Skip to content
Merged
Changes from all commits
Commits
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
149 changes: 149 additions & 0 deletions wren-ai-service/docs/config_examples/config.azure.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,149 @@
type: llm
provider: litellm_llm # litellm supports Azure through its provider
timeout: 120
models:
- 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_key_name: LLM_AZURE_OPENAI_API_KEY
api_version: 2024-02-15-preview

kwargs:
temperature: 0
n: 1
seed: 0
max_tokens: 4096


---
type: embedder
provider: azure_openai_embedder
models:
- model: text-embedding-ada-002 # Your Azure deployment name
# Must match model output check for your model

api_base: https://endpoint.openai.azure.com/ # Replace with your custom Azure endpoint
api_version: 2023-05-15 # Your Azure deployment name
timeout: 300

---
type: engine
provider: wren_ui
endpoint: http://wren-ui:3000

---
type: document_store
#name: qdrant
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
timeout: 120
recreate_index: true
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue

⚠️ Warning: Dangerous recreate_index setting

recreate_index: true will destroy and recreate the index on startup. This should be false in production to prevent data loss.


# For each pipe line component
# Replace llm with Azure deployed LLM model
# Replace Embeddings with Azure deployed Embedding model
---
type: pipeline
pipes:
- name: db_schema_indexing
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codebase verification

Fix List Item Indentation in Pipeline Block

The configuration in the file
wren-ai-service/docs/config_examples/config.azure.yaml
currently shows list items under the pipes: key indented by 2 spaces. YAMLlint expects these list items to start at column 0 (i.e., with no preceding space), per our project’s style guidelines.

  • Current Code:
    pipes:
      - name: db_schema_indexing
        embedder: azure_openai_embedder.text-embedding-ada-002
        document_store: qdrant  # Match document_store name
        llm: litellm_llm.azure/gpt-4
    
  • Expected Change (as per diff):
    pipes:
    - name: db_schema_indexing
      embedder: azure_openai_embedder.text-embedding-ada-002
      document_store: qdrant  # Match document_store name
      llm: litellm_llm.azure/gpt-4
    

Please adjust the indentation accordingly to meet the project standards.

🔗 Analysis chain

Check List Item Indentation in Pipeline Block
YAMLlint reports that the list item on line 49 is indented by 2 spaces (expected 0). Verify whether the current indentation meets your project standards and adjust if necessary.

-  - name: db_schema_indexing
+ - name: db_schema_indexing
🏁 Scripts executed

The following scripts were executed for the analysis:

Error: No shell scripts found


Script:

#!/bin/bash
echo "Displaying lines 45 to 55 of wren-ai-service/docs/config_examples/config.azure.yaml:"
sed -n '45,55p' wren-ai-service/docs/config_examples/config.azure.yaml

Length of output: 634

🧰 Tools
🪛 YAMLlint (1.35.1)

[warning] 49-49: wrong indentation: expected 0 but found 2

(indentation)

embedder: azure_openai_embedder.text-embedding-ada-002
document_store: qdrant # Match document_store name
llm: litellm_llm.azure/gpt-4
- name: historical_question_indexing
embedder: azure_openai_embedder.text-embedding-ada-002
document_store: qdrant
- name: table_description_indexing
embedder: azure_openai_embedder.text-embedding-ada-002
document_store: qdrant
- name: db_schema_retrieval
llm: litellm_llm.azure/gpt-4
embedder: azure_openai_embedder.text-embedding-ada-002
document_store: qdrant
- name: historical_question_retrieval
embedder: azure_openai_embedder.text-embedding-ada-002
document_store: qdrant
- name: sql_generation
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: sql_correction
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: followup_sql_generation
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: sql_summary
llm: litellm_llm.azure/gpt-4
- name: sql_answer
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: sql_breakdown
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: sql_expansion
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: sql_explanation
llm: litellm_llm.azure/gpt-4
- name: sql_regeneration
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: semantics_description
llm: litellm_llm.azure/gpt-4
- name: relationship_recommendation
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: question_recommendation
llm: litellm_llm.azure/gpt-4
- name: intent_classification
llm: litellm_llm.azure/gpt-4
embedder: azure_openai_embedder.text-embedding-ada-002
document_store: qdrant
- name: data_assistance
llm: litellm_llm.azure/gpt-4
- name: sql_pairs_preparation
document_store: qdrant
embedder: azure_openai_embedder.text-embedding-ada-002
llm: litellm_llm.azure/gpt-4
- name: sql_pairs_deletion
document_store: qdrant
embedder: azure_openai_embedder.text-embedding-ada-002
- name: sql_pairs_retrieval
document_store: qdrant
embedder: azure_openai_embedder.text-embedding-ada-002
llm: litellm_llm.azure/gpt-4
- name: preprocess_sql_data
llm: litellm_llm.azure/gpt-4
- name: sql_executor
engine: wren_ui
- name: chart_generation
llm: litellm_llm.azure/gpt-4
- name: chart_adjustment
llm: litellm_llm.azure/gpt-4
- name: sql_pairs_indexing
document_store: qdrant
embedder: azure_openai_embedder.text-embedding-ada-002
- name: sql_generation_reasoning
llm: litellm_llm.azure/gpt-4
- name: question_recommendation_db_schema_retrieval
llm: litellm_llm.azure/gpt-4
embedder: azure_openai_embedder.text-embedding-ada-002
document_store: qdrant
- name: question_recommendation_sql_generation
llm: litellm_llm.azure/gpt-4
engine: wren_ui
- name: sql_question_generation
llm: litellm_llm.azure/gpt-4

---
settings:
column_indexing_batch_size: 50
table_retrieval_size: 10
table_column_retrieval_size: 100
allow_using_db_schemas_without_pruning: false
query_cache_maxsize: 1000
query_cache_ttl: 3600
langfuse_host: https://cloud.langfuse.com
langfuse_enable: true
logging_level: DEBUG
development: false