Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation (RAG) is an architectural approach that improves the accuracy and reliability of LLM applications by grounding their outputs on external data....
DevA collection of 13 posts
Developing quality software
RAG: Deployment and Operations in Production
The final step is deploying the RAG system so that end-users or applications can consume it, and setting up an operational workflow to maintain it. We’ll discuss various deployment architectures and considerations on AWS, using NVIDIA and Databricks components....
RAG: Performance Optimization with NVIDIA TensorRT and Quantization
Large Language Models and semantic search can be resource-intensive. To deploy a responsive RAG system at scale, we need to optimize both the retrieval and generation components for latency and efficiency....
RAG: Post-Processing & Evaluation
Once the LLM generates an answer based on retrieved documents, there are a few additional steps that can enhance the quality and reliability of the RAG system: Answer Post-Processing, Evaluation and Continuous Monitoring....
RAG: LLM Integration and Generation
When it comes the generative part – using a Large Language Model to produce the final answer, augmented with the retrieved context. We need to integrate an LLM into our pipeline....
RAG: Query Handling and Document Retrieval Workflow
When a user query comes into a RAG system it must retrieve relevant documents and prepare them to feed into the LLM....