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 ...
Issue with current documentation:I wish to perform advanced RAG using langchain, in Databricks. In the documentation, they tell how to use the vector endpoint url, and index stored in catalogs. But I could not find any advanced RAG algos that are eas...
Hi allWe have just started a little mini project on using Genie and up until now, our experience is very positive. Therefore, Im interested in more documentation and learning materials other than what Databricks officially has (https://docs.databrick...
Hi @mortenhaga , since we are also looking for the same approach, is there a way that you found out or is there any reply which helped you to figure out the above problem?
I am facing issues calling the Llama Guard Model after deploying it to Model Serving on Databricks. I deployed the model by requesting instant access from Databricks Marketplace and deployed it to Model Serving.I am following the code examples here:...
@javieryw, The error you are encountering, "400 Client Error: Bad Request for url: https://westus.azuredatabricks.net/serving-endpoints/llama-guard/invocations. Response text: Bad request: json: unknown field 'dataframe_split'", indicates that the p...
I'm trying to take the quiz and get the badge for Gen AI Fundamentals, but unfortunately unable to do so as the login credentials aren't letting me in. Please advice where to find the link to take the quiz here.
I'm trying to take the quiz and get the badge for Gen AI Fundamentals, but unfortunately unable to do so as the login credentials aren't letting me in. Please advice where to find the link to take the quiz here.
I was trying to run a query on the foundational model using the example given in the document. - https://docs.databricks.com/en/machine-learning/model-serving/score-foundation-models.html But I am getting errors. Is it the issue with the version or t...
Can you share the error message that you are receiving?
Hi,I’m working with the Databricks vector store index and need to apply combined filters to retrieve chunks that meet specific criteria.My index contains the following columns: product_category, product_date, and description.Question 1: How can I re...
How do we do multiple filters? for example I want to filter a vector store by two columns with an AND logic.
Hello Databrick Support,Why is it so complex to get access to the Lab Materials after subscription. Each time I tried accessing this materials, it show a message stating "The Course has ended and no longer accessible". If this message is accurate, wh...
Did this ever get resolved? I was taking the course and then stopped for a month or so to focus on other things. Now that I'm back, I can't see the labs from within the course.
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...
The Delta table format is indeed open, which is one of its key benefits. However, the same cannot be said for vector indexes. The specifications for vector indexes are not openly available in the same way as Delta tables. Regarding the creation and...
I am currently exploring the possibility of using Databricks AI Genie to allow layman users to ask questions and retrieve data on their own.We would like to keep the data in our warehouse (e.g., Snowflake or local). I read the documentation, but it s...
I'll take a stab at "Also, how secure is Genie AI?" since I've dug into this for our own uses. There aren't many moving parts to Genie, it's really just a fine-tuned LLM and the rest is the same stuff you use in your notebooks.The most insecure part ...
Hello! I am implementing the use of a Genie Room in my company. During development, we are encountering several situations where Genie returns an empty table.I understand that an empty table is always an error—either due to a mistake in the user's qu...
I found this to be a very interesting approach.One important point to consider is that an empty result can also carry meaning. With this in mind, I provided the following instructions to Genie:When a user's query results in an empty table, first dete...
How can I efficiently handle large datasets in Databricks when performing group-by operations to avoid out-of-memory errors? Are there any best practices or optimizations for improving performance, such as partitioning or caching, especially when wor...
Hi, @maltasa I believe this article might help answer your question.Comprehensive Guide to Optimize Databricks, Spark and Delta Lake Workloads
I created a RAG application in databricks which performs the following steps:1. Extract text from PDF files2. Prepare embeddings on extracted text and create vector search index3. Create a LLM model and served the model which can answer question base...
How to unlock enterprise AI: “You can have all the AI in the world, but if it’s on a shaky data foundation, then it’s not going to bring you any value.” — Carol Clements, Chief Digital and Technology Officer, JetBlue Companies everywhere have been qu...
Must read
I am almost certain that AI/BI Genie is using Azure OpenAi under the hood. Does anyone knows if Langchain has been used too ?
Hi there,is this the correct approach to fulfil the rate limit restrictions in the foundational model API?from langchain_core.rate_limiters import InMemoryRateLimiter rate_limiter = InMemoryRateLimiter( requests_per_second=2.0, check_every_...
Hello @llmnerd, Yes, the approach you have outlined to fulfill the rate limit restrictions in the foundational model API using InMemoryRateLimiter from langchain_core appears to be correct. This setup should help you manage the rate limits effectivel...
