Empfohlener Stack
Was bauen Sie? RAG chatbot
Eine Technologie pro Position, mit der Begründung und womit man sie ersetzen kann.
LLM
modelFamily 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.
Alternativen
Embedding
conceptDense numeric vector representing the meaning of a piece of text.
Vector database
databaseOpen-source vector database written in Rust, with payload filtering.
Framework
frameworkFramework for composing language models with retrieval, tools and memory.
Reranking
techniqueSecond-stage ordering of retrieved candidates by a more accurate scoring model.
Why aus dem Graphen abgeleitet
Retrieve-then-rerank is the standard shape of a semantic search pipeline.