From 894c1bba44593cb33f696fc73b788b043c35f788 Mon Sep 17 00:00:00 2001 From: Orest Xherija Date: Mon, 25 Mar 2024 17:50:07 -0500 Subject: [PATCH] openai[patch]: increase max batch size for Azure OpenAI Embeddings API (#19532) **Description:** Azure OpenAI has increased its maximum batch size from 16 to 2048 for the Embeddings API per this How-To [page](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/embeddings?tabs=console#best-practices) Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> --- libs/partners/openai/langchain_openai/embeddings/azure.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/libs/partners/openai/langchain_openai/embeddings/azure.py b/libs/partners/openai/langchain_openai/embeddings/azure.py index 684689d92ac..0daabd40f92 100644 --- a/libs/partners/openai/langchain_openai/embeddings/azure.py +++ b/libs/partners/openai/langchain_openai/embeddings/azure.py @@ -99,10 +99,10 @@ class AzureOpenAIEmbeddings(OpenAIEmbeddings): values["azure_ad_token"] = ( convert_to_secret_str(azure_ad_token) if azure_ad_token else None ) - # Azure OpenAI embedding models allow a maximum of 16 texts + # Azure OpenAI embedding models allow a maximum of 2048 texts # at a time in each batch - # See: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#embeddings - values["chunk_size"] = min(values["chunk_size"], 16) + # See: https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/embeddings?tabs=console#best-practices + values["chunk_size"] = min(values["chunk_size"], 2048) # For backwards compatibility. Before openai v1, no distinction was made # between azure_endpoint and base_url (openai_api_base). openai_api_base = values["openai_api_base"]