Skip to main content

Tools · Runs in your browser

RAG Architecture Picker

Long-context, standard RAG, hybrid search or GraphRAG? pgvector or a dedicated vector database? Answer five questions and get a recommended design with the reasoning behind each choice — and links to the deeper write-ups in the RAG architecture guide.

  1. 1.How much content will the assistant answer from?
  2. 2.What do typical questions look like?
  3. 3.Where is the data allowed to go?
  4. 4.How fast must new or changed content show up in answers?
  5. 5.Who are the users?

0 of 5 answered — your recommendation appears when all are done.

Want this built, or reviewed?

I design and build production RAG systems end-to-end — ingestion, retrieval, evaluation, and deployment. If you have a design already, I can review it against your real data and constraints.

RAG Chatbot Development →Discuss your project

Frequently asked questions

When should I not use RAG at all?

When the whole corpus fits comfortably in the model's context window and doesn't change by the minute — a single handbook or a few policy documents. Putting the documents in the prompt, with prompt caching, is simpler and avoids retrieval misses. RAG earns its complexity once the corpus is too big or too costly to send on every request.

What is the difference between RAG, hybrid RAG and GraphRAG?

Standard RAG retrieves passages by embedding similarity. Hybrid RAG adds a keyword (BM25) index so exact terms like product codes and error messages are found too, and merges both result lists with a reranker. GraphRAG also extracts entities and relationships into a knowledge graph, so it can answer questions that connect several facts across documents.

Is pgvector good enough for production?

Yes, for most teams. Below a few million chunks pgvector performs well and keeps vectors in the same Postgres database as the rest of your data, with transactions, backups and SQL filtering. Dedicated engines like Qdrant or Pinecone pay off at tens of millions of vectors or very high query volume.

Can I build RAG without sending data to OpenAI or other cloud APIs?

Yes. Open-weight LLMs and embedding models can be served inside your own network with tools like Ollama or vLLM, with pgvector or self-hosted Qdrant for retrieval. The trade-off is running GPUs yourself and evaluating which open model answers your questions well enough.

Does this tool store my answers?

No. The recommendation is computed in your browser. Nothing you select is sent to a server or saved.