Simple RAG Consumption with Databricks Mosaic AI > Simple RAG Consumption with Databricks Mosaic AI recipe contents > Simple RAG Consumption with Databricks Mosaic AI recipe assets
  

Simple RAG Consumption with Databricks Mosaic AI recipe assets

The following table lists the assets that the Simple RAG Consumption with Databricks Mosaic AI recipe package contains:
Asset Name
Asset Type
Description
DatabricksMosaicAIConnection
App Connection
Databricks Mosaic AI connection.
Generate Embedding Model using Databricks Mosaic AI
Process
Subprocess that parses user input to a vector view and matches it with the embedding model. It returns the matching context score and metadata.
Query LLM with Context using Databricks Mosaic AI
Process
Subprocess that prepares and sends requests to the Databricks Mosaic AI LLM model with the context.
Get Embeddings
Process
Subprocess that generates embedding vectors from the user input using Databricks Embedding Models.
Query Databricks Index
Process
Subprocess that searches for coincidences from input vectors to vectors in the Databricks Index specified as input parameters and returns a result with metadata.
Query LLM with Context using Embeddings Model
Process
The process submits a query that is received from the user, converts it into a vector, and uses it to search for similar vectors in a database. The top K matches are retrieved, filtered by a cutoff score, and used to form a context. This context including the original query is passed to a Large Language Model (LLM) to generate and return a comprehensive response.