Differences

This shows you the differences between two versions of the page.

--- 712:ai_configuration [2026/03/02 13:16] – Doczkal, Tristan
+++ 712:ai_configuration [2026/10/20 13:36] (current) – Doczkal, Tristan
@@ Line 1: / Line 1: @@
-====== AI Configuration ======
+====== AI Feature Configuration: Chatbot Assistant and Content Generation ======
-===== AI Feature Configuration: Chatbot Assistant and Content Generation =====
-Content generation must always be configured to use the AI features, while the chatbot itself is optional. However, if the chatbot is used, it requires content generation to be configured first.
+To activate the AI chatbot and the content generation feature in Stages, the following steps are required.
+**The content generation feature needs to be configured to use the chatbot feature. The chatbot feature configuration is arbitrary - the content generation feature can be used without the chatbot feature.**
 ==== Stages version ====
-The chatbot will only work with Stages v7.12 or higher while the content generation feature works with Stages v7.11 or higher.
+**Chatbot** requires Stages v7.12 or higher.
+**Content generation** requires Stages v7.11 or higher.
 ==== Metamodel ====
-A new unified configuration metamodel for Stages v7.12 / v.7.11 is required to support the AI features. Please contact [[[email protected]]] for further metamodel update instructions - depending on your Stages version and server operating system. If you use a customized metamodel, please contact your Stages product consultant to extend your metamodel.
+A new unified configuration metamodel for Stages v7.12 / v.7.11 is required to support the AI features. Please contact [[[email protected]]] for further metamodel update instructions - depending on your Stages version and server operating system.
+If you use a customized metamodel, please contact your Stages product consultant to extend your metamodel.
 ==== User permissions ====
@@ Line 141: / Line 146: @@
 </cg>
 </code>
+**When using models newer than gpt4o (like gpt5)**
+>The temperature has to be adjusted to the default value of 1. Add <cg-property name="temperature" value="1" /> to the relevant <cg-hosts>
+>The <chatbot-property name="maxTokens" value="500"></chatbot-property> has to be replaced with <chatbot-property name="maxCompletionTokens" value="500"></chatbot-property>
 **AI content generation feature (OpenAI compatible):**
@@ Line 234: / Line 245: @@
   ai.model.url = [azure_ai_ressource_url]
   ai.model.key = [azure_ai_ressource_key]
-  ai.security.user = [custom_name_to_identify_stages_to_azure]
+  ai.security.user = [arbitrary_custom_name_to_identify_stages_to_azure]
   ai.translateservice.url = [azure_translate_service_url]
@@ Line 302: / Line 313: @@
 ===== AI Feature Tokenizer Configuration =====
-LLM that are NOT using the standard byte-pair-encoding algorithm CANNOT be used with the Azure tokenizer. Stages implements the HuggingFaceTokenizer from deep java library to support customized tokenizer.
+>Attention - Introduced with 7.12.8.1: \\ If openAiCompatible Adapter is used and no Tokenizer is provided via the conf folder, Stages falls back to a generic o200k based Tokenizer that is suitable for most of the late openAi compatible models.
+LLM that are NOT using the standard byte-pair-encoding algorithm or are provided via the openAICompatible adapter CANNOT be used with the Azure tokenizer. Stages implements the HuggingFaceTokenizer from deep java library to support customized tokenizer.
 Add the property “tokenizerFolder” to the cg-host section
@@ Line 311: / Line 324: @@
   </cg-host>
- In methodpark\stages\conf
+In methodpark\stages\conf
 Create a folder tokenizer\custom-model-v1 ← make sure the folder name exactly matches the value in the tokenizerFolder property
@@ Line 413: / Line 426: @@
 }
 </code>