Aller au contenu
Menu
Français

Cas d'usage

RAG chatbot

A chatbot that answers from your own documents instead of from the model's memory, so answers can be traced back to a source.

Voir la pile recommandée, avec les raisons et les alternatives →

Ce qu'il faut

Dans l'ordre où vous les adopteriez. Chaque étape s'ouvre dans le graphe de connaissances.

  1. 1 LLM

    GPT

    model

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

  2. 2 Embedding

    Embedding

    concept

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

  3. 3 Vector database

    Qdrant

    database

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

  4. 4 Framework

    LangChain

    framework

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

  5. 5 Reranking

    Reranking

    technique

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