I am getting this error while creating embeddings

[rakshahulle]

Git path - semantic-kernel/python/samples/getting_started/06-memory-and-embeddings.ipynb
for this "await populate_memory(memory)"
this error "ServiceResponseException: ("<class 'semantic_kernel.connectors.ai.open_ai.services.azure_text_embedding.AzureTextEmbedding'> service failed to generate embeddings", BadRequestError('Unsupported data type'))"

[moonbox3]

Hello @rakshahulle, could you please provide us some more context about how you're arriving at this error? What embedding model do you have configured? Have you changed any portion of the code or you receive this error from running the code as-is? Which exact cell are you seeing this error? await populate_memory(memory) is called three times in that notebook. Thanks.

[rakshahulle]

I have change code for OpenAI API to AzureOpenAI API service and gave its configuration. This is the below code with error logs

On Mon, Nov 4, 2024 at 7:57 PM Evan Mattson ***@***.***> wrote: Hello @rakshahulle <https://github.com/rakshahulle>, could you please provide us some more context about how you're arriving at this error? What embedding model do you have configured? Have you changed any portion of the code or you receive this error from running the code as-is? Which exact cell are you seeing this error? await populate_memory(memory) is called three times in that notebook. Thanks. — Reply to this email directly, view it on GitHub <#9518 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AXCZPRNDV6MXF2TYKCHTHKLZ65Y3PAVCNFSM6AAAAABREGWTE6VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMJUGMZTKMI> . You are receiving this because you were mentioned.Message ID: ***@***.*** com>

Populating memory... Traceback (most recent call last): File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/semantic_kernel/connectors/ai/open_ai/services/open_ai_handler.py", line 72, in _send_embedding_request response = await self.client.embeddings.create(**settings.prepare_settings_dict()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/openai/resources/embeddings.py", line 236, in create return await self._post( ^^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1838, in post return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1532, in request return await self._request( ^^^^^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1633, in _request raise self._make_status_error_from_response(err.response) from None openai.BadRequestError: Unsupported data type The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/home/raksha/project_work/toyota/semantic_kernel/semantic-kernel/python/samples/concepts/memory/memory.py", line 115, in <module> asyncio.run(main()) File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/asyncio/runners.py", line 194, in run return runner.run(main) ^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/asyncio/runners.py", line 118, in run return self._loop.run_until_complete(task) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete return future.result() ^^^^^^^^^^^^^^^ File "/home/raksha/project_work/toyota/semantic_kernel/semantic-kernel/python/samples/concepts/memory/memory.py", line 95, in main await populate_memory(memory) File "/home/raksha/project_work/toyota/semantic_kernel/semantic-kernel/python/samples/concepts/memory/memory.py", line 17, in populate_memory await memory.save_information(collection=collection_id, id="info1", text="Your budget for 2024 is $100,000") File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/semantic_kernel/memory/semantic_text_memory.py", line 56, in save_information embedding = (await self._embeddings_generator.generate_embeddings([text], **embeddings_kwargs))[0] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/semantic_kernel/connectors/ai/open_ai/services/open_ai_text_embedding_base.py", line 36, in generate_embeddings raw_embeddings = await self.generate_raw_embeddings(texts, settings, batch_size, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/semantic_kernel/connectors/ai/open_ai/services/open_ai_text_embedding_base.py", line 70, in generate_raw_embeddings raw_embedding = await self._send_embedding_request(settings=settings) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/raksha/anaconda3/envs/sk-3.12/lib/python3.12/site-packages/semantic_kernel/connectors/ai/open_ai/services/open_ai_handler.py", line 76, in _send_embedding_request raise ServiceResponseException( semantic_kernel.exceptions.service_exceptions.ServiceResponseException: ("<class 'semantic_kernel.connectors.ai.open_ai.services.azure_text_embedding.AzureTextEmbedding'> service failed to generate embeddings", BadRequestError('Unsupported data type'))

[moonbox3]

Thanks for your response. Which Azure OpenAI embedding model are you using?

[moonbox3]

Also, can you please have a look at the following closed issue that seems to be related? I think it may be related to an incorrect endpoint configuration:

#5697

[moonbox3]

Note, some of the code in that screenshot on the issue is old, but the main part is the deployment_name as part of AzureTextEmbedding.

[rakshahulle]

text-embedding-ada-002

…

On Mon, Nov 4, 2024 at 8:23 PM Evan Mattson ***@***.***> wrote: Thanks for your response. Which Azure OpenAI embedding model are you using? — Reply to this email directly, view it on GitHub <#9518 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AXCZPRPMHZNW4K6UMYHO2Z3Z6535ZAVCNFSM6AAAAABREGWTE6VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMJUGM3DQMY> . You are receiving this because you were mentioned.Message ID: ***@***.*** com>

[rakshahulle]

These are the configurations I am using: AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="gpt-4o-mini" AZURE_OPENAI_ENDPOINT=" https://openaisk123.openai.azure.com/openai/deployments/gpt-4o-mini/chat/completions?api-version=2024-08-01-preview " AZURE_OPENAI_API_KEY="" AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME="text-embedding-ada-002"

…

On Mon, Nov 4, 2024 at 8:28 PM Evan Mattson ***@***.***> wrote: Note, some of the code in that screenshot on the issue is old, but the main part is the deployment_name as part of AzureTextEmbedding. — Reply to this email directly, view it on GitHub <#9518 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AXCZPRNYE6KE2BJXG4TFXBLZ654O3AVCNFSM6AAAAABREGWTE6VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMJUGM3TKNI> . You are receiving this because you were mentioned.Message ID: ***@***.*** com>

[rakshahulle]

Thank you so much for the reference. Now the code is working.

…

On Mon, Nov 4, 2024 at 8:26 PM Evan Mattson ***@***.***> wrote: Also, can you please have a look at the following closed issue that seems to be related? I think it may be related to an incorrect endpoint configuration: #5697 <#5697> — Reply to this email directly, view it on GitHub <#9518 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AXCZPRIAWRNYNICSAOX43DDZ654IZAVCNFSM6AAAAABREGWTE6VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMJUGM3TEOI> . You are receiving this because you were mentioned.Message ID: ***@***.*** com>

[rakshahulle]

The response was very quick and helpful, which speed up my development process

[moonbox3]

Glad to hear!