- 30413 Views
- 18 replies
- 33 kudos
Databricks Announces the Industry’s First Generative AI Engineer Learning Pathway and Certification
Today, we are announcing the industry's first Generative AI Engineer learning pathway and certification to help ensure that data and AI practitioners have the resources to be successful with generative AI. At Databricks, we recognize that generative ...
- 30413 Views
- 18 replies
- 33 kudos
- 4033 Views
- 3 replies
- 1 kudos
I am struggling on complicated RAG code for Mosaic evaluation deployment
I want to know how I can apply some complicated RAG designs so I can directly deploy on the Mosaic AI evaluation UI. There are two cases:1. two or more index retrieval as independent tools (parallel retrievals)2.two index retrieval processes that dep...
- 4033 Views
- 3 replies
- 1 kudos
- 1 kudos
Hi @wind2025, for Mosaic RAG setups:Parallel retrievals: independent retrievers feeding one or multiple LLMs.Linear retrievals: chain retrievers so output of one filters the next.Independent RAG chains: define separate chains and register both as too...
- 1 kudos
- 552 Views
- 1 replies
- 1 kudos
Function Calling and Tool Integration: Empowering Agents to Take Action
Function calling is what truly unlocks an agent’s potential on Databricks. It’s the bridge between conversation and action — turning an LLM from a chatty assistant into an autonomous system that actually gets stuff done. Imagine this: an agent that c...
- 552 Views
- 1 replies
- 1 kudos
- 1 kudos
To strike the right balance, I’d focus on modular, well-documented tools with strict access control. Each callable function should have:Clear purpose & description – so the LLM knows when to invoke it.Input/output validation – prevents unintended act...
- 1 kudos
- 6208 Views
- 3 replies
- 0 kudos
How can we serve Genie as an endpoint model like RAG?
Is there any way to serve genie bot as a endpoint model like we serve RAG models. So we can access the genie bot outside the genie space?
- 6208 Views
- 3 replies
- 0 kudos
- 0 kudos
Hi @hammad, you can use AgentBricks - Multi Agent Supervisor to achieve the same result. You also use Genie as a Databricks-managed MCP tool. Depending on your situation, you can choose the option that suits you best.
- 0 kudos
- 3862 Views
- 1 replies
- 1 kudos
Resolved! Exception: The demo llm-rag-chatbot doesn't exist.
Hello,when I try to bring the demo environment (LLM Chatbot With Retrieval Augmented Generation (RAG) and DBRX) into my Databricks workspace, I get the following error: Exception: The demo llm-rag-chatbot doesn't exist.I execute the following code: %...
- 3862 Views
- 1 replies
- 1 kudos
- 1 kudos
Hi @xiinex - You are right. This demo is now deprecated. Please use the ai-agent demo.
- 1 kudos
- 664 Views
- 5 replies
- 1 kudos
Resolved! Problems with unstructured_data_pipeline
Hi everyone,I'm currently working with the unstructured data pipeline in Databricks, using the official notebook provided by Databricks without any modifications. Strangely, despite being an out-of-the-box resource, the notebook fails during executio...
- 664 Views
- 5 replies
- 1 kudos
- 1 kudos
Hi @Mariano-Vertiz - Which access mode are you using for your cluster - dedicated or standard? I think it is failing as a standard cluster does not allow the low-level operation it is trying to perform in cell 42. Is that where it's failing? I tried ...
- 1 kudos
- 4488 Views
- 1 replies
- 1 kudos
Resolved! Error when logging artifact OSError: [Errno 5] Input/output error: '/dbfs/Volumes'
Hi, I'm building an streamlit application on databricks apps, where user can upload some data , and I run an LLM model and return results. There, I want to log an artifact to a volume. I'm following this documentation https://docs.databricks.com/aws...
- 4488 Views
- 1 replies
- 1 kudos
- 1 kudos
The error text OSError: [Errno 5] Input/output error: '/dbfs/Volumes' occurs because Databricks Apps (including Streamlit apps running on Databricks) currently do not have direct write access to /dbfs/Volumes for artifact logging via M...
- 1 kudos
- 1343 Views
- 9 replies
- 2 kudos
getting 500 on embedding model invocation call
I'm getting the following error message "{"error_code": "INTERNAL_ERROR", "message": "The server received an invalid response from an upstream server."}" when making a call to bge-large-en embedding model.
- 1343 Views
- 9 replies
- 2 kudos
- 2 kudos
Hi @tefrati - Can you please go to the model serving endpoint and click on the use drop down (as shown in the picture below) and try the simple python or sql and see if that works for you. from openai import OpenAI import os # How to get your Databr...
- 2 kudos
- 368 Views
- 2 replies
- 0 kudos
Multilingual embedding foundation model request
Are there any plans to offer a foundation model with multilingual support? Llama embed nemotron 8b or qwen3-embedding 8b would help out a lot for users that do not only process data in the English language.
- 368 Views
- 2 replies
- 0 kudos
- 0 kudos
Sorry I wasn't clear enough in my question: I mean embedding models specifically.
- 0 kudos
- 1205 Views
- 1 replies
- 1 kudos
Permission Denied for Genie Auto-Generated Service Principal on SQL Endpoint in Playground
Hi community,Use Genie in multi-agent systems | Databricks DocumentationI’ve developed a multi-agent Genie in Databricks and integrated it with vector indexes. The setup works fine during model logging and prediction. The system successfully register...
- 1205 Views
- 1 replies
- 1 kudos
- 1 kudos
Hi @Karthik_Karanm - Can you ensure to add the Genie in the resources as mentioned in the TODO of the cell. To enable automatic authentication, specify the dependent Databricks resources when calling mlflow.pyfunc.log_model(). TODO: If your Unity Ca...
- 1 kudos
- 694 Views
- 2 replies
- 0 kudos
Utilizing Genie AI with Workflows
As subject says, is this possible via creating a python script that calls agent.predict etc...? Similar to thisagent.predict( { "messages": [{"role": "user", "content": "...the question we want to ask Genie..."}], } )I want to implement Genie AI, and...
- 694 Views
- 2 replies
- 0 kudos
- 0 kudos
Hi @stexil, you can achieve this by using Genie as an agent in a multi-agent system. If you prefer to use code then follow this - https://docs.databricks.com/aws/en/generative-ai/agent-framework/multi-agent-genie#gsc.tab=0. If you want to use point a...
- 0 kudos
- 1158 Views
- 2 replies
- 2 kudos
Resolved! Model serving endpoint API error - Mosaic AI Agents API
Hi, I have built a Chatbot App using Streamlit (through Databricks Apps UI). The chatbot backend is a custom RAG model which is built by following this example notebook: 02-Deploy-RAG-Chatbot-Model.The needed databricks packages are installed: databr...
- 1158 Views
- 2 replies
- 2 kudos
- 2 kudos
Hi @JingXie, This is a classic authentication token issue, but it's happening in a different place than you might think. The Invalid Token error is not coming from your Streamlit App's call to your chatbot_poc endpoint. It's coming from inside your c...
- 2 kudos
- 891 Views
- 1 replies
- 0 kudos
Resolved! DatabricksVectorSearch seems to crash when served
Hey y'all !So I'm experimenting with the Databricks' DatanircksVectorSearch class in Python to serve as a tool that can be used by an agent. When I run it on a notebook, I get the following error:"[NOTICE] Using a notebook authentication token. Recom...
- 891 Views
- 1 replies
- 0 kudos
- 0 kudos
Hello @brahaman , The notice you're seeing is exactly what's causing the authentication issue when your agent is deployed. When running in a notebook, the `DatabricksVectorSearch` class automatically uses your notebook authentication token (which wo...
- 0 kudos
- 3073 Views
- 3 replies
- 2 kudos
Resolved! Whether Databricks has any plans to Integrate Databricks Genie with Azure OpenAI?
Hi,I am checking to see if Databricks has any plans to Integrate Databricks Genie with Azure OpenAI? as I know Databricks Genie is designed to work with Databricks' data ecosystem itself. But is there any plans to enhance this capability where we can...
- 3073 Views
- 3 replies
- 2 kudos
- 2 kudos
@Prashanthkumar , if you are satisfied with my response would you mind clicking on "Accept as Solution" so that others will have confidence in the answer. Thanks, Louis.
- 2 kudos
- 459 Views
- 2 replies
- 1 kudos
Agent Serving Not Able To Use Route Optimisation
Hey y'all !I have model that I already serve with `agents.deploy` and works fine.I wanted to try out the Route Optimisation features as it can be found in the Edit tab of a model serving by adding in the creation via the API call (https://docs.databr...
- 459 Views
- 2 replies
- 1 kudos
- 1 kudos
@brahaman If this has solved your issue, please click the Accept as Solution button. Thanks!
- 1 kudos
- 341 Views
- 1 replies
- 0 kudos
Cannot create databricks app using knowledge assistant
Hello, I built a knowledge assistant and I want to create a databricks app with it. I am using the streamlit chatbot template. I get an error "endpoint not supported". I can successfully create other databricks apps using models like claude sonnet. I...
- 341 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @mmoise - It is not yet possible to create a DB app using an agent created from Agent Bricks KA. It will be added soon in the future. You can create a custom app, though. You can refer to the DB apps cookbook and use FastAPI as backend and React a...
- 0 kudos
