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

chore(wren-ai-service): Introduce Model Aliases for Simplified Pipeline Configuration #1371

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
+431 −412
Open

chore(wren-ai-service): Introduce Model Aliases for Simplified Pipeline Configuration #1371

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8f34661
chore: fix a api key name to reduce confusion for setting up the config
paopa Mar 6, 2025
2115a2a
chore: add default alias for llm and embedder model to reduce the com…
paopa Mar 6, 2025
4aa74d0
chore: using alias to specify llm and embedder for pipeline
paopa Mar 6, 2025
98a22c3
chore: using alias to specify llm and embedder for config example
paopa Mar 6, 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
64 changes: 33 additions & 31 deletions deployment/kustomizations/base/cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@ data:
timeout: 120
models:
- model: gpt-4o-mini-2024-07-18
alias: default
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
Expand Down Expand Up @@ -83,6 +84,7 @@ data:
provider: litellm_embedder
models:
- model: text-embedding-3-large
alias: default
api_base: https://api.openai.com/v1
api_key_name: EMBEDDER_OPENAI_API_KEY
timeout: 120
Expand All @@ -103,81 +105,81 @@ data:
type: pipeline
pipes:
- name: db_schema_indexing
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
document_store: qdrant
- name: historical_question_indexing
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
document_store: qdrant
- name: table_description_indexing
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
document_store: qdrant
- name: db_schema_retrieval
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: litellm_embedder.text-embedding-3-large
llm: litellm_llm.default
embedder: litellm_embedder.default
document_store: qdrant
- name: historical_question_retrieval
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
document_store: qdrant
- name: sql_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: sql_correction
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: followup_sql_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: sql_summary
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_answer
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_breakdown
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: sql_expansion
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: semantics_description
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: relationship_recommendation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: question_recommendation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: question_recommendation_db_schema_retrieval
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: litellm_embedder.text-embedding-3-large
llm: litellm_llm.default
embedder: litellm_embedder.default
document_store: qdrant
- name: question_recommendation_sql_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: intent_classification
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: litellm_embedder.text-embedding-3-large
llm: litellm_llm.default
embedder: litellm_embedder.default
document_store: qdrant
- name: data_assistance
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_pairs_indexing
document_store: qdrant
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
- name: sql_pairs_retrieval
document_store: qdrant
embedder: litellm_embedder.text-embedding-3-large
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: litellm_embedder.default
llm: litellm_llm.default
- name: preprocess_sql_data
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_executor
engine: wren_ui
- name: chart_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: chart_adjustment
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_question_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_generation_reasoning
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_regeneration
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui

---
Expand Down
64 changes: 33 additions & 31 deletions docker/config.example.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@ provider: litellm_llm
timeout: 120
models:
- model: gpt-4o-mini-2024-07-18
alias: default
api_base: https://api.openai.com/v1
api_key_name: LLM_OPENAI_API_KEY
kwargs:
Expand Down Expand Up @@ -34,6 +35,7 @@ type: embedder
provider: litellm_embedder
models:
- model: text-embedding-3-large
alias: default
api_base: https://api.openai.com/v1
api_key_name: EMBEDDER_OPENAI_API_KEY
timeout: 120
Expand All @@ -55,81 +57,81 @@ recreate_index: true
type: pipeline
pipes:
- name: db_schema_indexing
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
document_store: qdrant
- name: historical_question_indexing
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
document_store: qdrant
- name: table_description_indexing
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
document_store: qdrant
- name: db_schema_retrieval
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: litellm_embedder.text-embedding-3-large
llm: litellm_llm.default
embedder: litellm_embedder.default
document_store: qdrant
- name: historical_question_retrieval
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
document_store: qdrant
- name: sql_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: sql_correction
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: followup_sql_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: sql_summary
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_answer
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_breakdown
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: sql_expansion
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: semantics_description
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: relationship_recommendation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: question_recommendation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: question_recommendation_db_schema_retrieval
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: litellm_embedder.text-embedding-3-large
llm: litellm_llm.default
embedder: litellm_embedder.default
document_store: qdrant
- name: question_recommendation_sql_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui
- name: intent_classification
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: litellm_embedder.text-embedding-3-large
llm: litellm_llm.default
embedder: litellm_embedder.default
document_store: qdrant
- name: data_assistance
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_pairs_indexing
document_store: qdrant
embedder: litellm_embedder.text-embedding-3-large
embedder: litellm_embedder.default
- name: sql_pairs_retrieval
document_store: qdrant
embedder: litellm_embedder.text-embedding-3-large
llm: litellm_llm.gpt-4o-mini-2024-07-18
embedder: litellm_embedder.default
llm: litellm_llm.default
- name: preprocess_sql_data
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_executor
engine: wren_ui
- name: chart_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: chart_adjustment
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_question_generation
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_generation_reasoning
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
- name: sql_regeneration
llm: litellm_llm.gpt-4o-mini-2024-07-18
llm: litellm_llm.default
engine: wren_ui

---
Expand Down
Loading
Loading