cancel
Showing results for 
Search instead for 
Did you mean: 
Generative AI
Explore discussions on generative artificial intelligence techniques and applications within the Databricks Community. Share ideas, challenges, and breakthroughs in this cutting-edge field.
cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Sujitha
by Databricks Employee
  • 19033 Views
  • 13 replies
  • 20 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 ...

Screenshot 2024-01-24 at 11.32.01 PM.png
  • 19033 Views
  • 13 replies
  • 20 kudos
Latest Reply
Ayushi01
New Contributor II
  • 20 kudos

How to access the playground?

  • 20 kudos
12 More Replies
Nawneet
by New Contributor II
  • 42 Views
  • 1 replies
  • 0 kudos

Error running mlflow.evaluate()

Hi Team,I am following below article to evaluate my model.What is Mosaic AI Agent Evaluation? | Databricks on AWSExample for my model is below:input_example = pd.DataFrame({    "text": ["What is the stoppage duration for January month 2024?"],    "pa...

  • 42 Views
  • 1 replies
  • 0 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 0 kudos

Hello @Nawneet, Ensure that the input format for the agent evaluation matches the expected schema. Here is an example to structure your input data correctly: import mlflow import pandas as pd examples = { "request": [ {"messages": [{"ro...

  • 0 kudos
wind2025
by New Contributor
  • 85 Views
  • 1 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...

  • 85 Views
  • 1 replies
  • 1 kudos
Latest Reply
Mantsama4
Contributor III
  • 1 kudos

Interesting use case, would love to know the answer!

  • 1 kudos
MarsWalker
by New Contributor
  • 40 Views
  • 0 replies
  • 0 kudos

How to serve a RAG chain endpoint that supports streaming

Hello everyone,I am trying to serve a sample RAG chain model that should support streaming output. But I could not find any documantation on how to enable streaming for a serving endpoint for a langchain model. Could you provide some hints on how to ...

  • 40 Views
  • 0 replies
  • 0 kudos
paalvibe
by New Contributor III
  • 156 Views
  • 2 replies
  • 0 kudos

Should elaborate and complex LLM apps be deployed as MLFlow serving endpoints?

In a project we are building increasingly complex LLM-based Apps (RAG, multi-agent workflows, langgraph, unstructured ingestion etc), and we are having doubts if these apps should be deployed as MLFlow-based endpoints. I would like your feedback on i...

  • 156 Views
  • 2 replies
  • 0 kudos
Latest Reply
paalvibe
New Contributor III
  • 0 kudos

Actually, maybe root folder was imprecise. The point is that it gets file system access. It becomes a regular Workspace user, with too much access. If, however, you want to give it specific accesses beyond that, you could give it access to specific v...

  • 0 kudos
1 More Replies
heramb13
by New Contributor II
  • 211 Views
  • 3 replies
  • 0 kudos

Unable to log MLFlow run for LangChain chain while using databricks-langchain library

Whenever I try to log my run it throws me the following error: MlflowException: Failed to save runnable sequence: {'0': 'RunnableParallel<query,context> -- Failed to save runnable sequence: {\'context\': "RunnableSequence -- Failed to save runnable s...

  • 211 Views
  • 3 replies
  • 0 kudos
Latest Reply
heramb13
New Contributor II
  • 0 kudos

@Alberto_Umana or anyone? 

  • 0 kudos
2 More Replies
sebascardonal
by New Contributor II
  • 248 Views
  • 2 replies
  • 0 kudos

LangGraph MemorySaver checkpointer usage with MLflow

Hi everyone.I am working on a graph that utilizes the MemorySaver class to incorporate short-term memory. This will enable me to maintain a multi-turn conversation with the user by storing the chat history.I am using the MLflow "models from code" fea...

  • 248 Views
  • 2 replies
  • 0 kudos
Latest Reply
Pawan1979
New Contributor II
  • 0 kudos

To register a LangGraph graph in MLflow using MemorySaver for short-term memory, you can follow these steps:1. **Set up MemorySaver:** Create a `MemorySaver` checkpointer to enable persistent checkpointing, which saves the state of the graph after ea...

  • 0 kudos
1 More Replies
Kjetil
by Contributor
  • 404 Views
  • 4 replies
  • 5 kudos

Resolved! Model Serving and Streaming

Hi everyone,I have a question regarding the concurrency limitations of streaming responses from an LLM chain via Databricks Model Serving.When using a streaming response, the request remains open for the duration of the generation process. For exampl...

  • 404 Views
  • 4 replies
  • 5 kudos
Latest Reply
LaurenFletcher
New Contributor II
  • 5 kudos

Wow, Thank you so much for your help.

  • 5 kudos
3 More Replies
kbmv
by New Contributor III
  • 225 Views
  • 1 replies
  • 0 kudos

Resolved! Understanding compute requirements for Deploying Deepseek-R1-Distilled-Llama Models on databricks

Hi I came across the blog Deploying Deepseek-R1-Distilled-Llama Models on Databricks at https://www.databricks.com/blog/deepseek-r1-databricksI am new to using custom models that are not available as part of foundation models.According to the blog, I...

kbmv_0-1738850768911.png
  • 225 Views
  • 1 replies
  • 0 kudos
Latest Reply
kbmv
New Contributor III
  • 0 kudos

Its Resolved https://community.databricks.com/t5/machine-learning/understanding-compute-requirements-for-deploying-deepseek-r1/m-p/109357#M3956

  • 0 kudos
aliciachimeno
by New Contributor II
  • 337 Views
  • 6 replies
  • 4 kudos

Genie Agent Integration in Databricks

I'm developing an Agent using the Cookbook template and would like to incorporate a Genie agent. I came across the Databricks GitHub repository and noticed they're actively working on it: GitHub - Genie Agent. However, it seems to be in the early sta...

  • 337 Views
  • 6 replies
  • 4 kudos
Latest Reply
NathanSundarara
Contributor
  • 4 kudos

I think Teams/Slack channel as a chat bot will be more exciting use case. When we demoed the Genie to our executives we are in Retail Industry Client and we have lots of stores one of the thing they said is this would be awesome if this can be in Tea...

  • 4 kudos
5 More Replies
Paolo_Finardi
by New Contributor III
  • 194 Views
  • 3 replies
  • 2 kudos

Building a Chatbot Assistant for Data Analysts Leveraging Unity Catalog

Hey everyone,I'm working on a project to enhance our data analysts' experience on the platform. In our company, we've done a great job with Unity Catalog, and we have comprehensive descriptions for all the tables and columns in our data lake.I'm inte...

  • 194 Views
  • 3 replies
  • 2 kudos
Latest Reply
Paolo_Finardi
New Contributor III
  • 2 kudos

Hi MariuszK,I can confirm that the RAG architecture on Databricks works very well—we’ve taken it to production and are very satisfied with the results. As a first step, I'll try creating a Genie Room on the system table to see if it can help retrieve...

  • 2 kudos
2 More Replies
dileepkumar_t
by New Contributor
  • 844 Views
  • 1 replies
  • 0 kudos

Error - Interact with SQL database

 When I try to use Datbricks sql agent, I'm getting below error:DatabaseError: (databricks.sql.exc.ServerOperationError) [UNBOUND_SQL_PARAMETER] Found the unbound parameter: param_1. Please, fix `args` and provide a mapping of the parameter to a SQL ...

  • 844 Views
  • 1 replies
  • 0 kudos
Latest Reply
kamal_ch
Databricks Employee
  • 0 kudos

Hi @dileepkumar_t The UNBOUND_SQL_PARAMETER error in Databricks SQL Agent occurs when a parameter marker in a SQL query is not associated with a value. This error is raised because the SQL query is expecting a parameter to be provided, but it has not...

  • 0 kudos
Mohanrajv27
by New Contributor
  • 646 Views
  • 1 replies
  • 0 kudos

Cost Analysis for Databricks Compute

I am currently using the Databricks Vector Search on top of my databricks workspace and running the DBRX Model for querying off and retrieve the results out of it.I have noticed something, a category of compute occurred, which I haven't seen earlier....

  • 646 Views
  • 1 replies
  • 0 kudos
Latest Reply
kamal_ch
Databricks Employee
  • 0 kudos

Hi @Mohanrajv27 The "Automated Serverless compute Pro" category in Databricks is designed to provide a serverless environment where compute resources are automatically managed and scaled by Databricks. Hope this answers your question!

  • 0 kudos
thmonte
by New Contributor II
  • 179 Views
  • 2 replies
  • 1 kudos

Tool Calls with Workspace Models

I recently followed the blog post on running deepseek llama distilled.  I then served it via Serving Endpoints with provisioned throughput.  In my use case I am using pydantic-ai to build out some simple agents for testing.  It seems with this style ...

  • 179 Views
  • 2 replies
  • 1 kudos
Latest Reply
thmonte
New Contributor II
  • 1 kudos

Thanks @Alberto_Umana which one of these controls allows the conversation to continue past the first tool call?  Is there documentation on all configurable fields?  Also does this still allow override some of these at the client level? Ex. passing in...

  • 1 kudos
1 More Replies
SristiRaj
by New Contributor
  • 182 Views
  • 1 replies
  • 0 kudos

Databricks REST api to manage and deploy Genie spaces programmatically

Hello,I am looking to find documentation for databricks REST api for creating and deploying genie spaces with necessary configuration. Could you please guide me to the documentation for the same.Regards,Sristi Raj 

  • 182 Views
  • 1 replies
  • 0 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 0 kudos

Hi @SristiRaj, Currently there is not API for that. I see that Databricks Genie Conversation APIs are currently in private preview. Please stay tune for news on this!

  • 0 kudos