Unable to deploy model with embedding model text-embedding-ada-002

[raina0990]

Describe the bug

After successful start of the Wren AI, when I try deoloy model for Azure Open AI setup. I get below error: openai.BadRequestError: Error code: 400 - {'error': {'message': 'This model does not support specifying dimensions.', 'type': 'invalid_request_error', 'param': None, 'code': None}}

Oh no an error! Need help with Hamilton? Join our slack and ask for help! https://join.slack.com/t/hamilton-opensource/shared_invite/zt-1bjs72asx-wcUTgH7q7QX1igiQ5bbdcg

2024-08-02 21:53:15,557 - wren-ai-service - ERROR - ask pipeline - Failed to prepare semantics: Error code: 400 - {'error': {'message': 'This model does not support specifying dimensions.', 'type': 'invalid_request_error', 'param': None, 'code': None}} (indexing.py:60)

To Reproduce Steps to reproduce the behavior:

1. set up .env.ai for azure_open_ai
2. Set embedding model as follows: EMBEDDING_MODEL=text-embedding-ada-002 EMBEDDING_MODEL_DIMENSION=1536

Expected behavior Model should be deployed. We should get 'synced' message in the UI

Wren AI Information

• Version: 0.7.3
• LLM_PROVIDER= azure_openai_llm
• GENERATION_MODEL= gpt-4o

[cyyeh]

@raina0990 this bug is already fixed with this PR(https://github.com/Canner/WrenAI/pull/579), and will be released in the next official release. stay tuned :)