Ventz Petkov
Ventz Petkov
@floleuerer Thank you! -- I'll verify. I suspect the embeddings were created using the OpenAI engine.
@floleuerer Just some interesting information to follow up on this. Moved the embeddings to Azure's OpenAI: Azure AI's embedding model limits the document "submits" to *1* currently. (this seems insane!)...
@pm78 Implementing a work-around is very simple -- it's effectively a loop where you just create a "Document" of each item and embbed it. I am just surprised by this...
@pm78 See my post here: https://github.com/hwchase17/langchain/issues/2377#issue-1653258263 Specifically # 2 -- you have to change a few things to go from OpenAI -> Azure's OpenAI.
@pm78 For your AzureOpenAI -- initialize it with with just `deployment_name`. There is no model_name for that. If you initialize these as env variables, you don't need to pass them...
@geg00 Until this is fixed, you an simply pass the "k=1" expclitily: ``` print(file_db.similarity_search_by_vector(vector1, k=1)) ```
This was fixed - closing.
I am also running into API rate limitations -- not seeing the backoff with `0.0.121`: ``` raise self.handle_error_response( openai.error.APIError: Internal error { "error": { "message": "Internal error", "type": "internal_error", "param":...
I suspect it is not enough time (clearly `embed_with_retry` is wrapped): ``` def embed_with_retry(embeddings: OpenAIEmbeddings, **kwargs: Any) -> Any: """Use tenacity to retry the completion call.""" retry_decorator = _create_retry_decorator(embeddings) @retry_decorator...