Skip to content

feat(wren-ai-service): add support for new GPT-5 models in configuration files (ai-env-changed) #1875

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

Merged
cyyeh merged 6 commits into from
Aug 8, 2025
Merged

feat(wren-ai-service): add support for new GPT-5 models in configuration files (ai-env-changed) #1875

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ab7edec
feat(wren-ai-service): add support for new GPT-5 models in configurat…
yichieh-lu Aug 8, 2025
a450d66
fix
cyyeh Aug 8, 2025
648d089
fix(config): update context window size for GPT-5 models to 380000 ac…
yichieh-lu Aug 8, 2025
39d83f7
fix(config): standardize context window size for all GPT-5 models to …
yichieh-lu Aug 8, 2025
02b6f74
update
cyyeh Aug 8, 2025
0720398
Merge branch 'main' into feat/wren-ai-service/support-gpt-5
cyyeh Aug 8, 2025
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
19 changes: 18 additions & 1 deletion deployment/kustomizations/base/cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,24 @@ data:
n: 1
seed: 0
temperature: 0

- model: gpt-5-nano-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
- model: gpt-5-mini-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
- model: gpt-5-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
---
type: embedder
provider: litellm_embedder
Expand Down
18 changes: 18 additions & 0 deletions docker/config.example.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,24 @@ models:
n: 1
seed: 0
temperature: 0
- model: gpt-5-nano-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
- model: gpt-5-mini-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
- model: gpt-5-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0

---
type: embedder
Expand Down
796 changes: 694 additions & 102 deletions wren-ai-service/poetry.lock
View file
Open in desktop

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions wren-ai-service/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ package-mode = false
[tool.poetry.dependencies]
python = ">=3.12.*, <3.13"
fastapi = "^0.115.2"
uvicorn = {extras = ["standard"], version = "^0.30.1"}
uvicorn = {extras = ["standard"], version = "^0.29.0"} # Litellm requires uvicorn < 0.30.0
python-dotenv = "^1.0.1"
haystack-ai = "==2.7.0"
openai = "^1.40.0"
Expand All @@ -33,8 +33,8 @@ pydantic-settings = "^2.5.2"
google-auth = "^2.35.0"
tiktoken = "^0.8.0"
jsonschema = "^4.23.0"
litellm = "^1.70.0"
boto3 = "^1.35.90"
litellm = {extras = ["proxy"], version = "^1.75.2"}
boto3 = "^1.34.34" # Litellm requires boto3 = 1.34.34
qdrant-client = "==1.11.0"

[tool.poetry.group.dev.dependencies]
Expand Down
18 changes: 18 additions & 0 deletions wren-ai-service/tools/config/config.example.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,24 @@ models:
n: 1
seed: 0
temperature: 0
- model: gpt-5-nano-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
- model: gpt-5-mini-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
- model: gpt-5-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0

---
type: embedder
Expand Down
18 changes: 18 additions & 0 deletions wren-ai-service/tools/config/config.full.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,24 @@ models:
n: 1
seed: 0
temperature: 0
- model: gpt-5-nano-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
- model: gpt-5-mini-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0
- model: gpt-5-2025-08-07
context_window_size: 380000
kwargs:
max_completion_tokens: 4096
n: 1
seed: 0

---
type: embedder
Expand Down
5 changes: 4 additions & 1 deletion wren-launcher/commands/launch.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,7 +109,7 @@ func askForGenerationModel() (string, error) {

prompt := promptui.Select{
Label: "Select an OpenAI's generation model",
Items: []string{"gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano"},
Items: []string{"gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "gpt-5", "gpt-5-mini", "gpt-5-nano"},
}

_, result, err := prompt.Run()
Expand Down Expand Up @@ -389,6 +389,9 @@ func getOpenaiGenerationModel() (string, bool) {
"gpt-4.1": true,
"gpt-4.1-mini": true,
"gpt-4.1-nano": true,
"gpt-5": true,
"gpt-5-mini": true,
"gpt-5-nano": true,
}
if !validModels[openaiGenerationModel] {
pterm.Error.Println("Invalid generation model", openaiGenerationModel)
Expand Down
3 changes: 3 additions & 0 deletions wren-launcher/utils/docker.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,9 @@ var generationModelToModelName = map[string]string{
"gpt-4.1": "gpt-4.1-2025-04-14",
"gpt-4.1-mini": "gpt-4.1-mini-2025-04-14",
"gpt-4.1-nano": "gpt-4.1-nano-2025-04-14",
"gpt-5": "gpt-5-2025-08-07",
"gpt-5-mini": "gpt-5-mini-2025-08-07",
"gpt-5-nano": "gpt-5-nano-2025-08-07",
}

func replaceEnvFileContent(content string, projectDir string, openaiApiKey string, openAIGenerationModel string, hostPort int, aiPort int, userUUID string, telemetryEnabled bool, platform string, localStorage string) string {
Expand Down
Loading