schthms
schthms
any news on this one?
@sukhoi47 Have you been able to find a way?
It works if you specify both embedding and completion model: ``` embed_model = OpenAIEmbedding(deployment_name="text-search-ada-doc-001") llm_predictor = LLMPredictor(llm=AzureOpenAI(deployment_name="davinci-003", openai_api_key=openai.api_key)) index = GPTSimpleVectorIndex(documents, embed_model=embed_model, llm_predictor=llm_predictor) ```