The input is not a valid Base64 string of encoded floats. #794
Replies: 7 comments
-
I used the previous version of the Kernel Memory service, and everything worked smoothly:
|
Beta Was this translation helpful? Give feedback.
-
are you using a custom endpoint? |
Beta Was this translation helpful? Give feedback.
-
I have the same exception using a custom endpoint to LM Studio |
Beta Was this translation helpful? Give feedback.
-
i have the same bug when using a custom endpoint |
Beta Was this translation helpful? Give feedback.
-
As you can see from the stack trace, the error is thrown by OpenAI .NET library, which is an internal dependency of Semantic Kernel.
LM Studio and similar projects attempt to mimic OpenAI service output, however, sometimes the output has minor differences that can lead to exceptions, for example if a type doesn't match, if a special token is missing, etc. The previous version of KM used an older version of Semantic Kernel, which used different code/libraries/versions. I would report the issue to LM Studio asking to check for differences and compatibility with OpenAI .NET library. |
Beta Was this translation helpful? Give feedback.
-
Openai also supports whether float or base64 can have parameters that can be configured. There are many private model interfaces that currently do not support base64 |
Beta Was this translation helpful? Give feedback.
-
Context / Scenario
I am trying to use the KernelMemory embedding scenario with the basic configuration of the
kernelmemory/service
Docker container.Here is the configuration summery in
appsettings.Production.json
:What happened?
When I attempt to embed something or use the ask API, I encounter the following error in the container console:
System.FormatException: The input is not a valid Base64 string of encoded floats. at OpenAI.Embeddings.Embedding.<ConvertToVectorOfFloats>
Importance
I cannot use Kernel Memory
Platform, Language, Versions
Docker Image:
kernelmemory/service:sha-d6af98f
Relevant log output
Beta Was this translation helpful? Give feedback.
All reactions