- 40465 Views
- 23 replies
- 51 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 ...
- 40465 Views
- 23 replies
- 51 kudos
- 6470 Views
- 14 replies
- 10 kudos
Resolved! AgentBricks - Multi Agent Supervisor Issue
Hi, I am doing POC using AgentBricks and using Multi Agent Supervisor. I have configured 2 subagents.1. Genie Space2. UC Function to call LLM3. UC Function to plot chartsHowever, the agent is able to access and use only Genie space agent and not usin...
- 6470 Views
- 14 replies
- 10 kudos
- 10 kudos
We have a Unity Catalog SQL function that is scalar, takes one STRING parameter, returns STRING, and reads a single Delta table. It works when called directly in the SQL editor. Registered as the only tool on an Agent Bricks Supervisor agent, every c...
- 10 kudos
- 346 Views
- 3 replies
- 2 kudos
Can Unity AI Gateway Model Service guardrails protect an existing LangGraph agent deployed as a Data
I have a LangGraph agent deployed as a Unity Catalog model on aDatabricks Serving Endpoint.Architecture:User↓Databricks Serving Endpoint↓UC Model: ai_workspace.agent.agent↓LangGraph agent↓LLM + toolsThe serving endpoint shows "AI Gateway enabled", bu...
- 346 Views
- 3 replies
- 2 kudos
- 2 kudos
AI Gateway Model Service guardrails are scoped to Databricks-hosted foundation models and external LLM endpoints, not to custom UC-registered models or agent-serving endpoints. The "AI Gateway enabled" flag on your endpoint provides usage tracking an...
- 2 kudos
- 40465 Views
- 23 replies
- 51 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 ...
- 40465 Views
- 23 replies
- 51 kudos
- 315 Views
- 1 replies
- 0 kudos
Best Practices for Deploying Custom LLM Pipelines on Databricks?
Hi community,We are currently designing an enterprise-grade LLM pipeline on Databricks to handle end-to-end data processing, model fine-tuning, and inference serving.While Spark handles our data orchestration effectively, we are looking at optimizing...
- 315 Views
- 1 replies
- 0 kudos
- 0 kudos
@exrwebflowai Model Serving and Routing Architecture Hybrid setup anchored by Databricks Model Serving / Unity AI Gateway gives the best balance between deterministic latency and governance for production workloads. Use Provisioned Throughput endpoin...
- 0 kudos
- 407 Views
- 1 replies
- 1 kudos
How Can a Databricks App Render the Same Detailed Response as the Genie UI?
I’m building a Databricks App with a Genie Space at the core and have run into a difference between the Genie UI and the Genie Conversation API.For the same business question, the Genie web UI can produce a detailed response containing an executive s...
- 407 Views
- 1 replies
- 1 kudos
- 1 kudos
Checked the current Genie REST API reference for this rather than guessing, a few concrete answers. Query attachment result data: GET /api/2.0/genie/spaces/{space_id}/conversations/{conversation_id}/messages/{message_id}/attachments/{attachment_id}/q...
- 1 kudos
- 296 Views
- 1 replies
- 0 kudos
Agent mode: will per-turn context reporting be added, or is there another way to read it?
Genie spaces are steered by a semantic layer: text instructions (e.g. "when the user says 'sales', always filter to region = 'EMEA'") and example question→SQL pairs.We read turn payloads programmatically — via the message endpoint behind the Genie UI...
- 296 Views
- 1 replies
- 0 kudos
- 0 kudos
Checked the current Agent mode Responses API docs on this (docs.databricks.com/aws/en/genie-agents/api) and your read looks right, not a gap in your search. The response stream only documents four output item types: reasoning, function_call, function...
- 0 kudos
- 558 Views
- 2 replies
- 1 kudos
Resolved! Custom Agent traces only showing basic input and output
I've been working with MLflow Agent Server deployments using the OpenAI Agents SDK hosted both locally and in Databricks Apps. Currently, tracing is instrumented with:set_trace_processors([]) mlflow.openai.autolog()Locally, everything works great and...
- 558 Views
- 2 replies
- 1 kudos
- 1 kudos
@taniumalloy Unity Catalog trace storage provides additional benefits beyond trace detail - unlimited storage, queryability for analysis and debugging, Unity Catalog governance and permissions and compatibility with the latest features. Trace richnes...
- 1 kudos
- 6045 Views
- 13 replies
- 3 kudos
Resolved! RLS in Genie Space
I am developing a Conversational BI Solution using Genie. There are users from different roles and we need to restrict the rows returned based on the user's role. Typically RLS. I understand from documentation Genie leverage the RLS setup on the Unit...
- 6045 Views
- 13 replies
- 3 kudos
- 3 kudos
This post explains the solution to your problem.Multi-Tenant Genie Spaces: Working Demo | by Rohit Bhagwat | Medium
- 3 kudos
- 556 Views
- 1 replies
- 0 kudos
Databricks-hosted Foundation Model APIs blocked by workspace rate limit of 0
Hello,My Databricks-hosted Foundation Model endpoints appear READY, but every runtime invocation is blocked by a workspace-level quota.Workspace details:- Workspace ID: 7474647458172567- Workspace URL: https://dbc-731cb41b-741e.cloud.databricks.com- ...
- 556 Views
- 1 replies
- 0 kudos
- 0 kudos
@APIUser4827 What you are encountering is the expected behavior in free edition. Databricks imposes a hard limit of 0 on premium, high demand Foundation Models especially - Claude and GPT groups when a workspace is operating under a free edition.You ...
- 0 kudos
- 1172 Views
- 5 replies
- 0 kudos
Failed to save agent Supervisor Agent is not available. To access this feature, please contact sales
Hello,I am trying to create a Supervisor Agent via the web UI, and when starting to try and use it I get the errorFailed to save agent Supervisor Agent is not available. To access this feature, please contact salesThis is despite this preview being e...
- 1172 Views
- 5 replies
- 0 kudos
- 0 kudos
Well @appliable_ai then you might want to open a support ticket/contact your Databricks account team and ask them to enable/fix the Supervisor Agent entitlement on workspace. It works for me, but if I remember correctly I had to reach out to the our...
- 0 kudos
- 423 Views
- 3 replies
- 2 kudos
Endpoint Error
I have a GCP Databricks account on the Enterprise plan with GCP Marketplace configured as the default payment method. Partner-powered AI features are enabled, and we enabled the Supervisor API Beta preview. Unity Catalog v3 model services are visible...
- 423 Views
- 3 replies
- 2 kudos
- 2 kudos
Hey, thanks for replying! I'm not really sure how to upgrade 'further' from what I can currently see under the 'Billing' section of my workplace, screenshot for the same is attached; your advice would be really helpful!
- 2 kudos
- 637 Views
- 1 replies
- 0 kudos
Resolved! Bedrock and Genie
Genie expertsWe are planning to utilize the AWS Bedrock agent to work with Genie One and invoke endpoints within Databricks. Our setup will involve multiple Databricks accounts that will be integrated with the Bedrock agent. I would appreciate any g...
- 637 Views
- 1 replies
- 0 kudos
- 0 kudos
A few practical patterns/gotchas that tend to matter for this kind of setup: 1. Bedrock doesn't have a native Genie connector, so the usual approach is to implement the call as a Bedrock Agent action group backed by a Lambda function. The Lambda wrap...
- 0 kudos
- 1555 Views
- 5 replies
- 4 kudos
[Genie] Format assistance & entity match doesn't work for me
I enable format assistance & entity match for some table fields in my genie space. But it looks like it doesn't work. e.g. the following field is categorical and I enable format assistance & entity match for it. The following is the generated sql: mo...
- 1555 Views
- 5 replies
- 4 kudos
- 4 kudos
@pavannaidu I would like to reopen this issue, as I have faced similar problems (and yes I made sure to enable it properly, toggling off and saving, toggling on and saving again, etc.). For Genie Agent in Chat Mode, when going into the thinking proce...
- 4 kudos
- 323 Views
- 2 replies
- 1 kudos
Questions about "Store OpenTelemetry traces in Unity Catalog"
Hi,I'm trying to use the OpenTelemetry traces in Unity Catalog https://docs.databricks.com/aws/en/mlflow3/genai/tracing/trace-unity-catalogBut I'm having trouble to understand the behavior.First, I can't find any data in the following two tables.<tab...
- 323 Views
- 2 replies
- 1 kudos
- 1 kudos
The _otel_logs and _otel_metrics tables may remain empty if your traces are stored primarily in the spans table. Check _otel_spans first and verify that the UC trace storage and permissions are configured correctly.For a new setup, use Unity Catalog ...
- 1 kudos
- 538 Views
- 5 replies
- 0 kudos
facing issue in llm models
i have signed up to databricks using aws but when i try to access model i m getting error Error (403): PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0.
- 538 Views
- 5 replies
- 0 kudos
- 0 kudos
Yes. If you have already upgraded from the Free Trial to Enterprise and the error is still exactly Databricks-set rate limit of 0, then changing the QPM/TPM limit in the UI is not going to fix it.I checked the current Databricks documentation and rec...
- 0 kudos
-
agent
2 -
agent bricks
2 -
Agent Skills
1 -
agents
2 -
AI
3 -
AI Agents
11 -
ai gateway
3 -
AIAgents
1 -
Anthropic
1 -
API Documentation
1 -
App
3 -
Application
1 -
Artificial Intelligence
1 -
Asset Bundles
1 -
Authentication
1 -
Autologging
1 -
automoation
1 -
Aws databricks
2 -
ChatDatabricks
1 -
claude
5 -
Cluster
1 -
copilot
1 -
copilot_studio
1 -
Credentials
1 -
crewai
1 -
cursor
1 -
Custom Agents
1 -
Data Engineering
1 -
databricks
1 -
Databricks App
3 -
Databricks Course
1 -
Databricks Delta Table
1 -
databricks genie
1 -
Databricks Mlflow
2 -
Databricks Notebooks
1 -
Databricks SQL
1 -
Databricks Table Usage
1 -
Databricks-connect
1 -
databricksapps
1 -
delta sync
1 -
Delta Tables
1 -
Developer Experience
1 -
DLT Pipeline
1 -
documentation
1 -
Ethical Data Governance
1 -
Foundation Model
4 -
gemini
1 -
gemma
1 -
GenAI
12 -
GenAI agent
2 -
GenAI and LLMs
5 -
GenAI Generation AI
1 -
GenAIGeneration AI
55 -
Generation AI
3 -
Generative AI
8 -
Genie
22 -
Genie - Notebook Access
2 -
Genie Agent
2 -
Genie Code
3 -
GenieAPI
5 -
Google
1 -
GPT
1 -
healthcare
1 -
Index
1 -
inference table
1 -
Information Extraction
1 -
Knowledge Agent
1 -
Langchain
4 -
LangGraph
1 -
Llama
1 -
Llama 3.3
1 -
LLM
2 -
Machine Learning
1 -
machine-learning
1 -
mcp
4 -
Metric Views
1 -
MlFlow
4 -
MLflow Experiment
1 -
Mlflow registry
1 -
MLFlow Tracking Server
1 -
MLModels
1 -
Model Serving
3 -
modelserving
1 -
mosic ai search
1 -
Multiagent
2 -
NPM error
1 -
OpenAI
1 -
Pandas udf
1 -
Playground
1 -
productivity
1 -
Pyspark
1 -
Pyspark Dataframes
1 -
RAG
4 -
ro
1 -
Scheduling
1 -
Server
1 -
serving endpoint
3 -
streaming
2 -
Tasks
1 -
tools
1 -
Vector
1 -
vector index
1 -
Vector Search
2 -
Vector search index
6
- « Previous
- Next »
| User | Count |
|---|---|
| 44 | |
| 31 | |
| 28 | |
| 17 | |
| 14 |