opensource/WrenAI
3
0
Fork 0
mirror of https://github.com/Canner/WrenAI.git synced 2026-09-01 04:57:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore(wren-ai-service): make openai llm version fixed (#1045)

Browse Source
This commit is contained in:
Chih-Yu Yeh
2024-12-23 10:47:35 +08:00
committed by GitHub
parent 8915cc3bbc
commit d5091604fe
7 changed files with 89 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files
deployment/kustomizations/base/cm.yaml
+20 -20
View File
@@ -23,7 +23,7 @@ data:
POSTHOG_HOST: "https://app.posthog.com"
TELEMETRY_ENABLED: "false"
# this is for telemetry to know the model, i think ai-service might be able to provide a endpoint to get the information
GENERATION_MODEL: "gpt-4o-mini"
GENERATION_MODEL: "gpt-4o-mini-2024-07-18"
# service endpoints of AI service & engine service
WREN_ENGINE_ENDPOINT: "http://wren-engine-svc:8080"
@@ -53,7 +53,7 @@ data:
provider: litellm_llm
timeout: 120
models:
- model: gpt-4o-mini
- model: gpt-4o-mini-2024-07-18
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
@@ -106,58 +106,58 @@ data:
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: db_schema_retrieval
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: historical_question_retrieval
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: sql_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_correction
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: followup_sql_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_summary
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_answer
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: preprocess_sql_data
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_breakdown
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_expansion
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_explanation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_regeneration
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: semantics_description
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: relationship_recommendation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: question_recommendation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: intent_classification
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: data_assistance
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_executor
engine: wren_ui
- name: chart_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: chart_adjustment
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
---
settings:
column_indexing_batch_size: 50
docker/config.example.yaml
+20 -20
View File
@@ -2,7 +2,7 @@ type: llm
provider: litellm_llm
timeout: 120
models:
- model: gpt-4o-mini
- model: gpt-4o-mini-2024-07-18
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
@@ -11,7 +11,7 @@ models:
max_tokens: 4096
response_format:
type: json_object
- model: gpt-4o
- model: gpt-4o-2024-08-06
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
@@ -56,58 +56,58 @@ pipes:
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: db_schema_retrieval
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: historical_question_retrieval
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: sql_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_correction
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: followup_sql_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_summary
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_answer
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_breakdown
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_expansion
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_explanation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_regeneration
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: semantics_description
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: relationship_recommendation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: question_recommendation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: intent_classification
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: data_assistance
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: preprocess_sql_data
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_executor
engine: wren_ui
- name: chart_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: chart_adjustment
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
---
settings:
column_indexing_batch_size: 50
wren-ai-service/src/web/v1/services/__init__.py
+2 -2
View File
@@ -28,7 +28,7 @@ class Configuration(BaseModel):
end: str
class Timezone(BaseModel):
name: str = "Asia/Taipei"
name: str = "UTC"
utc_offset: str = "" # Deprecated, will be removed in the future
def show_current_time(self):
@@ -41,7 +41,7 @@ class Configuration(BaseModel):
return f'{current_time.strftime("%Y-%m-%d %A %H:%M:%S")}' # YYYY-MM-DD weekday_name HH:MM:SS, ex: 2024-10-23 Wednesday 12:00:00
fiscal_year: Optional[FiscalYear] = None
language: Optional[str] = "en"
language: Optional[str] = "English"
timezone: Optional[Timezone] = Timezone()
wren-ai-service/tests/pytest/services/test_relationship_recommendation.py
+1 -1
View File
@@ -27,7 +27,7 @@ async def test_recommend_success(relationship_recommendation_service, mock_pipel
assert response.id == "test_id"
assert response.status == "finished"
assert response.response == {"test": "data"}
mock_pipeline.run.assert_called_once_with(mdl={"key": "value"}, language="en")
mock_pipeline.run.assert_called_once_with(mdl={"key": "value"}, language="English")
@pytest.mark.asyncio
wren-ai-service/tools/config/config.example.yaml
+20 -20
View File
@@ -2,7 +2,7 @@ type: llm
provider: litellm_llm
timeout: 120
models:
- model: gpt-4o-mini
- model: gpt-4o-mini-2024-07-18
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
@@ -11,7 +11,7 @@ models:
max_tokens: 4096
response_format:
type: json_object
- model: gpt-4o
- model: gpt-4o-2024-08-06
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
@@ -70,56 +70,56 @@ pipes:
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: db_schema_retrieval
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: historical_question_retrieval
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: sql_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_correction
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: followup_sql_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_summary
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_answer
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_breakdown
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_expansion
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_explanation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_regeneration
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: semantics_description
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: relationship_recommendation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: question_recommendation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: chart_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: chart_adjustment
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: intent_classification
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: data_assistance
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: preprocess_sql_data
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_executor
engine: wren_ui
---
wren-ai-service/tools/config/config.full.yaml
+20 -20
View File
@@ -2,7 +2,7 @@ type: llm
provider: litellm_llm
timeout: 120
models:
- model: gpt-4o-mini
- model: gpt-4o-mini-2024-07-18
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
@@ -11,7 +11,7 @@ models:
max_tokens: 4096
response_format:
type: json_object
- model: gpt-4o
- model: gpt-4o-2024-08-06
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
@@ -89,58 +89,58 @@ pipes:
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: db_schema_retrieval
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: historical_question_retrieval
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: sql_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_correction
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: followup_sql_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_summary
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_answer
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_breakdown
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_expansion
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: sql_explanation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_regeneration
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: semantics_description
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: relationship_recommendation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
engine: wren_ui
- name: question_recommendation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: chart_generation
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: chart_adjustment
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: intent_classification
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: openai_embedder.text-embedding-3-large
document_store: qdrant
- name: data_assistance
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
- name: sql_executor
engine: wren_ui
- name: preprocess_sql_data
llm: litellm_llm.gpt-4o-mini
llm: litellm_llm.gpt-4o-mini-2024-07-18
---
settings:
wren-launcher/utils/docker.go
+6 -1
View File
@@ -30,6 +30,11 @@ const (
AI_SERVICE_CONFIG_URL string = "https://raw.githubusercontent.com/Canner/WrenAI/" + WREN_PRODUCT_VERSION + "/docker/config.example.yaml"
)
var generationModelToModelName = map[string]string{
"gpt-4o-mini": "gpt-4o-mini-2024-07-18",
"gpt-4o": "gpt-4o-2024-08-06",
}
func replaceEnvFileContent(content string, projectDir string, openaiApiKey string, openAIGenerationModel string, hostPort int, aiPort int, userUUID string, telemetryEnabled bool) string {
// replace PROJECT_DIR
reg := regexp.MustCompile(`PROJECT_DIR=(.*)`)
@@ -152,7 +157,7 @@ func PrepareConfigFileForOpenAI(projectDir string, generationModel string) error
// replace the generation model in config.yaml
config := string(content)
config = strings.ReplaceAll(config, "litellm_llm.gpt-4o-mini", "litellm_llm."+generationModel)
config = strings.ReplaceAll(config, "litellm_llm.gpt-4o-mini-2024-07-18", "litellm_llm."+generationModelToModelName[generationModel])
// write back to config.yaml
err = os.WriteFile(configPath, []byte(config), 0644)