default/Enterprise Server/ddenterpriseapi/config directory .

Highlights

Some default values for highlights parameters ars eset by default. You can change these values if you wish to influence the way in which highlights are identified.

Agent

This section allows you to configure the server parameters for the use of DigDash Agent. See paragraph Configuring DigDash server settings for a detailed description.