RAG

• Packages
  • {ragnar} - Helps implement Retrieval-Augmented Generation (RAG) workflows.
    • Focuses on providing a complete solution with sensible defaults, while still giving the knowledgeable user precise control over all the step
    • Designed to be transparent, so you can inspect outputs at intermediate steps
  • {rdocdump} - Dump source code, documentation and vignettes of R packages into a single file. Supports installed packages, tar.gz archives, and package source directories
    • The output is a single plain text file or a ‘character’, which is useful to ingest complete package documentation into a large language model (‘LLM’) or pass it further to other tools, such as {ragnar} to create a Retrieval-Augmented Generation (RAG) workflow.
  • {RAGFlowChainR} - Brings Retrieval-Augmented Generation (RAG) capabilities to R, inspired by LangChain. It enables intelligent retrieval of documents from a local vector store (DuckDB), enhanced with optional web search, and seamless integration with Large Language Models (LLMs).
• Resources
  • Rapid RAG Prototyping - Example using {ellmer} and DuckDB’s vss extension (See Databases, DuckDB >> Extensions >> Vector DBs
  • Fresh Stack - Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents
  • Ida Silfverskiöld articles
• Process (source)
  
• Pros
  • Context Awareness: Improves accuracy
  • Source Citation: Access to sources enhances the transparency of the responses
  • Reduces Hallucinations
  • Good for domain-specific data
• Cons
  • Latency: Response times can be problematic for real-time applications
  • An external knowledge base is required
• Use Cases: Document Querying, Coversational Agents, Personalized Recommendation, Content Generation
• Versus Fine-Tuning (source)
  
• Chunking
  • In RAG applications, the first part is about fetching the correct information, and getting it right is important because you can’t overload an agent with too much irrelevant information.
  • To make it precise the chunks need to be quite small and relevant to the search query.
  • However, if you make the chunks too small, you risk giving the LLM too little context. With chunks that are too large, the search system may become imprecise.
• Retrieval
  • Often benefits from hybrid search (supported by both Qdrant and LlamaIndex), although it may not be enough.
    • Semantic search can connect things that answer the question without using the exact wording,
    • Sparse methods can identify exact keywords. But sparse methods like BM25 are token-based by default, so plain BM25 won’t match substrings.
    • If you also want to search for substrings (part of product IDs, that kind of thing), you need to add a search layer that supports partial matches as well.