chore: using alias to specify llm and embedder for config example

Canner · Mar 6, 2025 · 98a22c3 · 98a22c3
1 parent 4aa74d0
commit 98a22c3
Show file tree

Hide file tree

Showing 5 changed files with 267 additions and 258 deletions.
diff --git a/wren-ai-service/docs/config_examples/config.azure.yaml b/wren-ai-service/docs/config_examples/config.azure.yaml
@@ -7,27 +7,28 @@
 type: llm
 provider: litellm_llm
 models:
-# put AZURE_API_KEY=<your_api_key> in ~/.wrenai/.env
-- model: azure/gpt-4     # Your Azure deployment name, put 'azure/' before deployment name
-  api_base: https://endpoint.openai.azure.com  # Replace with your custom Azure endpoint
-  api_version: 2024-02-15-preview
-  timeout: 120
-  kwargs:
-    temperature: 0
-    n: 1
-    seed: 0
-    max_tokens: 4096
-
+  # put AZURE_API_KEY=<your_api_key> in ~/.wrenai/.env
+  - model: azure/gpt-4 # Your Azure deployment name, put 'azure/' before deployment name
+    alias: default
+    api_base: https://endpoint.openai.azure.com # Replace with your custom Azure endpoint
+    api_version: 2024-02-15-preview
+    timeout: 120
+    kwargs:
+      temperature: 0
+      n: 1
+      seed: 0
+      max_tokens: 4096
 
 ---
 type: embedder
-provider: litellm_embedder  
+provider: litellm_embedder
 models:
-# put AZURE_API_KEY=<your_api_key> in ~/.wrenai/.env
-- model: azure/text-embedding-ada-002  # Your Azure deployment name, put 'azure/' before deployment name
-  api_base: https://endpoint.openai.azure.com  # Replace with your custom Azure endpoint
-  api_version: 2023-05-15
-  timeout: 300
+  # put AZURE_API_KEY=<your_api_key> in ~/.wrenai/.env
+  - model: azure/text-embedding-ada-002 # Your Azure deployment name, put 'azure/' before deployment name
+    alias: default
+    api_base: https://endpoint.openai.azure.com # Replace with your custom Azure endpoint
+    api_version: 2023-05-15
+    timeout: 300
 
 ---
 type: engine
@@ -37,8 +38,8 @@ endpoint: http://wren-ui:3000
 ---
 type: document_store
 provider: qdrant
-location: http://qdrant:6333  # Donot set the QDRANT_API_KEY if you are using the qdrant from docker
-embedding_model_dim: 1536  # Must match model dimension from embedder
+location: http://qdrant:6333 # Donot set the QDRANT_API_KEY if you are using the qdrant from docker
+embedding_model_dim: 1536 # Must match model dimension from embedder
 timeout: 120
 recreate_index: true
 
@@ -49,87 +50,87 @@ recreate_index: true
 type: pipeline
 pipes:
   - name: db_schema_indexing
-    embedder: litellm_embedder.azure/text-embedding-ada-002
-    document_store: qdrant  # Match document_store name
-    llm: litellm_llm.azure/gpt-4
+    embedder: litellm_embedder.default
+    document_store: qdrant # Match document_store name
+    llm: litellm_llm.default
   - name: historical_question_indexing
-    embedder: litellm_embedder.azure/text-embedding-ada-002
+    embedder: litellm_embedder.default
     document_store: qdrant
   - name: table_description_indexing
-    embedder: litellm_embedder.azure/text-embedding-ada-002
+    embedder: litellm_embedder.default
     document_store: qdrant
   - name: db_schema_retrieval
-    llm: litellm_llm.azure/gpt-4
-    embedder: litellm_embedder.azure/text-embedding-ada-002
+    llm: litellm_llm.default
+    embedder: litellm_embedder.default
     document_store: qdrant
   - name: historical_question_retrieval
-    embedder: litellm_embedder.azure/text-embedding-ada-002
+    embedder: litellm_embedder.default
     document_store: qdrant
   - name: sql_generation
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_correction
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
   - name: followup_sql_generation
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_summary
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: sql_answer
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_breakdown
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_expansion
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
   - name: semantics_description
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: relationship_recommendation
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
   - name: question_recommendation
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: intent_classification
-    llm: litellm_llm.azure/gpt-4
-    embedder: litellm_embedder.azure/text-embedding-ada-002
+    llm: litellm_llm.default
+    embedder: litellm_embedder.default
     document_store: qdrant
   - name: data_assistance
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: sql_pairs_preparation
     document_store: qdrant
-    embedder: litellm_embedder.azure/text-embedding-ada-002
-    llm: litellm_llm.azure/gpt-4
+    embedder: litellm_embedder.default
+    llm: litellm_llm.default
   - name: sql_pairs_retrieval
     document_store: qdrant
-    embedder: litellm_embedder.azure/text-embedding-ada-002
-    llm: litellm_llm.azure/gpt-4
+    embedder: litellm_embedder.default
+    llm: litellm_llm.default
   - name: preprocess_sql_data
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: sql_executor
     engine: wren_ui
   - name: chart_generation
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: chart_adjustment
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: sql_pairs_indexing
     document_store: qdrant
-    embedder: litellm_embedder.azure/text-embedding-ada-002
+    embedder: litellm_embedder.default
   - name: sql_generation_reasoning
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: question_recommendation_db_schema_retrieval
-    llm: litellm_llm.azure/gpt-4
-    embedder: litellm_embedder.azure/text-embedding-ada-002
+    llm: litellm_llm.default
+    embedder: litellm_embedder.default
     document_store: qdrant
   - name: question_recommendation_sql_generation
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_question_generation
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
   - name: sql_regeneration
-    llm: litellm_llm.azure/gpt-4
+    llm: litellm_llm.default
     engine: wren_ui
 
 ---

diff --git a/wren-ai-service/docs/config_examples/config.deepseek.yaml b/wren-ai-service/docs/config_examples/config.deepseek.yaml
@@ -7,41 +7,43 @@
 type: llm
 provider: litellm_llm
 models:
-# put DEEPSEEK_API_KEY=<your_api_key> in ~/.wrenai/.env
-- api_base: https://api.deepseek.com/v1
-  model: deepseek/deepseek-reasoner
-  timeout: 120
-  kwargs:
-    n: 1
-    temperature: 0
-    response_format:
-      type: text
-- api_base: https://api.deepseek.com/v1
-  model: deepseek/deepseek-chat
-  timeout: 120
-  kwargs:
-    n: 1
-    temperature: 0
-    response_format:
-      type: text
-- api_base: https://api.deepseek.com/v1
-  model: deepseek/deepseek-coder
-  timeout: 120
-  kwargs:
-    n: 1
-    temperature: 0
-    response_format:
-      type: json_object
+  # put DEEPSEEK_API_KEY=<your_api_key> in ~/.wrenai/.env
+  - api_base: https://api.deepseek.com/v1
+    model: deepseek/deepseek-reasoner
+    alias: default
+    timeout: 120
+    kwargs:
+      n: 1
+      temperature: 0
+      response_format:
+        type: text
+  - api_base: https://api.deepseek.com/v1
+    model: deepseek/deepseek-chat
+    timeout: 120
+    kwargs:
+      n: 1
+      temperature: 0
+      response_format:
+        type: text
+  - api_base: https://api.deepseek.com/v1
+    model: deepseek/deepseek-coder
+    timeout: 120
+    kwargs:
+      n: 1
+      temperature: 0
+      response_format:
+        type: json_object
 
 ---
 type: embedder
 provider: litellm_embedder
 models:
-# define OPENAI_API_KEY=<api_key> in ~/.wrenai/.env if you are using openai embedding model
-# please refer to LiteLLM documentation for more details: https://docs.litellm.ai/docs/providers
-- model: text-embedding-3-large  # put your embedding model name here, if it is not openai embedding model, should be <provider>/<model_name>
-  api_base: https://api.openai.com/v1  # change this according to your embedding model
-  timeout: 120
+  # define OPENAI_API_KEY=<api_key> in ~/.wrenai/.env if you are using openai embedding model
+  # please refer to LiteLLM documentation for more details: https://docs.litellm.ai/docs/providers
+  - model: text-embedding-3-large # put your embedding model name here, if it is not openai embedding model, should be <provider>/<model_name>
+    alias: default
+    api_base: https://api.openai.com/v1 # change this according to your embedding model
+    timeout: 120
 
 ---
 type: engine
@@ -52,7 +54,7 @@ endpoint: http://wren-ui:3000
 type: document_store
 provider: qdrant
 location: http://qdrant:6333
-embedding_model_dim: 3072  # put your embedding model dimension here
+embedding_model_dim: 3072 # put your embedding model dimension here
 timeout: 120
 recreate_index: true
 
@@ -63,90 +65,90 @@ 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.deepseek/deepseek-coder
-    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.deepseek/deepseek-coder
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_correction
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
     engine: wren_ui
   - name: followup_sql_generation
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_summary
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
   - name: sql_answer
-    llm: litellm_llm.deepseek/deepseek-chat
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_breakdown
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
     engine: wren_ui
   - name: sql_expansion
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
     engine: wren_ui
   - name: semantics_description
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
   - name: relationship_recommendation
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
     engine: wren_ui
   - name: question_recommendation
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
   - name: question_recommendation_db_schema_retrieval
-    llm: litellm_llm.deepseek/deepseek-coder
-    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.deepseek/deepseek-coder
+    llm: litellm_llm.default
     engine: wren_ui
   - name: chart_generation
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
   - name: chart_adjustment
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
   - name: intent_classification
-    llm: litellm_llm.deepseek/deepseek-coder
-    embedder: litellm_embedder.text-embedding-3-large
+    llm: litellm_llm.default
+    embedder: litellm_embedder.default
     document_store: qdrant
   - name: data_assistance
-    llm: litellm_llm.deepseek/deepseek-chat
+    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.deepseek/deepseek-coder
+    embedder: litellm_embedder.default
+    llm: litellm_llm.default
   - name: preprocess_sql_data
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
   - name: sql_executor
     engine: wren_ui
   - name: sql_question_generation
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
   - name: sql_generation_reasoning
-    llm: litellm_llm.deepseek/deepseek-reasoner
+    llm: litellm_llm.default
   - name: sql_regeneration
-    llm: litellm_llm.deepseek/deepseek-coder
+    llm: litellm_llm.default
     engine: wren_ui
 
 ---
 settings:
   column_indexing_batch_size: 50
   table_retrieval_size: 10
   table_column_retrieval_size: 100
-  allow_using_db_schemas_without_pruning: false  # if you want to use db schemas without pruning, set this to true. It will be faster
+  allow_using_db_schemas_without_pruning: false # if you want to use db schemas without pruning, set this to true. It will be faster
   query_cache_maxsize: 1000
   query_cache_ttl: 3600
   langfuse_host: https://cloud.langfuse.com