- 3827 Views
- 3 replies
- 1 kudos
I am struggling on complicated RAG code for Mosaic evaluation deployment
I want to know how I can apply some complicated RAG designs so I can directly deploy on the Mosaic AI evaluation UI. There are two cases:1. two or more index retrieval as independent tools (parallel retrievals)2.two index retrieval processes that dep...
- 3827 Views
- 3 replies
- 1 kudos
- 1 kudos
Hi @wind2025, for Mosaic RAG setups:Parallel retrievals: independent retrievers feeding one or multiple LLMs.Linear retrievals: chain retrievers so output of one filters the next.Independent RAG chains: define separate chains and register both as too...
- 1 kudos
- 4266 Views
- 1 replies
- 1 kudos
Resolved! Error when logging artifact OSError: [Errno 5] Input/output error: '/dbfs/Volumes'
Hi, I'm building an streamlit application on databricks apps, where user can upload some data , and I run an LLM model and return results. There, I want to log an artifact to a volume. I'm following this documentation https://docs.databricks.com/aws...
- 4266 Views
- 1 replies
- 1 kudos
- 1 kudos
The error text OSError: [Errno 5] Input/output error: '/dbfs/Volumes' occurs because Databricks Apps (including Streamlit apps running on Databricks) currently do not have direct write access to /dbfs/Volumes for artifact logging via M...
- 1 kudos
- 1324 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...
- 1324 Views
- 3 replies
- 0 kudos
- 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
- 2426 Views
- 2 replies
- 0 kudos
Retrieved Docs in Message History
Hi,I've deployed a Langchain model via MLFlow log model and a deployment agent (following this https://notebooks.databricks.com/demos/llm-rag-chatbot/index.html#)How do I add additional content to the message history for example, I'd like to add retr...
- 2426 Views
- 2 replies
- 0 kudos
- 0 kudos
Hi @davidhuang thanks for pointing to that demo! That implementation of chat history did work in my experience, but it's a little simplistic and could be token-intensive if the history needs to be maintained as a list like that. Has Databricks done a...
- 0 kudos