W/Y expert

Create your custom assistant and experiment with all the available parameters (vision included). Additionally, you can choose to keep the context of your conversation and manage your personal assistant's memory. Your personal data will NOT be collected. To use this app, you must have an account with an AI services provider. Thank you all for your positive comments and feedback. Have fun! -- Current parameters to play with: - model - endpoint - role-system-content: describes what kind of assistant do you want to interact with. The default try to provide a natural interaction (Italian assistant from Florence). - opening exchange: role-user-content and role-assistant-content. - max_tokens: The maximum number of tokens to generate in the completion. - temperature: It makes the output more random or more focused and deterministic. - top_p: Nucleus sampling, the model considers the results of the tokens with top_p probability mass. - n: How many completions to generate for each prompt. - presence_penalty: Positive values increase the model's likelihood to talk about new topics. - frequency_penalty: Positive values decrease the model's likelihood to repeat the same line verbatim.