-
LLM Batch requests
I am experiencing rate limit errors for my LLM requests. Is there a simple method to batch my requests? My thanks in advance. Tom Operating system used: Mac OS
-
"Project key is already used", but I cannot find it
Hello, I am trying to duplicate a project and have set a new project key "NEW_KEY" for the copy. When I try this I get the following error: Project key NEW_KEY is already used. Please check that you have not already imported this project. Since the message states the project already exists I tried accessing it (via the URL…
-
Expanding reach
Hello, I am an experienced AI/ML consultant with significant hands-on experience using Dataiku with three certifications. I am interested to learn about effective strategies on how to reach clients in search of Dataiku consultants. Best Regards Operating system used: mac os
-
ModuleNotFoundError: No module named 'dataiku.langchain'
Hi, I was recently trying to install the dataiku api locally for some testing purposes but was met with some errors. Installation seemed to be working fine but the moment I tried to run this code:`from dataiku.langchain.llm import DKUChatModel` , it seemed to crash and be unable to find the dataiku.langchain module. What…
-
pythonレシピで生成し、マネージドフォルダにpickleしたモデルのファインチューニング
タイトル通り、pythonレシピで生成し、マネージドフォルダにpickleしたモデルが有れば、そのモデルを読み込んで追加のエポックを回したり、ファインチューニングするような処理を検討しています。 しかし、同一のマネージドフォルダをpythonレシピのインプットとアウトプット両方にするとエラーが発生してしまいます。 マネージドフォルダからさらに中のモデルを別のマネージドフォルダに移して、それを読み込むなどの実装はデータの冗長性の観点から避けたいと考えています。…
-
Why is dataiku not a familiar platform amongst the developers?
-
Recommended usage of Schema Description
Hello, I recently found out you can make a schema description to note some details about specific columns. This seems very useful but I find it hard to create legible descriptions as they only show what fits in the column width: This makes it hard to read unless you go into the settings to see what exactly is written there…
-
Label task
Hello, I have created a label task for the evaluation of a query. The input is a sample of rows of a bigger dataset. With the label task you can then assigned one of five categories. Using the label task has lead to changes of the query that feeds the label task. Now I want to reset the task / remove the data associated…
-
Dataset overwritten instead of error
When building datasets I have seen that, on changes to the schema given by the recipe, the dataset is fully overwritten, data and all. This means that, when a recipe suddenly does not return the correct schema, all previous data is lost… Previously we did get an error message if this was the case and we would not lose any…
-
Checks with custom error/warning messages
Is it possible to create a custom error message for a check? I've created some checks for important datasets but find the default error messaging of "Checks on the output produced 1 error" a bit lacking as this does not give any information on what's wrong to users who are not as versed in Dataiku or programming in…