Skip to content

Commit

Permalink
Update readme
Browse files Browse the repository at this point in the history
  • Loading branch information
aiqinxuancai committed Dec 22, 2023
1 parent 47cf7d4 commit fbd4673
Show file tree
Hide file tree
Showing 2 changed files with 12 additions and 0 deletions.
6 changes: 6 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,12 @@ var msg = await client.SendMessage("{[MrWang][Can Trump be president again?]}",

## Update

### 2.0.0 20231221
* Added support for sending images using the Vision model and pre-computing image tokens (local files only).
* Improved the token algorithm for messages to align with the official API.
* Added more default token count data for official website models and automatic conversion of '16k' in model names to maximum tokens.
* Considering the increasing number of tokens in models, introduced a method to support unlimited MaxResponseTokens and MaxPromptTokens. Setting them to 0 will remove the limit.

### 1.1.4 20230711
* Add support gpt-3.5-turbo-16k

Expand Down
6 changes: 6 additions & 0 deletions README_CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,12 @@ var msg = await client.SendMessage("{[小王][特朗普还能再当总统吗?]

## Update

### 2.0.0 20231221
* 支持Vision model的图片发送,并预先计算图片token(仅本地文件)
* 改进消息的token算法,使其与官方接口一致
* 增加更多官网模型的默认token数量数据,以及自动转换模型名称中的16k字样为最大token
* 鉴于模型的token数量越来越大,支持不限制的MaxResponseTokens、MaxPromptTokens的方法,将其设置为0既可

### 1.1.4 20230711
* 支持gpt-3.5-turbo-16k

Expand Down

0 comments on commit fbd4673

Please sign in to comment.