Dataiku can connect with down elasticsearch ver 8.14. so i wonder dataiku can connect with logstash
Can Dataiku's Customllm support multimodal, VLM, and other settings? Customllm's presets include text, embedding, and image generation, so I'm wondering if it supports other models as well. Dataiku version used: 14.1.2 Dataiku version used: 14.1.2
Hi, do you know any of the LLM providers that proposes a free API with free prompts through Dataiku LLM mesh (on limited basis of course) so using one of the LLM recipes of Dataiku the reason why i ask this : i am teaching to students data science using Dataiku , i would like to have my students practicing Gen AI through…
Hello Dataiku Team, I am creating a custom agent, and I am trying to add a python script for the SELECT parameter, but it is not working. Here is what I have in my agent.json: Here is how my tree looks like: And the compute_llm_choices.py is like this: Please, could you spot any reason why this is not working from the…
Hello, I'm trying to automate plugins upgrade through REST API. However, I'm facing some issues you might help with. First, I cannot filter plugins based on their Origin. In the web UI, Origin appears either as Builtin, Store or Local dev, for instance : I've filtered out Local dev using the "isDev" field. But I cannot…
No option found to install python libraries like pandas, numpy, sickit-learn, statsmodels, yfinance. Hoping a solution to fix Operating system used: Windows 11
Hi, In plugin I cannot save selected values for fields in recipe.json, when values comes from API. Below user description: “these values don’t persist once you leave the recipe screen and return. As an example, you can see after we add values for multiple other values, and then you can see in the upper right I saved. Then…
In plugin I cannot see default value for field in recipe.json, when value comes from API. In recipe.json I have field: { "name": "field", "label": "Field", "type": "SELECT", "getChoicesFromPython": true, "mandatory": true, "defaultValue": "Default", }, In above code default value is set to "Default", but it is not set in…
Dear dataikuler thanks for reading my question. Hi, so my problem is when i re-train my model with different dataset (like my first dataset is from 12/10 /2024 to 12/10/2025 and my second dataset is 30/11/2024 to 30/11/2025) and then i deploy the second model i check the hyperparameter of each version and i see all of them…
Since each plugin in Dataiku requires its own code environment, I wanted to ask if there is a recommended or best-practice approach to manage this more efficiently. Specifically, is it possible to use a previously built code environment and add only the custom libraries required for different plugins to avoid duplication…
Create an account to contribute great content, engage with others, and show your appreciation.
