Recommended stack

What are you building? RAG chatbot

One technology per slot, with the reason it is suggested and what to use instead.

LLM

model

Family of decoder-only Transformer language models trained with a generative objective.

Why editorial

Any capable instruction-following model works here; the retrieval step, not the model, is what makes the answers specific to your documents.

Alternatives

concept

Dense numeric vector representing the meaning of a piece of text.

Why derived from the graph

Embedding used by Qdrant

Alternatives

database

Open-source vector database written in Rust, with payload filtering.

Why derived from the graph

Qdrant uses Embedding

Alternatives

framework

Framework for composing language models with retrieval, tools and memory.

Why derived from the graph

GPT integrates with LangChain

Alternatives

technique

Second-stage ordering of retrieved candidates by a more accurate scoring model.

Why derived from the graph

Retrieve-then-rerank is the standard shape of a semantic search pipeline.

Alternatives