{"id":432,"date":"2024-08-22T13:39:56","date_gmt":"2024-08-22T11:39:56","guid":{"rendered":"https:\/\/iag-recursos.azurewebsites.net\/?page_id=432"},"modified":"2024-10-10T10:15:34","modified_gmt":"2024-10-10T08:15:34","slug":"2-2-herramientas-personalizadas-de-iag","status":"publish","type":"page","link":"https:\/\/iag.recursos.uoc.edu\/en\/2-2-herramientas-personalizadas-de-iag\/","title":{"rendered":"2.2. Customized GAI tools"},"content":{"rendered":"

Some GAI models that can be installed on a personal computer have already appeared. This is an artificial intelligence similar to ChatGPT using the GPT4All project. This open-source project, available on GitHub, allows us to operate a chatbot locally without needing the internet or a powerful computer, although with more limited capabilities than models such as GPT-4. In addition, we can train the GAI with data to customize an IAG.<\/p>\n

GPT4All primarily uses models based on GPT-J, derived from GPT-2 (OpenAI) or Llama\u2019s AI (Meta), so it offers a more private alternative for tasks such as answering questions, assisting in writing, summarizing documents and other basic functions. To install it, visit https:\/\/gpt4all.io<\/a>, choose the version for your operating system (Windows, macOS or GNU\/Linux) and follow the steps to select and download the AI models, which are pretrained multi-gigabyte files.<\/p>\n

Once the desired model is installed and configured, you can start interacting with the chatbot. Although the models are primarily trained in English, they may work to some degree in Spanish. In addition, the app allows new models to be updated and downloaded as they become available (some models require APIs and, therefore, work upon payment, but some are free, such as Mistral).<\/p>\n

\"\"
Gpt4all.io
Source: own creation<\/figcaption><\/figure>\n

Another company that has provided a similar option is Nvidia with its ChatRTX tool. It is a GAI tool that allows us to customize a GPT model connected to our own content: documents, notes or other data. This allows us to query a custom chatbot to get context-relevant responses quickly. But there is currently an essential requirement: our personal computer, where we have installed ChatRTX, must have a Nvidia RTX-type graphics card.<\/p>\n

Nvidia. (22 of April 2024). Build a Custom LLM with ChatRTX. https:\/\/www.nvidia.com\/en-us\/ai-on-rtx\/chatrtx\/<\/a><\/p>\n<\/div>\n

\"\"
ChatRTX installed on a personal computer
Source: Nvidia<\/figcaption><\/figure>\n

There is also the option to use similar technologies on mobile devices, such as LuzIA<\/a>.<\/p>\n

If we do not want to install software on our computer, we can create customized ChatGPTs of our own or use public ChatGPTs. This is called Chat GPRT\u2019s GPTs<\/strong>.<\/p>\n

Public GPTs can be found at the link below: https:\/\/chat.openai.com\/gpts<\/a><\/p>\n<\/div>\n

\"\"
OpenAI<\/a>
Source: own creation<\/figcaption><\/figure>\n

If we want to create our own custom GPT, we will need a paid version of ChatGPT. We must access the website: https:\/\/chat.openai.com\/gpts\/editor<\/a>.<\/p>\n

\"\"
OpenAi<\/a>
Source: own creation<\/figcaption><\/figure>\n

How do we parameterize it?<\/h3>\n