Dear Dataiku Experts, I’m working on a Dataiku project where I want to enable natural language interaction with a production SQL database — essentially, a chatbot I call the “Production Analyst.” The idea is that a user can type queries in natural language, and the chatbot will interpret them to perform production…
Hello everyone, I am working on Dataiku, primarily using their API. I have trained my model and would like to retrieve the dataset that was used for testing via the API methods. Despite trying several methods, including get_train_info(), I am unable to obtain the test dataset. I don't want to export it; I just want to…
Hello, We've been experiencing issues on different recipes/notebooks, few sql recipes show Unknown error - Code 403 and a webapp does the same as well, even though scenarios run perfectly fine whenever we edit a recipe and try to validate we get the same error and it happens for some recipes not all of them. Operating…
I have never really exposed Dataiku web apps in “Public” mode, i.e., open from the instance. Dataiku seems to make it clear that this is not very secure and that the service could be compromised if someone finds its URL. However, I need to expose a web app quickly on my website, so I'm wondering what the risks are of…
I feel like I'm going crazy trying to find something that seems like it should be a simple formatting option. I'm making a dashboard that has a lot of graphs like the one pictured, with lots of stacked bars. For some reason, these seem to be as skinny as possible and I can not for the life of me figure out how to change…
I get an error when trying to get dataset https://www2.census.gov/geo/tiger/TIGER2019/COUNTY/tl_2019_us_county.zip or ftp://ftp2.census.gov/geo/tiger/TIGER2019/COUNTY/tl_2019_us_county.zip from New HTTP dataset or or New FTP dataset respectively An error occurred class com.dataiku.dip.datasets.fs.HTTPDatasetTestHandler…
Is there a way to download updated dataset if queried via “Explore” option and having filter applied on through “Sample Settings”., usually it downloads entire dataset as is and not the one generated after applying filter.
Hi, I'm trying to create a prompt to ask questions to a LLM and get an answer based on 5,000 reviews for a product. I know there are ways to classify or perform sentiment analysis, but what I want to do is to ask an LLM a question about the whole bunch of reviews. I tried using RAG, but it is my understanding the this…
I want to create an R Shiny application to query data. The data exists in dataiku where a pipeline runs nightly. I would like to add a button to my app that would rebuild my data on an ad-hoc basis. Is this possible? In python it looks like this works. Is there an R equivalent? import dataiku project =…
Create an account to contribute great content, engage with others, and show your appreciation.
