@gtconway3d@SenCoryGardner@realDonaldTrump If recent history tells us anything, GOP senators who willingly choose to be complicit in shielding Trump from his charged misdeeds, should worry what he'll do next. As he pushes our democracy closer and closer to the cliff history will record them as enablers.
8 RAG architectures for AI Engineers:
(explained with usage)
1) Naive RAG
- Retrieves documents purely based on vector similarity between the query embedding and stored embeddings.
- Works best for simple, fact-based queries where direct semantic matching suffices.
2) Multimodal RAG
- Handles multiple data types (text, images, audio, etc.) by embedding and retrieving across modalities.
- Ideal for cross-modal retrieval tasks like answering a text query with both text and image context.
3) HyDE (Hypothetical Document Embeddings)
- Queries are not semantically similar to documents.
- This technique generates a hypothetical answer document from the query before retrieval.
- Uses this generated document’s embedding to find more relevant real documents.
4) Corrective RAG
- Validates retrieved results by comparing them against trusted sources (e.g., web search).
- Ensures up-to-date and accurate information, filtering or correcting retrieved content before passing to the LLM.
5) Graph RAG
- Converts retrieved content into a knowledge graph to capture relationships and entities.
- Enhances reasoning by providing structured context alongside raw text to the LLM.
6) Hybrid RAG
- Combines dense vector retrieval with graph-based retrieval in a single pipeline.
- Useful when the task requires both unstructured text and structured relational data for richer answers.
7) Adaptive RAG
- Dynamically decides if a query requires a simple direct retrieval or a multi-step reasoning chain.
- Breaks complex queries into smaller sub-queries for better coverage and accuracy.
8) Agentic RAG
- Uses AI agents with planning, reasoning (ReAct, CoT), and memory to orchestrate retrieval from multiple sources.
- Best suited for complex workflows that require tool use, external APIs, or combining multiple RAG techniques.
Most architectures here involve some form of retrieval-time decision. But they all run on top of whatever was already indexed.
If that indexing step outputs messy chunks, every architecture inherits them. Improving it is a separate problem from the 8 above.
My co-founder wrote about a better unit for the indexing step. The technique:
- cuts corpus size by 40x.
- reduces tokens per query by 3x.
- improves vector search relevance by 2.3x.
And it doesn't alter the retrieval algorithm, the reranker, or the embedding model.
Read it below.
@rudygobert27 Touched in their house for those first six years because they didn't want my germs in their house. She turned away and never looked back.
@rudygobert27 You are not alone in this. My mother knew her family had issues with me being born but never knew how bad it was until I was six years old and after our house burnt down, at 3am, they wouldn't allow me to sleep there until morning. Learned that they had disinfected anything I'd