Asset Name | Asset Type | Description |
|---|---|---|
NVIDIANIMRAGConnection | App Connection | NVIDIA NIM connection. |
SlackRAGConnection | App Connection | Slack connection. |
PineconeRAGConnection | App Connection | Pinecone connection. |
Get Embeddings | Process | Subprocess that generates embedding vectors from the user input. |
Query LLM with Context using Embeddings Model | Process | Subprocess that 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. |
Generate Embeddings Model | Process | Subprocess that parses the user input into a vector view and matches it with the embedded model. It returns the matching context score and metadata. |
Query LLM with Context using NVIDIA NIM | Process | Subprocess that prepares and sends a request to the NVIDIA NIM LLM with the context. |
Query Pinecone | Process | Subprocess that searches for coincidences from input vectors to vectors in the base Pinecone index specified as input parameter Index_Host_Pinecone and returns a result with metadata. |
RAG Consumption with NVIDIA NIM | Process | The process that receives a query from Slack, searches for the relevant context in a vector database, sends both the query and the context to an LLM, and returns the generated response to the Slack channel. |