Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. Weโ€™ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

๐Ÿ› fix: MiniMax output long content interrupted by non-existent error #4088

Merged
merged 13 commits into from
Sep 25, 2024

Conversation

sxjeru
Copy link
Contributor

@sxjeru sxjeru commented Sep 23, 2024

๐Ÿ’ป ๅ˜ๆ›ด็ฑปๅž‹ | Change Type

  • โœจ feat
  • ๐Ÿ› fix
  • โ™ป๏ธ refactor
  • ๐Ÿ’„ style
  • ๐Ÿ‘ท build
  • โšก๏ธ perf
  • ๐Ÿ“ docs
  • ๐Ÿ”จ chore

๐Ÿ”€ ๅ˜ๆ›ด่ฏดๆ˜Ž | Description of Change

ๅŽป้™คไบ†้ป˜่ฎค็š„ frequency_penalty ๅ‚ๆ•ฐใ€‚

ๅŒๆ—ถ็ป“ๅˆไธŠไธ‹ๆ–‡็ช—ๅฃ็ญ‰ๆจกๅž‹ไฟกๆฏ๏ผŒไผ˜ๅŒ–ไบ†้ป˜่ฎค็š„ max_tokens ๅ‚ๆ•ฐใ€‚

ๅฆๅค–็”ฑไบŽ minimax ๆตๅผ่พ“ๅ‡บๅœจๆœ€ๅŽไผšไธ€ๆฌกๆ€ง่พ“ๅ‡บๆ‰€ๆœ‰ๅ†…ๅฎน๏ผŒๅฏผ่‡ดๆœ€ๅŽไธ€ไธช chunk ๆ— ๆณ•่ขซ่งฃๆžไธบ json๏ผŒๆ•…ๅธธๅœจ็”ŸๆˆๅฎŒๆฏ•ๆ—ถๆŠฅ้”™ใ€‚็›ฎๅ‰ๅขžๅŠ ไบ†ๅค„็†ๆต็จ‹๏ผŒๅŽป้™คๆœ€ๅŽไธ€ๆฌก็š„ data ๆตๆ•ฐๆฎ๏ผŒไปฅไฟฎๅคๆญค้—ฎ้ข˜ใ€‚

ไธชไบบๆฒกๆœ‰ๆกไปถๆต‹่ฏ•๏ผŒๅฏไปฅๆต‹่ฏ•ๅŽๅ†ๅˆๅนถใ€‚
ๆต‹่ฏ•ๅฏ็”จใ€‚

๐Ÿ“ ่กฅๅ……ไฟกๆฏ | Additional Information

fix #4054

image

image

Copy link

vercel bot commented Sep 23, 2024

@sxjeru is attempting to deploy a commit to the LobeHub Pro Team on Vercel.

A member of the Team first needs to authorize it.

@dosubot dosubot bot added the size:S This PR changes 10-29 lines, ignoring generated files. label Sep 23, 2024
@lobehubbot
Copy link
Member

๐Ÿ‘ @sxjeru

Thank you for raising your pull request and contributing to our Community
Please make sure you have followed our contributing guidelines. We will review it as soon as possible.
If you encounter any problems, please feel free to connect with us.
้žๅธธๆ„Ÿ่ฐขๆ‚จๆๅ‡บๆ‹‰ๅ–่ฏทๆฑ‚ๅนถไธบๆˆ‘ไปฌ็š„็คพๅŒบๅšๅ‡บ่ดก็Œฎ๏ผŒ่ฏท็กฎไฟๆ‚จๅทฒ็ป้ตๅพชไบ†ๆˆ‘ไปฌ็š„่ดก็ŒฎๆŒ‡ๅ—๏ผŒๆˆ‘ไปฌไผšๅฐฝๅฟซๅฎกๆŸฅๅฎƒใ€‚
ๅฆ‚ๆžœๆ‚จ้‡ๅˆฐไปปไฝ•้—ฎ้ข˜๏ผŒ่ฏท้šๆ—ถไธŽๆˆ‘ไปฌ่”็ณปใ€‚

Copy link

codecov bot commented Sep 23, 2024

Codecov Report

Attention: Patch coverage is 93.54839% with 2 lines in your changes missing coverage. Please review.

Project coverage is 92.48%. Comparing base (2d956a3) to head (dd07c2f).
Report is 28 commits behind head on main.

Files with missing lines Patch % Lines
src/libs/agent-runtime/minimax/index.ts 87.50% 2 Missing โš ๏ธ
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #4088      +/-   ##
==========================================
+ Coverage   92.45%   92.48%   +0.02%     
==========================================
  Files         482      482              
  Lines       34354    34497     +143     
  Branches     3214     3232      +18     
==========================================
+ Hits        31763    31905     +142     
- Misses       2591     2592       +1     
Flag Coverage ฮ”
app 92.48% <93.54%> (+0.02%) โฌ†๏ธ
server 97.36% <รธ> (รธ)

Flags with carried forward coverage won't be shown. Click here to find out more.

โ˜” View full report in Codecov by Sentry.
๐Ÿ“ข Have feedback on the report? Share it here.

Copy link

vercel bot commented Sep 23, 2024

The latest updates on your projects. Learn more about Vercel for Git โ†—๏ธŽ

Name Status Preview Comments Updated (UTC)
lobe-chat-preview โœ… Ready (Inspect) Visit Preview ๐Ÿ’ฌ Add feedback Sep 25, 2024 3:12pm

@LovelyGuYiMeng
Copy link
Contributor

LovelyGuYiMeng commented Sep 23, 2024

{
  "message": "chat response streaming chunk parse error, please contact your API Provider to fix it.",
  "context": {
    "error": {
      "message": "Cannot read properties of undefined (reading '0')",
      "name": "TypeError"
    },
    "chunk": {
      "raw": "4890\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"ๆ‘ๆฐ‘ไปฌไธ€ไธชๆŽฅไธ€ไธชๅœฐๅ–ไธ‹ไบ†่ฏๅ‰‚๏ผŒไป–ไปฌ็š„็—…ๆƒ…ๅผ€ๅง‹ๅฅฝ่ฝฌ๏ผŒๆœ€็ปˆๅ…จ้ƒจๅบทๅคใ€‚่Ž‰\",\"role\":\"assistant\",\"name\":\"MMๆ™บ่ƒฝๅŠฉ็†\",\"audio_content\":\"\"}}],\"created\":1727073422,\"model\":\"abab6.5s-chat\",\"object\":\"chat.completion.chunk\",\"usage\":{\"total_tokens\":0,\"total_characters\":0},\"input_sensitive\":false,\"output_sensitive\":false,\"input_sensitive_type\":0,\"output_sensitive_type\":0,\"output_sensitive_int\":0}\n\n"
    }
  }
}

่ฏฅ็‰ˆๆœฌไพๆ—ง่พ“ๅ‡บ้•ฟๆ–‡ๆœฌไธญๆ–ญ

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


{
"message": "chat response streaming chunk parse error, please contact your API Provider to fix it.",
"context": {
"error": {
"message": "Cannot read properties of undefined (reading '0')",
"name": "TypeError"
},
"chunk": {
"raw": "4890","choices":[{"index":0,"delta":{"content":"The villagers drank the potion one after another , their conditions began to improve, and eventually they all recovered. "}}],"created":1727073422,"model":"abab6.5s-chat","object":"chat.completion.chunk","usage" :{"total_tokens":0,"total_characters":0},"input_sensitive":false,"output_sensitive":false,"input_sensitive_type":0,"output_sensitive_type":0 ,"output_sensitive_int":0}\n\n"
}
}
}

This version still outputs long text interruptions

@dosubot dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. and removed size:S This PR changes 10-29 lines, ignoring generated files. labels Sep 23, 2024
@LovelyGuYiMeng
Copy link
Contributor

maxtoken่ฆ้™ๅˆถๅœจ4kๅ’Œ8kๅ—๏ผŒๆ˜Žๆ˜Žๆœ‰ๆ›ด้ซ˜็š„ไธŠ้™

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


Should maxtoken be limited to 4k and 8k? There is obviously a higher limit

@LovelyGuYiMeng
Copy link
Contributor

image
ๅฝ“ๅ‰็‰ˆๆœฌ้•ฟๆ–‡ๆœฌไธๅ†ๆŠฅ้”™๏ผŒไฝ†ไป็„ถไผšไธญๆ–ญ

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


image
In the current version, long text no longer reports an error, but it will still be interrupted.

@arvinxx
Copy link
Contributor

arvinxx commented Sep 23, 2024

maxtoken่ฆ้™ๅˆถๅœจ4kๅ’Œ8kๅ—๏ผŒๆ˜Žๆ˜Žๆœ‰ๆ›ด้ซ˜็š„ไธŠ้™

ๆœ‰ๆ–‡ๆกฃๅ—

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


Should maxtoken be limited to 4k and 8k? There is obviously a higher limit

Is there any documentation?

@LovelyGuYiMeng
Copy link
Contributor

maxtoken่ฆ้™ๅˆถๅœจ4kๅ’Œ8kๅ—๏ผŒๆ˜Žๆ˜Žๆœ‰ๆ›ด้ซ˜็š„ไธŠ้™

ๆœ‰ๆ–‡ๆกฃๅ—
image
ไป–่ฟ™ๅผ ๅ›พๅฐฑๆ˜ฏmaxtoken่Œƒๅ›ด

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


Should maxtoken be limited to 4k and 8k? There is obviously a higher limit

Is there any documentation?
image
This picture of his is the maxtoken range

@sxjeru
Copy link
Contributor Author

sxjeru commented Sep 23, 2024

max_tokens ๅฏไปฅๅœจ lobechat ๆ‰‹ๅŠจ่ฐƒ๏ผŒ็›ฎๅ‰ๆ˜ฏ็ป™ไบ†ไธ€ไธช่พƒๅคง็š„้ป˜่ฎคๅ€ผใ€‚๏ผˆ็›ธ่พƒไบŽๅŽŸๆœฌ็š„ 256๏ผ‰

่ฏทๅ…ˆไธ่ฆๅˆๅนถ๏ผŒ่ฟ˜ๆœ‰้—ฎ้ข˜ๅพ…ไฟฎๅค๏ผŒๅ‚ๆ•ฐๅชๆ˜ฏๅ…ถไธญไธ€ไธช้—ฎ้ข˜ใ€‚

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


max_tokens can be adjusted manually in lobechat, and currently a larger default value is given. (compared to the original 256)

Please don't merge yet, there are still problems to be fixed, and parameters are just one of them.

@sxjeru sxjeru changed the title ๐Ÿ› fix: Avoid introducing frequency_penalty param for MiniMax ๐Ÿ› fix: MiniMax output long content interrupted by non-existent error Sep 23, 2024
@arvinxx
Copy link
Contributor

arvinxx commented Sep 23, 2024

@sxjeru ๅปบ่ฎฎๆŒ‰ Minimax ็š„ๆ–‡ๆกฃๆฅ็ป™max_token ๅ€ผๅงใ€‚็”จๆˆทไธไธ€ๅฎšไผšๆ„่ฏ†ๅˆฐ่ฟ˜้œ€่ฆๆ‰‹ๅŠจๆ”นไธ‹ๆ‰่ƒฝ่ฎฉ 6.5s ่พ“ๅ‡บๅˆฐ200k+ ใ€‚

ไฝ†็กฎๅฎš่ฟ™ไธชๅ€ผๆ˜ฏๆญฃ็กฎ็š„ๅ—๏ผŸ6.5s ็กฎๅฎš่ƒฝ่พ“ๅ‡บ 200k ็š„output๏ผŸๆˆ‘ไธชไบบๆœ‰็‚นไธๅคช็›ธไฟก

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


@sxjeru suggests setting the max_token value according to the Minimax documentation. Users may not necessarily realize that they need to manually change it to output 200k+ in 6.5s.

But are you sure this value is correct? Are you sure it can output 200k output in 6.5s? I personally don't believe it

@sxjeru
Copy link
Contributor Author

sxjeru commented Sep 23, 2024

ๆ–‡ๆกฃๆ˜ฏ่ฟ™ๆ ทๅ†™็š„ใ€‚
https://platform.minimaxi.com/document/ChatCompletion%20v2?key=66701d281d57f38758d581d0

่ฟ™่พนๆฏ”่พƒๆททๆท†็š„ๆ˜ฏ minimax ๅ‚ๆ•ฐ้‡Œ็š„ max_tokens ็›ธๅฝ“ไบŽ openai ็š„ Max output tokens๏ผŒ่€Œไธๆ˜ฏไธŠไธ‹ๆ–‡็ช—ๅฃๅคงๅฐ๏ผŒๆ‰€ไปฅๆˆ‘ๆ‰ไผšๆฏ”่พƒ่ฐจๆ…Žๅœฐ่ฎพๅฎšใ€‚

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


The documentation says this.
https://platform.minimaxi.com/document/ChatCompletion%20v2?key=66701d281d57f38758d581d0

What is confusing here is that max_tokens in the minimax parameter is equivalent to openai's Max output tokens, so I will set it more carefully.

@arvinxx
Copy link
Contributor

arvinxx commented Sep 23, 2024

ๅปบ่ฎฎๆœ€ๅฅฝๆต‹ไธ‹ output ่พ“ๅ‡บๆ˜ฏๅฆ่ƒฝๅˆฐ 20kโ€ฆ ๅฆ‚ๆžœ่ƒฝๅˆฐ 20k ่‚ฏๅฎšๅฐฑๆฒก้—ฎ้ข˜

@sxjeru
Copy link
Contributor Author

sxjeru commented Sep 23, 2024

ๅบ”่ฏฅไฟฎๅฅฝไบ†ใ€‚minimax ็š„ๆตๅผ่พ“ๅ‡บๆœ‰็‚นๆ„ๆ€๏ผŒๆœ€ๅŽไผšไธ€ๆฌกๆ€งๅ†่พ“ๅ‡บไธ€ๆฌกๆ‰€ๆœ‰ๅ†…ๅฎนใ€‚

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


It should be fixed.

@arvinxx
Copy link
Contributor

arvinxx commented Sep 24, 2024

@sxjeru ci ๆŒ‚ไบ†

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


@sxjeru ci died

@sxjeru
Copy link
Contributor Author

sxjeru commented Sep 25, 2024

ๅทฒไฟฎๅคใ€‚

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


Fixed.

@arvinxx
Copy link
Contributor

arvinxx commented Sep 25, 2024

@sxjeru ๆž„ๅปบๆŒ‚ไบ†

image

@arvinxx
Copy link
Contributor

arvinxx commented Sep 25, 2024

@sxjeru @LovelyGuYiMeng ่ฏด่ฟ˜ๆœ‰ๆˆชๆ–ญ็š„้—ฎ้ข˜๏ผŒๅฆๅค–ๅผ€ไธ€ไธช PR ไฟฎๅง

@arvinxx arvinxx merged commit 4f6e20d into lobehub:main Sep 25, 2024
6 of 8 checks passed
@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


@sxjeru @LovelyGuYiMeng said there is still a truncation problem, please open another PR to fix it

@lobehubbot
Copy link
Member

โค๏ธ Great PR @sxjeru โค๏ธ

The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world.
้กน็›ฎ็š„ๆˆ้•ฟ็ฆปไธๅผ€็”จๆˆทๅ้ฆˆๅ’Œ่ดก็Œฎ๏ผŒๆ„Ÿ่ฐขๆ‚จ็š„่ดก็Œฎ! ๅฆ‚ๆžœๆ‚จๅฏน LobeHub ๅผ€ๅ‘่€…็คพๅŒบๆ„Ÿๅ…ด่ถฃ๏ผŒ่ฏทๅŠ ๅ…ฅๆˆ‘ไปฌ็š„ discord๏ผŒ็„ถๅŽ็งไฟก @arvinxx ๆˆ– @canisminor1990ใ€‚ไป–ไปฌไผš้‚€่ฏทๆ‚จๅŠ ๅ…ฅๆˆ‘ไปฌ็š„็งๅฏ†ๅผ€ๅ‘่€…้ข‘้“ใ€‚ๆˆ‘ไปฌๅฐ†ไผš่ฎจ่ฎบๅ…ณไบŽ Lobe Chat ็š„ๅผ€ๅ‘๏ผŒๅˆ†ไบซๅ’Œ่ฎจ่ฎบๅ…จ็ƒ่Œƒๅ›ดๅ†…็š„ AI ๆถˆๆฏใ€‚

@LovelyGuYiMeng
Copy link
Contributor

image
ๆœ€ๆ–ฐๆž„ๅปบๆƒ…ๅ†ต

@sxjeru sxjeru deleted the patch-1 branch September 25, 2024 15:27
@sxjeru
Copy link
Contributor Author

sxjeru commented Sep 25, 2024

็”จๅฎขๆˆท็ซฏ่ฏทๆฑ‚ๅฐฑๆ˜ฏๆญฃๅธธ็š„๏ผŒไธๆธ…ๆฅšๆ˜ฏ่ถ…ๆ—ถ่ฟ˜ๆ˜ฏไป€ไนˆๅŽŸๅ› ใ€‚

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


It's normal to use the client to request. I don't know if it's a timeout or what the reason is.

github-actions bot pushed a commit that referenced this pull request Sep 25, 2024
### [Version&nbsp;1.19.33](v1.19.32...v1.19.33)
<sup>Released on **2024-09-25**</sup>

#### ๐Ÿ› Bug Fixes

- **misc**: MiniMax output long content interrupted by non-existent error.

#### ๐Ÿ’„ Styles

- **misc**: Update google provider model info.

<br/>

<details>
<summary><kbd>Improvements and Fixes</kbd></summary>

#### What's fixed

* **misc**: MiniMax output long content interrupted by non-existent error, closes [#4088](#4088) ([4f6e20d](4f6e20d))

#### Styles

* **misc**: Update google provider model info, closes [#4129](#4129) ([b1442b9](b1442b9))

</details>

<div align="right">

[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)

</div>
@lobehubbot
Copy link
Member

๐ŸŽ‰ This PR is included in version 1.19.33 ๐ŸŽ‰

The release is available on:

Your semantic-release bot ๐Ÿ“ฆ๐Ÿš€

github-actions bot pushed a commit to bentwnghk/lobe-chat that referenced this pull request Sep 25, 2024
### [Version&nbsp;1.62.14](v1.62.13...v1.62.14)
<sup>Released on **2024-09-25**</sup>

#### ๐Ÿ› Bug Fixes

- **misc**: MiniMax output long content interrupted by non-existent error.

#### ๐Ÿ’„ Styles

- **misc**: Add function call for `taichu_llm`, update google provider model info.

<br/>

<details>
<summary><kbd>Improvements and Fixes</kbd></summary>

#### What's fixed

* **misc**: MiniMax output long content interrupted by non-existent error, closes [lobehub#4088](https://github.com/bentwnghk/lobe-chat/issues/4088) ([4f6e20d](4f6e20d))

#### Styles

* **misc**: Add function call for `taichu_llm`, closes [lobehub#4119](https://github.com/bentwnghk/lobe-chat/issues/4119) ([8f629d8](8f629d8))
* **misc**: Update google provider model info, closes [lobehub#4129](https://github.com/bentwnghk/lobe-chat/issues/4129) ([b1442b9](b1442b9))

</details>

<div align="right">

[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)

</div>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
released size:M This PR changes 30-99 lines, ignoring generated files.
Projects
None yet
4 participants