- 41574 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 ...
- 41574 Views
- 23 replies
- 51 kudos
- 3889 Views
- 3 replies
- 0 kudos
Vector Index format.
On of the key benefits of a delta table format is that it's open. Is this also the case for vector indexes as well? If so where could I find it's specification?In Databricks today, we see that we can create and manage a vector index using API's. (ht...
- 3889 Views
- 3 replies
- 0 kudos
- 0 kudos
HI Team, I am trying to update an existing vector search index with new data which is in another delta table. But i have no luck figuring out how to do it using Python SDK. Can you please hekp point to the right resources?
- 0 kudos
- 5948 Views
- 1 replies
- 0 kudos
Is It Possible to use genie as tool in agents?
Hello, community,I am currently exploring the agentic workflow surrounding Genie and would like to know if there are ways to effectively integrate or incorporate Genie as a tool within my existing agentic workflow. I am open to utilizing frameworks s...
- 5948 Views
- 1 replies
- 0 kudos
- 0 kudos
You may find this useful for your use case - https://gist.github.com/prithvikannan/82e789730c2fceec11932816bda50e59
- 0 kudos
- 4407 Views
- 1 replies
- 1 kudos
Resolved! AI/BI Genie Space - 20 QPM
Hi Databricks Community,I'm working with Genie Spaces and came across the documented limit of 20 questions per minute per workspace. Could someone please confirm whether this is a soft limit, and if it can be relaxed or increased upon request through...
- 4407 Views
- 1 replies
- 1 kudos
- 1 kudos
Hello @Rumesh! The 20 questions per minute per workspace limit is fixed. To double-check for enterprise or production use cases, I recommend contacting your Account Executive or Databricks Support to confirm or explore possible options.
- 1 kudos
- 5302 Views
- 2 replies
- 1 kudos
Databricks Serving Endpoint 400 Error: Model Response Format Issue while langgraph tool calling
Dear Databricks Community,I am seeking assistance with an issue I've encountered while deploying a model on Databricks. When invoking the serving endpoint, I receive the following error message sometimes:400 Client Error: Error: Model response did no...
- 5302 Views
- 2 replies
- 1 kudos
- 1 kudos
Same issue here... developing a langraph tool-calling agent, and for certain (but not all) questions, I get the same error.Any luck resolving?
- 1 kudos
- 1062 Views
- 1 replies
- 0 kudos
Compute Claster Creation Failing
Everytime we try to roll out compute cluster it fails.
- 1062 Views
- 1 replies
- 0 kudos
- 0 kudos
Hey @SomLTIM , Can you provide any additional information here to help troubleshoot? It would be helpful to know the region, cloud, error message, and any configurations you can provide on the cluster.
- 0 kudos
- 3236 Views
- 1 replies
- 0 kudos
Unable to read message from Genie Conversation API
Hi Team,I am facing issue in getting the message details from the genie conversation API. I have created the conversation, which returns the message ID and conversation ID. But I am unable to see the message. I am getting error, when hitting the Get ...
- 3236 Views
- 1 replies
- 0 kudos
- 0 kudos
@RitikaKulshrest I can see what's happening with your Genie conversation API issue. The problem is not with your API call but with the Genie service's attempt to execute your query.The response indicates that your message was received but failed to p...
- 0 kudos
- 2641 Views
- 3 replies
- 0 kudos
Genie Agent integration issue
Hi, anyone from development team for Genie Agent integration? i had an issue of using sample code of Genie Agent integration. The issue is that underlying code (databricks_ai_bridge/genie.py) cannot connect to url openaipublic.blob.core.windows.net ...
- 2641 Views
- 3 replies
- 0 kudos
- 0 kudos
You're absolutely right. The implementation should definitely take restricted network scenarios into consideration, as many enterprise Databricks deployments operate in air-gapped or network-restricted environments.Commenting out the token counting l...
- 0 kudos
- 9786 Views
- 2 replies
- 2 kudos
Resolved! LLM with the largest context window
A Generative AI Engineer is tasked with developing an application that is based on an open-source large language model (LLM). They need a foundation LLM with a large context window. Which model fits this need?DBRX,Llama2-70B,DistilBert MPT-30B.DBRX h...
- 9786 Views
- 2 replies
- 2 kudos
- 2 kudos
@royinblr11 You're absolutely right to question the answer — the correct model for an application needing a foundation LLM with a large context window is: DBRXWhy DBRX is the Best Fit:It is a foundation model, designed for generation tasks.It support...
- 2 kudos
- 1876 Views
- 3 replies
- 0 kudos
Are serverless endpoints possible in this Technical Blog post by qianyu?
Hi, are serverless endpoints possible for Whisper and Llama in this Technical Blog post by qianyu?https://community.databricks.com/t5/technical-blog/streamline-customer-call-center-transcripts-analytics-with/ba-p/101689Thanks!
- 1876 Views
- 3 replies
- 0 kudos
- 0 kudos
https://www.databricks.com/product/pricing/foundation-model-servingWe don´t serve models on databricks, but as far as i can see you pay per input/output tokens (for foundation models).For classic models:https://www.databricks.com/product/pricing/mode...
- 0 kudos
- 6362 Views
- 4 replies
- 2 kudos
Resolved! MLFlow Authentication from Databricks App for GenAI Tracing
I am working on a Dash-based app that includes a call to a Databricks-hosted LLM endpoint. I am trying to track those calls with MLFlow. My code is (roughly) like this:from openai import OpenAIimport mlflowmlflow.set_tracking_uri("databricks")mlflow....
- 6362 Views
- 4 replies
- 2 kudos
- 2 kudos
Thank you for the push in the right direction! I was able to solve the issue with this codeos.environ["DATABRICKS_CLIENT_ID"] = "" os.environ["DATABRICKS_CLIENT_SECRET"] = "" os.environ["DATABRICKS_TOKEN"] = os.environ.get("VAR_CONFIGURED_WITH_DATABR...
- 2 kudos
- 11290 Views
- 2 replies
- 1 kudos
AI/BI Genie API
Hi everyone,I'm currently working on a project that implements a custom front end for Genie using the Genie API: https://docs.databricks.com/api/workspace/genie. So far, I’ve successfully built a working model that can send and receive messages.Howev...
- 11290 Views
- 2 replies
- 1 kudos
- 1 kudos
Is there any possibility that workspace admin could have removed this permission to you? If you check the permissions on your side do you see yourself with at least Can View?
- 1 kudos
- 5307 Views
- 1 replies
- 0 kudos
Resolved! Roadmap for vector_search function
I was wondering if there was a roadmap for the development of the vector_search function: vector_search function | Databricks DocumentationSpecifically, I was wondering if / when the following limitations may be lifted:Querying DIRECT_ACCESS index ty...
- 5307 Views
- 1 replies
- 0 kudos
- 0 kudos
Hello @jAAmes_bentley, DIRECT_ACCESS & filters_json are not currently supported with vector_search sql function. These are on our roadmap, but we don’t have concrete ETAs to share at the moment as we’re focusing on other high-priority tasks. Hybrid s...
- 0 kudos
- 10882 Views
- 1 replies
- 0 kudos
Resolved! How to do NLP against PDFs in Databricks? Can be done in Snowflake very easily.
I’d love to build a quick "art of the possible" demo showing how easy it is to query unstructured PDFs using natural language. In Snowflake, I wired up a similar solution in ~2 hours just by following their tutorial guide.Does anyone know the best wa...
- 10882 Views
- 1 replies
- 0 kudos
- 0 kudos
To query unstructured PDF files using natural language in Databricks, you can leverage an approach similar to the "Retrieval Augmented Generation (RAG) and DBRX" demo. Although the specific demo you referenced (https://notebooks.databricks.com/demos/...
- 0 kudos
- 5793 Views
- 4 replies
- 3 kudos
LangChain Compatibility in Databricks – Painfully Inconsistent Experience
Hey all,Is anyone else experiencing major friction when using LangChain within Databricks?Even after carefully pinning versions like:%pip install \ loguru \ mlflow==2.10.1 \ langchain==0.1.5 \ langchain-google-vertexai \ databricks-vectorse...
- 5793 Views
- 4 replies
- 3 kudos
- 3 kudos
I'll definitely look into installing libraries at the cluster level via init scripts makes a lot of sense for stability and reproducibility. I hadn't considered that approach, so I really appreciate you highlighting that and providing the relevant Da...
- 3 kudos
- 5063 Views
- 1 replies
- 0 kudos
Getting "The given endpoint does not exist" for LLM endpoint though I've access to it
When trying out this LLM RAG notebook steps I'm getting this error:"The given endpoint does not exist, please retry after checking the specified model and version deployment exists"This notebook originally referred to databricks-meta-llama-3-1-70b-in...
- 5063 Views
- 1 replies
- 0 kudos
- 0 kudos
Hey @Iris12 ,Not sure if this will fix your issue, but I’ve seen similar errors caused by permission mismatches.Make sure that the user or service principal you’re using has the correct permissions both in the Models and Serving tab.Also, double-chec...
- 0 kudos
