Stack recomendado

¿Qué estás construyendo? RAG chatbot

Una tecnología por posición, con el motivo de la sugerencia y qué usar en su lugar.

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.

Alternativas

concept

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

Why derivado del grafo

Embedding used by Qdrant

Alternativas

database

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

Why derivado del grafo

Qdrant uses Embedding

Alternativas

framework

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

Why derivado del grafo

GPT integrates with LangChain

Alternativas

technique

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

Why derivado del grafo

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

Alternativas