| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| 712:ai_configuration [2026/03/02 13:16] – Doczkal, Tristan | 712:ai_configuration [2026/03/02 14:15] (current) – Doczkal, Tristan |
|---|
| * If run on consumer hardware, it will probably be necessary to increase the default timeout. | * If run on consumer hardware, it will probably be necessary to increase the default timeout. |
| |
| <code -> | <code xml> |
| <cg> | <cg> |
| <cg-type name="openAICompatible"> | <cg-type name="openAICompatible"> |
| Please stop the Stages service after saving the changes, run the update.bat or .sh script located under /methodpark/stages/bin/ and restart Stages. | Please stop the Stages service after saving the changes, run the update.bat or .sh script located under /methodpark/stages/bin/ and restart Stages. |
| |
| ===== AI Feature Configuration: How to create Azure OpenAI services ===== | ===== How to create Azure OpenAI services ===== |
| |
| 1. Login to Azure-Management-Portal and navigate to "Azure OpenAI" service:\\ \\ {{ :712:create_azure_openai_services_01.jpg?400&direct }}\\ 2. Create a new service within the OpenAI service:\\ \\ {{ :712:create_azure_openai_services_02.jpg?400&direct }}\\ 3. Define basic information for the resource - e.g. select region:\\ \\ {{ :712:create_azure_openai_services_03.jpg?400&direct }}\\ 4. Create resource: click "Create":\\ \\ {{ :712:create_azure_openai_services_04.jpg?400&direct }}\\ 5. Select resource and navigate to "AI Foundry portal". Required AI models need to be configured here:\\ \\ {{ :712:create_azure_openai_services_05.jpg?400&direct }}\\ 6. Within "AI foundry portal" these three models need to be deployed:\\ \\ {{ :712:create_azure_openai_services_06.jpg?400&direct }}\\ {{ :712:create_azure_openai_services_07.jpg?400&direct }}\\ 7. Within the resource navigate to "Keys and Endpoints":\\ \\ {{ :712:create_azure_openai_services_08.jpg?200&direct }}\\ 8. Here the required access data for Stages can be exported (URL, Key):\\ \\ {{ :712:create_azure_openai_services_09.jpg?400&direct }}\\ 9. Afterwards create another resource for the translator-services:\\ \\ {{ :712:create_azure_openai_services_10.jpg?400&direct }}\\ {{ :712:create_azure_openai_services_11.jpg?400&direct }}\\ 10. Define name and region:\\ \\ {{ :712:create_azure_openai_services_12.jpg?400&direct }}\\ 11. Leave system-identitiy-switch turned "off":\\ \\ {{ :712:create_azure_openai_services_13.jpg?400&direct }}\\ 12. Create resource: click "Create":\\ \\ {{ :712:create_azure_openai_services_14.jpg?400&direct }}\\ 13. Export Stages access data (Key, Endpoint):\\ \\ {{ :712:create_azure_openai_services_15.jpg?400&direct }}\\ If you want to check if Stages can reach your AI resources please execute the command below in a command shell on the server that Stages is installed on: | Please follow the linked instructions to create the needed AI ressources/models. This will get you the needed URLs for the configuration. |
| | |
| | **[[:712:ai_configuration:create_openai_services|Creat OpenAI services]]** |
| | |
| | If you want to check if Stages can reach your AI resources please execute the command below in a command shell on the server that Stages is installed on: |
| |
| Linux: | Linux: |
| 1. cg-host configuration in config.xml | 1. cg-host configuration in config.xml |
| |
| <code -> | <code xml> |
| <cg-type name="openAICompatible"> | <cg-type name="openAICompatible"> |
| <cg-host ident="training-model" url="${ai.model.url}" displayName="DeepSeek V3.2 for Chat"> | <cg-host ident="training-model" url="${ai.model.url}" displayName="DeepSeek V3.2 for Chat"> |
| >You need to change all chatbot steps that shall use the configured LLM | >You need to change all chatbot steps that shall use the configured LLM |
| |
| <code -> | <code xml> |
| default: | default: |
| <chatbot-step ident="summaries" type="azureOpenAI" host="gpt-4o-mini"> | <chatbot-step ident="summaries" type="azureOpenAI" host="gpt-4o-mini"> |