{"id":6322,"date":"2025-12-18T09:31:52","date_gmt":"2025-12-18T08:31:52","guid":{"rendered":"https:\/\/www.nextfem.it\/it\/?page_id=6322"},"modified":"2026-02-11T17:30:55","modified_gmt":"2026-02-11T16:30:55","slug":"nextfem-ai-tools","status":"publish","type":"page","link":"https:\/\/www.nextfem.it\/it\/nextfem-ai-tools\/","title":{"rendered":"NextFEM AI Tools"},"content":{"rendered":"\n\n\n\n
\"\"<\/td>\n\n

NextFEM AI Tools<\/h2>\n<\/td>\n<\/tr>\n

\n
AI-DRIVEN DESIGN IN NextFEM PROGRAMS<\/h5>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

AI Assistant v2<\/h2>\n

\"\"<\/span><\/p>\n

NextFEM Designer v2.7 integrates the new AI Assistant v2<\/strong>, which supports the NextFEM MCP tools (now shipped with the program). It can be started from the Plugins<\/em> tab.
\nThis plugin keeps the support for simple modelling AI calls in v1 (see chapter below), however the usage with MCP tools is strongly encouraged. The MCP mode can be activated by selecting the “MCP tools<\/em>” checkbox in the main window.<\/p>\n

\"\"
\nAfter selecting the checkbox, please wait for the local MCP server to be started. When you read the number of available MCP tools, you’re ready to go.<\/p>\n

The providers supported by v1 continues to be supported. Generally, the AI client supports OpenAI chat model v1.<\/p>\n\n\n\n\n\n\n\n\n
Provider<\/strong><\/td>\nEndpoint<\/strong><\/td>\n<\/tr>\n
OpenRouter<\/td>\nhttps:\/\/openrouter.ai\/api\/v1<\/td>\n<\/tr>\n
HuggingFace<\/td>\nhttps:\/\/router.huggingface.co\/v1<\/td>\n<\/tr>\n
Groq<\/td>\nhttps:\/\/api.groq.com\/openai\/v1<\/td>\n<\/tr>\n
LM Studio<\/td>\nhttp:\/\/localhost:1234\/v1<\/td>\n<\/tr>\n
Cohere<\/td>\nhttps:\/\/api.cohere.com\/v1<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Please note that the endpoint address to be provided are different from the ones that had to be supplied in v1.<\/p>\n

Finally, v2 supports the storage of endpoint address, API key and chat AI model specification in a CSV file called “LLMkeys.csv” that can be places in the installation folder of NextFEM Designer.
\nSample content of the CSV file:<\/p>\n

#Endpoint;API key;Modelname\r\nhttps:\/\/api.yourprovider.com\/v1;apikey;gpt-4.1<\/pre>\n
Please contact us for further informations.<\/p>\n
AI Assistant v1<\/h2>\n
This chapter illustrates how to use the plugin AI Assistant v1<\/strong> shipped in NextFEM Designer v.2.6.
\nThe plugin, free for everyone, permits to use AI APIs with NextFEM Designer. Users can interact via chat with their favourite AI provides, while the plugin tells the API to format the reply in a way that can be read by the plugin and converted in commands. In that sense, the plugin acts like an AI agent<\/strong> in NextFEM Designer.<\/p>\n
\"\"<\/p>\n
Supported AI providers<\/h4>\n
The user must supply his own API key and AI\/LLM server address. The plugin support natively all LLM APIs that are OpenAI-like, and it has been tested with:<\/p>\n