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
  • 30814 Views
  • 19 replies
  • 34 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
  • 30814 Views
  • 19 replies
  • 34 kudos
Latest Reply
Poorva21
New Contributor II
  • 34 kudos

This is an exciting step forward from Databricks! Looking forward to diving into the curriculum and exploring what's next in the world of data + AI! Thanks for sharing @Sujitha 

  • 34 kudos
18 More Replies
shivamrai162
by New Contributor III
  • 149 Views
  • 2 replies
  • 1 kudos

Resolved! Not able to add scorer to multi agent supervisor

Hello,When I try to add scorers to Multi agent endpoint based on the last 10 traces that I have logged and visible in the experiments tab, i get this error.Also, are there any demos which i can refer regarding the tabs within the evaluation bar expla...

shivamrai162_0-1763609354150.png shivamrai162_2-1763609468060.png
  • 149 Views
  • 2 replies
  • 1 kudos
Latest Reply
stbjelcevic
Databricks Employee
  • 1 kudos

Hi @shivamrai162 , Did you add the last 10 traces to the evaluation dataset? You can follow the steps here to make sure you added the traces to the evaluation dataset. To answer your second question, here is a good article that covers the concepts an...

  • 1 kudos
1 More Replies
jmartin1
by New Contributor
  • 158 Views
  • 1 replies
  • 1 kudos

Resolved! Claude Code-Execution Call Format

Is it possible to use the code execution tool with instances of Claude hosted through Databricks? If I try to format the payload like in Anthropic's documentation, I get an error that the function isn't defined properly:  tools=[{ "type": ...

  • 158 Views
  • 1 replies
  • 1 kudos
Latest Reply
Louis_Frolio
Databricks Employee
  • 1 kudos

Greeting @jmartin1 ,  The Anthropic “code execution” tool isn’t supported through Databricks’ Foundation Model APIs. Databricks exposes an OpenAI-compatible tools interface, and the only supported tool type today is a function defined with a JSON sch...

  • 1 kudos
dfighter1312
by New Contributor
  • 4653 Views
  • 3 replies
  • 1 kudos

Behavior of Vector Index Sync with Delta Tables When Using OVERWRITE vs MERGE in Databricks

I'm working with vector search in Databricks using vector index sync with Delta tables, and I'm a bit unclear on how updates to the source table affect the vector index, specifically when using different write operations.If I overwrite the source Del...

  • 4653 Views
  • 3 replies
  • 1 kudos
Latest Reply
jameswood32
Contributor
  • 1 kudos

From community experience, vector index sync behavior depends heavily on how the Delta table is updated. With OVERWRITE, the table is effectively replaced, so the vector index typically treats this as a full refresh. Existing embeddings are dropped a...

  • 1 kudos
2 More Replies
Rajat-TVSM
by New Contributor III
  • 142 Views
  • 2 replies
  • 1 kudos

Documentation on all ways to access agent serving endpoint from outside databricks

Struggling to find clear documentation which can help me with the subject. Need to know all the ways (production best practices) along with API method. As far as I know, using PAT is not a production best practice

  • 142 Views
  • 2 replies
  • 1 kudos
Latest Reply
Gecofer
Contributor II
  • 1 kudos

Hi @Rajat-TVSM You’re absolutely right that Personal Access Tokens (PATs) are not considered a production best practice. For accessing Agent / Model Serving endpoints from outside Databricks, the recommended and supported approach for production is:S...

  • 1 kudos
1 More Replies
Suheb
by Contributor
  • 195 Views
  • 3 replies
  • 2 kudos

How do I integrate third-party ML/AI libraries with Databricks GenAI workflows?

How can I use external AI libraries inside my Databricks GenAI projects?

  • 195 Views
  • 3 replies
  • 2 kudos
Latest Reply
Thompson2345
New Contributor III
  • 2 kudos

You can use third-party ML/AI libraries in Databricks GenAI by installing them on your cluster or notebook (%pip install library-name), importing them in your code, and then integrating their outputs into your GenAI workflows. For large models, use a...

  • 2 kudos
2 More Replies
Jackryan360
by New Contributor
  • 200 Views
  • 2 replies
  • 1 kudos

How do Agentic AI services differ from traditional AI automation tools?

Hi everyone,I’m looking to understand the real difference between Agentic AI services and the traditional AI automation tools many businesses already use.In your experience, what makes Agentic AI services more advanced or effective?Are the advantages...

Generative AI
Agentic AI
AI
erpsoftware
Microsoft
  • 200 Views
  • 2 replies
  • 1 kudos
Latest Reply
Abeshek
New Contributor
  • 1 kudos

Hi @Jackryan360, I saw your question on Agentic AI vs traditional automation. Many teams are exploring the same distinction as they shift from rule-based workflows to autonomous, multi-step agent systems. At Kanerika, we’ve been helping companies eva...

  • 1 kudos
1 More Replies
GiriSreerangam
by New Contributor III
  • 285 Views
  • 5 replies
  • 2 kudos

ai_parse_document + Genie with ai_query

Hi EveryoneI have used ai_parse_document to process multiple PDFs and store the parsed data in a table (one PDF per row). Later, I ran ai_query in natural language, which correctly scans all rows and returns answers from each PDF.However, when I use ...

  • 285 Views
  • 5 replies
  • 2 kudos
Latest Reply
Hubert-Dudek
Databricks MVP
  • 2 kudos

I think Genie is not optimized for this use case. Please run some experiments - chunk pdf to use multi-agent supervisor from agent bricks to combine Genie with Knowledge Base (although I haven't yet it yet)

  • 2 kudos
4 More Replies
Suheb
by Contributor
  • 108 Views
  • 1 replies
  • 0 kudos

What’s the recommended architecture for integrating Databricks + MLflow + GenAI for model training

If I want to use Databricks, MLflow, and GenAI together, what is the best way to organize and connect them so that I can train AI models and then use them in real apps?

  • 108 Views
  • 1 replies
  • 0 kudos
Latest Reply
Raman_Unifeye
Contributor III
  • 0 kudos

Broad question. I will recommend to follow Databricks offical documents and ML Training at their customer portal.Yet, I will try to answer it as belowUse the Databricks Lakehouse as the unified platform, with Unity Catalog (UC) providing centralized ...

  • 0 kudos
JN_Bristol
by Contributor
  • 2029 Views
  • 6 replies
  • 3 kudos

Resolved! ai_parse_document struggling to detect pdf

Hi helpful experts I'm writing my first PySpark Notebook that makes use of the new `ai_parse_document` function.  I am basically following the code example from here: https://learn.microsoft.com/en-gb/azure/databricks/sql/language-manual/functions/ai...

  • 2029 Views
  • 6 replies
  • 3 kudos
Latest Reply
lucaperes
New Contributor III
  • 3 kudos

Hello @JN_Bristol,I discovered that ai_parse_document only works when the input is parsed as real Python bytes.The binaryFile format in Spark returns the content as an internal binary type (like a memoryview), and ai_parse_document can’t process that...

  • 3 kudos
5 More Replies
Sujitha
by Databricks Employee
  • 30814 Views
  • 19 replies
  • 34 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
  • 30814 Views
  • 19 replies
  • 34 kudos
Latest Reply
Poorva21
New Contributor II
  • 34 kudos

This is an exciting step forward from Databricks! Looking forward to diving into the curriculum and exploring what's next in the world of data + AI! Thanks for sharing @Sujitha 

  • 34 kudos
18 More Replies
Daya3189
by New Contributor II
  • 182 Views
  • 1 replies
  • 1 kudos

Databricks app services

Hi- I have built node.js based chatbot app that uses Azure OpenAI API to build connection and get query answers from it. I am using my organization deployed API on azure that requires cert.pem and cacert.pem certificates to authenticate. everything i...

  • 182 Views
  • 1 replies
  • 1 kudos
Latest Reply
stbjelcevic
Databricks Employee
  • 1 kudos

Hi @Daya3189 , Your local system likely has the organization's certificates installed in the Windows/Mac system trust store, which Node.js (or your browser) can read. On Databricks, the app runs in a secure, isolated Linux container. It has no knowle...

  • 1 kudos
andcch552
by New Contributor
  • 130 Views
  • 1 replies
  • 0 kudos

Slow Delta write when creating embeddings with mapPartitions

I’m trying to generate 35k+ embeddings in Databricks. What I’ve tried so far:Per-row UDF (very slow).Replaced UDF with rdd.mapPartitions to batch API calls, create one Azure client per partition, and call client.embed_documents(texts) in batches. Thi...

  • 130 Views
  • 1 replies
  • 0 kudos
Latest Reply
bianca_unifeye
Contributor
  • 0 kudos

HiYou’ve optimised the embedding side really nicely already, batching in mapPartitions and creating one Azure client per partition is exactly what we recommend.For 35k rows, if embedding is fast but the Delta write/commit is slow, it’s almost always ...

  • 0 kudos
rajcoder
by New Contributor II
  • 425 Views
  • 3 replies
  • 3 kudos

Issue with ai_parse_document Not Extracting Text from Images in PDF

Hello Team,I hope you are doing well.I am a student currently exploring Databricks and learning how to work with the "ai parse document" function. While experimenting, I encountered a couple of issues related to text extraction from images inside PDF...

  • 425 Views
  • 3 replies
  • 3 kudos
Latest Reply
rajcoder
New Contributor II
  • 3 kudos

Thank you for your reply!Yes, I have gone through your article — it explains very well how to extract text content from PDFs. However, I am facing a different issue.In my case, the PDF contains multiple images and paragraphs, but "ai_parse_document" ...

  • 3 kudos
2 More Replies
Suheb
by Contributor
  • 112 Views
  • 1 replies
  • 0 kudos

What is the difference between full fine-tuning, LoRA, and p-tuning on Databricks?

How are these three methods different?Full Fine-TuningLoRAP-Tuning

  • 112 Views
  • 1 replies
  • 0 kudos
Latest Reply
saurabh18cs
Honored Contributor II
  • 0 kudos

Hi @Suheb Summary Table:Method What’s Tuned Speed/Cost Flexibility Use CaseFull Fine-TuningAll model weightsSlow/HighMaximumCustom tasks, large dataLoRASmall adapter layersFast/LowHighEfficient adaptationp-tuningPrompt embeddingsFastest/LowLimitedPro...

  • 0 kudos

Join Us as a Local Community Builder!

Passionate about hosting events and connecting people? Help us grow a vibrant local community—sign up today to get started!

Sign Up Now