Drop smart chat now supports visual models!
Supported models include: Claude 3 Haiku，Claude 3 Sonnet， Claude 3 Opus as well as GPT-4o (For GPT-4o, it also supports setting the image definition level to be high or low.)。）
Clients for each platform have been released，Update 0.6.3 version。
Restrictions on Use
Because the model has a processing power limit for images，On every conversation send，The Lag Zhiliao client supports sending up to 5 pictures，Each image must not exceed 3.5MB in size，If the user selects an image that is larger than 3.5MB，A pop-up window will appear for the user to choose whether to compress or discard。(But be careful.)，Different models process different amounts of images at a time，Specifically, it should be used according to the model setting。）
Drop smart chat API
likewise，Drop smart chat API also already supports picture vision，Available to users who use the API gpt-4o claude-3-5-sonnet claude-3-opus claude-3-sonnet claude-3-haiku Use the image feature as the model name，Requests are all unified OpenAI format。
For GPT-4o，Drop smart chat API is not supported detail for auto mode，If the field is not set or set to auto ，then it defaults high 。
