Define how the assistant responds to you. For example: "Be concise and direct" or "Use detailed explanations with examples" or "Respond in a friendly, casual tone"
User Information
Provide information about your personality, interests, and preferences to help LyRinth tailor its responses to you.
Memory
Allow LyRinth to remember important information from your conversations and reference it in future chats.
Enable streaming to receive partial responses as they are generated, providing a more interactive experience. Recommended: Keep this enabled for faster perceived response times.
When enabled, LyRinth will automatically decide when to use tools based on the context of your questions.
Controls the randomness of the model's output. Recommended: Set to 1.5 if you encounter issues when generating tables.
1
Sets the maximum number of tokens the model can generate in its response.
Controls the diversity of the model's output by focusing on the most probable tokens.
0.9
Limits the model to consider only the top K most probable next tokens.
Controls the model's tendency to repeat the same phrases or sentences.
Values > 1.0 penalize repetition, while values < 1.0 encourage it.
1.0
Use seed to get deterministic results.
0 means random seed.
Use your own API key to remove rate limits and enjoy unlimited usage.
Without your key, you'll use LyRinth's shared service with usage limits. Get a free API key from the provider - it costs you nothing to try!
WE WILL NOT USE YOUR API KEYS FOR ANY OTHER PURPOSES.