Giters

ruoccofabrizio / azure-open-ai-embeddings-qna

A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3, GPT-3.5 or GPT-4 to extract the matching answer for the question.

Home Page:https://azure.microsoft.com/en-us/products/cognitive-services/openai-service

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

embedding model not detected

cpavel opened this issue · comments

commented

Keep running into the issue of my embedding model not being detected by the app. Error details below. I made sure I have the deployment as per name below and model as per name below. It is right next to the LLM model (GPT-4).

LLM is working!

Embedding model is not working.
Please check you have a deployment named "text-embedding-ada-002" for "text-embedding-ada-002" model in your Azure OpenAI resource https://i*********.openai.azure.com/.
Then restart your application.

Traceback (most recent call last): File "/usr/local/src/myscripts/OpenAI_Queries.py", line 31, in check_deployment llm_helper.embeddings.embed_documents(texts=["This is a test"]) File "/usr/local/lib/python3.9/site-packages/langchain/embeddings/openai.py", line 258, in embed_documents return self._get_len_safe_embeddings(texts, engine=self.document_model_name) File "/usr/local/lib/python3.9/site-packages/langchain/embeddings/openai.py", line 194, in _get_len_safe_embeddings encoding = tiktoken.model.encoding_for_model(self.document_model_name) File "/usr/local/lib/python3.9/site-packages/tiktoken/model.py", line 51, in encoding_for_model raise KeyError( KeyError: 'Could not automatically map ruocco-ada to a tokeniser. Please use tiktok.get_encoding to explicitly get the tokeniser you expect.'

commented

I am encountering the same issue!

commented

Please check you have a deployment named "text-embedding-ada-002" in your Azure OpenAI resource and that the env variable OPENAI_EMBEDDINGS_ENGINE in the WebApp is "text-embedding-ada-002" as well.

commented

I am encountering the same issue,too.
In my Azure OpenAI, I havea a deployed named "hoge-text-embedding-ada-002", model name "text-embedding-ada-002".
I set OPENAI_EMBEDDINGS_ENGINE in the WebApp is "hoge-text-embedding-ada-002"

--
Traceback (most recent call last): File "/usr/local/src/myscripts/OpenAI_Queries.py", line 31, in check_deployment llm_helper.embeddings.embed_documents(texts=["This is a test"]) File "/usr/local/lib/python3.9/site-packages/langchain/embeddings/openai.py", line 258, in embed_documents return self._get_len_safe_embeddings(texts, engine=self.document_model_name) File "/usr/local/lib/python3.9/site-packages/langchain/embeddings/openai.py", line 206, in _get_len_safe_embeddings response = embed_with_retry( File "/usr/local/lib/python3.9/site-packages/langchain/embeddings/openai.py", line 53, in embed_with_retry return _completion_with_retry(**kwargs) File "/usr/local/lib/python3.9/site-packages/tenacity/init.py", line 289, in wrapped_f return self(f, *args, **kw) File "/usr/local/lib/python3.9/site-packages/tenacity/init.py", line 379, in call do = self.iter(retry_state=retry_state) File "/usr/local/lib/python3.9/site-packages/tenacity/init.py", line 314, in iter return fut.result() File "/usr/local/lib/python3.9/concurrent/futures/_base.py", line 439, in result return self.__get_result() File "/usr/local/lib/python3.9/concurrent/futures/_base.py", line 391, in __get_result raise self._exception File "/usr/local/lib/python3.9/site-packages/tenacity/init.py", line 382, in call result = fn(*args, **kwargs) File "/usr/local/lib/python3.9/site-packages/langchain/embeddings/openai.py", line 51, in _completion_with_retry return embeddings.client.create(**kwargs) File "/usr/local/lib/python3.9/site-packages/openai/api_resources/embedding.py", line 33, in create response = super().create(*args, **kwargs) File "/usr/local/lib/python3.9/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create response, _, api_key = requestor.request( File "/usr/local/lib/python3.9/site-packages/openai/api_requestor.py", line 226, in request resp, got_stream = self._interpret_response(result, stream) File "/usr/local/lib/python3.9/site-packages/openai/api_requestor.py", line 619, in _interpret_response self._interpret_response_line( File "/usr/local/lib/python3.9/site-packages/openai/api_requestor.py", line 682, in _interpret_response_line raise self.handle_error_response( openai.error.InvalidRequestError: The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again.

commented

As shared, the deployment name must be "text-embedding-ada-002" for the library version the solution runs on.

commented

Thanks. I did wil!