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
  • 42551 Views
  • 24 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 ...

Screenshot 2024-01-24 at 11.32.01 PM.png
  • 42551 Views
  • 24 replies
  • 51 kudos
Latest Reply
ThiamLee
Contributor III
  • 51 kudos

Great initiative by Databricks! This is a valuable opportunity to build practical GenAI skills and stay ahead in the rapidly evolving AI space.

  • 51 kudos
23 More Replies
SandipCoder
by • New Contributor II
  • 3996 Views
  • 2 replies
  • 0 kudos

How to deploy an agent into model registry using MLFlow

Goal :Here below I am attaching my code snippet where I am trying to build an agent on my custom functions .Things are working well when I am running agent.invoke(“Question”).But now I want to deploy this agent into model registry using MLFlow but I ...

  • 3996 Views
  • 2 replies
  • 0 kudos
Latest Reply
prar_shah
New Contributor III
  • 0 kudos

Had the same question when I was trying to deploy my custom llm. How we did it was wrapping it inside a custom mlflow model and registering it.

  • 0 kudos
1 More Replies
olivierddr
by • New Contributor III
  • 19165 Views
  • 1 replies
  • 6 kudos

Databricks MCP Server

Hey, couldn't find a working Databricks MCP so I forked one and fixed it: https://github.com/markov-kernel/databricks-mcp This allows you to (using Cursor, Claude Code, Windsurf, Claude, etc.):*   Manage Databricks Clusters: List, create, terminate, ...

  • 19165 Views
  • 1 replies
  • 6 kudos
Latest Reply
spaceghost
New Contributor II
  • 6 kudos

very cool

  • 6 kudos
Krthk
by • New Contributor
  • 1855 Views
  • 1 replies
  • 0 kudos

Datbricks Notebook as a Server ?

Hello, What I'm trying to do : I have a piece of python code (an ai application) that i want to deploy as a server, almost exactly like one would lets say on an EC2. The only difference being instead of a flask api i would use dbutils and the databri...

  • 1855 Views
  • 1 replies
  • 0 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 0 kudos

Hi @Krthk, Thanks for your question. Have you thought about using Model serving endpoint for your use-case: https://docs.databricks.com/aws/en/machine-learning/model-serving/ Launching a Databricks job via the REST API and dbutils is a different para...

  • 0 kudos
neha89
by • New Contributor II
  • 4930 Views
  • 3 replies
  • 1 kudos

Resolved! Custom LLM Function similar to Databricks built in AI functions

Hi Team,I am new to Databricks and working on Gen AI requirements.Task - Build custom prompt with set of instructions to classify incident e.g. False Positive or True Positive. Input will be columns in Delta TableCan I build custom LLM function with ...

  • 4930 Views
  • 3 replies
  • 1 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 1 kudos

No problem, if you have any other question, let me know!

  • 1 kudos
2 More Replies
SaiVihAI
by • New Contributor
  • 2233 Views
  • 1 replies
  • 0 kudos

Vector Quantization

Does Databricks Vector Search support vector quantization?

  • 2233 Views
  • 1 replies
  • 0 kudos
Latest Reply
santhakumar11
New Contributor III
  • 0 kudos

Hi SaiVihAIIn my opinion, Databricks utilizes Mosaic Vector Search, which is largely aided by the Hierarchial Navigable Small World (HNSW) algorithm for neighbor search and hybrid keyword similarity search.Ref   Mosaic AI Vector Search | Databricks D...

  • 0 kudos
sebascardonal
by • Databricks Partner
  • 19358 Views
  • 4 replies
  • 0 kudos

Resolved! 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...

  • 19358 Views
  • 4 replies
  • 0 kudos
Latest Reply
sebascardonal
Databricks Partner
  • 0 kudos

Hi @moemedina. No, I didn't.I'm considering using ChatModel/ChatAgent class to wrap the graph and be able to move on. However, the MLflow documentation is still referring to ChatModel where Chat Agent is the latest recommendation:MLflow ChatModel Doc...

  • 0 kudos
3 More Replies
SaiVihAI
by • New Contributor
  • 2038 Views
  • 1 replies
  • 0 kudos

Metadata filtering mechanism in Databricks Vector Search

Does Databricks vector search support pre-filtering or post-filtering or both in metadata filtering?

  • 2038 Views
  • 1 replies
  • 0 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 0 kudos

Hello @SaiVihAI, Yes, It uses in-query filtering. The algorithm takes a series of iterative steps to determine if the filtered set is small enough to execute brute-force search or if it proceeds with AN

  • 0 kudos
Mohamednazeer
by • New Contributor III
  • 8140 Views
  • 2 replies
  • 2 kudos

Serving endpoint with external model (azure openai) is throwing "Public network access is disable "

Databricks serving endpoint is not working as expected throwing an exception as "Public network access is disable, Create private endpoints".We have create the azure openAI resource with public network access disabled, but also we have created the pr...

  • 8140 Views
  • 2 replies
  • 2 kudos
Latest Reply
Ismael-K
Databricks Employee
  • 2 kudos

Serving endpoints with external models will require creating Network Connectivity Configuration objects at the account level to connect to the Azure OpenAI resource. The feature is currently in private preview, please reach out to your Databricks acc...

  • 2 kudos
1 More Replies
VELU1122
by • New Contributor II
  • 6202 Views
  • 1 replies
  • 0 kudos

Copying/cloning Vector index table

Regarding copying or cloning vector index tables, it appears that direct copying or cloning is not possible, as Databricks throws the message: "Securable with kind TABLE_ONLINE_VECTOR_INDEX_REPLICA does not support Lakehouse Federation."It seems that...

  • 6202 Views
  • 1 replies
  • 0 kudos
Latest Reply
Ismael-K
Databricks Employee
  • 0 kudos

Direct cloning of a vector index table may not be possible. However, if Databricks generates the embeddings, you can enable "Sync computed embeddings" to save them to a Unity Catalog table. Alternatively, you can set the parameter sync_computed_embed...

  • 0 kudos
Paolo_Finardi
by • New Contributor III
  • 4771 Views
  • 4 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...

  • 4771 Views
  • 4 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
3 More Replies
aero_g
by • Databricks Partner
  • 3194 Views
  • 1 replies
  • 0 kudos

Issues with Generating Synthetic Data Using the Mosaic AI API - 403 Permission Denied Error

 Hi everyone,I’m currently working with the new Synthetic Data Generation API in Mosaic AI, and I’ve encountered an issue when trying to generate questions for a document. Specifically, I’m running into the following error:Failed to generate question...

  • 3194 Views
  • 1 replies
  • 0 kudos
Latest Reply
Alberto_Umana
Databricks Employee
  • 0 kudos

Hi @aero_g, Looks like it is not supported on your region, but I will get more details internally.

  • 0 kudos
paalvibe
by • Databricks MVP
  • 2690 Views
  • 3 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...

  • 2690 Views
  • 3 replies
  • 0 kudos
Latest Reply
paalvibe
Databricks MVP
  • 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
2 More Replies
Nawneet
by • New Contributor II
  • 1731 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...

  • 1731 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
Kjetil
by • Contributor
  • 7055 Views
  • 4 replies
  • 4 kudos

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...

  • 7055 Views
  • 4 replies
  • 4 kudos
Latest Reply
LaurenFletcher
New Contributor II
  • 4 kudos

Wow, Thank you so much for your help.

  • 4 kudos
3 More Replies
kbmv
by • Contributor
  • 3397 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
  • 3397 Views
  • 1 replies
  • 0 kudos
Latest Reply
kbmv
Contributor
  • 0 kudos

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

  • 0 kudos
Labels