eulersearch / embedding_studio Goto Github PK

Hi!
I'm trying to adopt the framework, but can't see any text domain related functionality.

Can you add text support too? I'm using mostly multilingual-e5-large and all-MiniLM-L12-v2.

Guys, I’ve tried the code and look into it. I can’t see any inference related stuff. Looks interesting, but unless I can easily redeploy it in my infrastructure, it’s hard to be adopted.
Are you going to implement something like this? Or can you suggest any workaround?

I've read your readme, and you mentioned about some query parsing tools, but can't find anything in your repo. Where can I read about it more? What is the release data of the feature? Thanks.

Hey, trying to run the fine tuning , found out that image downloading is quite slow. Checked it out, seems that it’s even not multithreaded or async. Are you going to speed it up somehow?

Hey!
I’m looking into code, what was behind the decision to use MongoDB as a Clickstream storage backend?
We are using ClickHouse as the part of technical stack, it’s more convenient for this purpose. Will you add ClickHouse support?
Best regards.

I'm trying to use my dataset for model training, but I'm encountering the following error:

ClientError                               Traceback (most recent call last)
/tmp/ipykernel_199154/1286885123.py in <module>
----> 1 response = s3_client.get_object(Bucket='embedding-studio-experiments', Key='remote-lanscapes/clickstream/f6816566-cac3-46ac-b5e4-0d5b76757c93/sessions.json')
~/anaconda3/lib/python3.9/site-packages/botocore/client.py in _api_call(self, *args, **kwargs)
    528                 )
    529             # The "self" in this scope is referring to the BaseClient.
--> 530             return self._make_api_call(operation_name, kwargs)
    531 
    532         _api_call.__name__ = str(py_operation_name)
~/anaconda3/lib/python3.9/site-packages/botocore/client.py in _make_api_call(self, operation_name, api_params)
    958             error_code = parsed_response.get("Error", {}).get("Code")
    959             error_class = self.exceptions.from_code(error_code)
--> 960             raise error_class(parsed_response, operation_name)
    961         else:
    962             return parsed_response
ClientError: An error occurred (InvalidAccessKeyId) when calling the GetObject operation: The AWS Access Key Id you provided does not exist in our records.

I attempted to set my AWS Access Key ID in the .env file under the variables MINIO_ACCESS_KEY and MINIO_SECRET_KEY. However, as I understand it, these variables are used for artifact storage, not for my datasets. Can you advise on how I can resolve this error?