List of required configuration parameters for the RAG Query Milvus [Technical Preview] ReadyFlow

When deploying the RAG Query Milvus [Technical Preview] ReadyFlow, you have to provide the following parameters. Use the information you collected in Prerequisites.

Table 1. RAG Query Milvus [Technical Preview] ReadyFlow configuration parameters
Parameter name Description
HuggingFace Embedding Model Specify the HuggingFace model name to use for embedding the data.

The default model is 'all-MiniLM-L12-v2'.

Milvus Access Token Specify the access token for the destination Milvus instance.
Milvus Collection Name Specify the name of the destination Milvus collection.
Milvus Instance URI Specify the URI of the destination Milvus instance.
OpenAI API Key Specify the API key used to authenticate to OpenAI.
OpenAI Model Name Specify the OpenAI model name.

The default model is 'gpt-4o-mini'.

User Query Specify the question to include in the ChatGPT prompt.