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.

Sign up for GitHub

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

Already on GitHub? Sign in to your account

fix: add maxTokens to serve mode #1280

Merged
merged 8 commits into from
Nov 12, 2024
Merged

fix: add maxTokens to serve mode #1280

Changes from 6 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e7067b8
fix: add maxTokens to serve mode
samirtahir91 Oct 23, 2024
bc4bdad
Merge branch 'main' into fix/add-max-tokens-to-serve
samirtahir91 Oct 30, 2024
5a84185
Merge branch 'main' into fix/add-max-tokens-to-serve
samirtahir91 Oct 30, 2024
afac15b
Merge branch 'main' into fix/add-max-tokens-to-serve
AlexsJones Oct 31, 2024
6ee2085
Merge branch 'main' into fix/add-max-tokens-to-serve
samirtahir91 Oct 31, 2024
45f72b7
Merge branch 'main' into fix/add-max-tokens-to-serve
samirtahir91 Nov 3, 2024
1357523
Merge branch 'main' into fix/add-max-tokens-to-serve
samirtahir91 Nov 12, 2024
9f68d30
Merge branch 'main' into fix/add-max-tokens-to-serve
samirtahir91 Nov 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions cmd/serve/serve.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
defaultTemperature float32 = 0.7
defaultTopP float32 = 1.0
defaultTopK int32 = 50
defaultMaxTokens int = 2048
)

var (
Expand Down Expand Up @@ -102,6 +103,18 @@
}
return int32(topK)
}
maxTokens := func() int {
samirtahir91 marked this conversation as resolved.
Show resolved Hide resolved
env := os.Getenv("K8SGPT_MAX_TOKENS")
if env == "" {
return defaultMaxTokens
}
maxTokens, err := strconv.ParseInt(env, 10, 32)
if err != nil {
color.Red("Unable to convert maxTokens value: %v", err)
os.Exit(1)
}
return int(maxTokens)

Check warning on line 116 in cmd/serve/serve.go

View check run for this annotation

Codecov / codecov/patch

cmd/serve/serve.go#L106-L116 

Added lines #L106 - L116 were not covered by tests
}
// Check for env injection
backend = os.Getenv("K8SGPT_BACKEND")
password := os.Getenv("K8SGPT_PASSWORD")
Expand All @@ -125,6 +138,7 @@
Temperature: temperature(),
TopP: topP(),
TopK: topK(),
MaxTokens: maxTokens(),

Check warning on line 141 in cmd/serve/serve.go

View check run for this annotation

Codecov / codecov/patch

cmd/serve/serve.go#L141 

Added line #L141 was not covered by tests
}

configAI.Providers = append(configAI.Providers, *aiProvider)
Expand Down
Loading