Search unstructured Salesforce docs in Data Cloud and Einstein using RAG technology

Hands on demo showing how to search unstructured data and use it in a Generative AI use case using Data Cloud, Einstein Prompt Builder and Copilot Studio

[@shadeishere]

‍🔥This is exactly what I was looking for-talk about perfect timing! You uploaded this just as I was diving into this topic. I really appreciate the content and hope to see more!

[@dirkkoechner9631]

It would be very helpful to see how the Data Stream was configured to ingest unstructured files from S3. Data Streams seem to only support CSV and Parquet formats, what was the 'file type' used for ingesting PDF docs?

[@pengang9173]

Hello Daniel, many thanks for this video. As a non-dev type, any chance that I ask you to help point me to ressources pertaining to the AWS Lambda part of the process? If possible, the Salesforce connected-app side as well? Again, many thanks for this video and also for considering helping me out

[@shantanuy1]

We setup all the component needed to make this work and i can see PDF showing up in the Directory table of the DMO, but no chunking has happened since a day or so. Is there anyway to know if that errored out or does it take a long time for it to chunk the PDF in DC?

[@Timvoortaal]

Is the file notification function needs for an initial load too?
OR only needed when afterwards adding files?