最新消息:雨落星辰是一个专注网站SEO优化、网站SEO诊断、搜索引擎研究、网络营销推广、网站策划运营及站长类的自媒体原创博客

c# - How to count # of tokens consumed by OpenAI Assistant while streaming the message - Stack Overflow

programmeradmin1浏览0评论

I am using openAI Assistant, I get the streamingUpdate using

streamingUpdate = assistantClient.CreateRunStreaming(thread, assistant);

I could iterate through streamingUpdate and send the response to the client using SignalR api. however I would like to know how to count the #of tokens consumed in the streaming mode.

I am using openAI Assistant, I get the streamingUpdate using

streamingUpdate = assistantClient.CreateRunStreaming(thread, assistant);

I could iterate through streamingUpdate and send the response to the client using SignalR api. however I would like to know how to count the #of tokens consumed in the streaming mode.

Share Improve this question edited Jan 8 at 19:39 General Grievance 5,04338 gold badges37 silver badges56 bronze badges asked Nov 18, 2024 at 10:14 Sankaranarayanan RajkumarSankaranarayanan Rajkumar 511 silver badge7 bronze badges
Add a comment  | 

1 Answer 1

Reset to default 1

I found the way to get the token count

CompletionTokens = assistantClient.GetRuns(threadID).Select(f => f.Usage.CompletionTokens).SingleOrDefault();
PromptTokens = assistantClient.GetRuns(threadID).Select(f => f.Usage.PromptTokens).SingleOrDefault();
TotalTokens = assistantClient.GetRuns(threadID).Select(f => f.Usage.TotalTokens).SingleOrDefault();
发布评论

评论列表(0)

  1. 暂无评论