Contents Menu Expand Light mode Dark mode Auto light/dark mode
AutoGluon-RAG 0.1 documentation
Light Logo Dark Logo

Tutorials

  • RAG
    • Usage
    • Data Processing Module
      • Using AutoGluon-RAG to obtain processed data from documents/websites
    • Embedding Module
      • Using AutoGluon-RAG to generate embeddings
      • Set max tokens for AWS Bedrock Embedding Models
    • Vector DB Module
      • Optimizing FAISS for large-scale data
    • Retriever Module
      • Disable the reranker and only use embedding model for retrieval
    • Generator Module
      • Change generator after initializing RAG pipeline
      • Using generator directly without retrieved context
      • Use speculative decoding for inference
      • Using Speculative Decoding in AutoGluon-RAG
    • General
      • Setting Parameters for AutoGluonRAG class through code
      • Accessing models through different services
      • Configurable parameters that can be passed into the AutoGluonRAG class
      • Using AWS resources and services

Common Errors

  • List of common errors

Evaluation

  • Evaluation Module

Resources

  • GitHub
Back to top

List of general tutorials for AutoGluon-RAG#

  1. Setting Parameters for AutoGluonRAG class through code

  2. Accessing models through different services

  3. Configurable parameters that can be passed into the AutoGluonRAG class

  4. Using AWS resources and services

Next
Setting module parameters in AutoGluonRAG.
Previous
Use speculative decoding for inference
Copyright © 2024, All authors. Licensed under Apache 2.0.
Made with Sphinx and @pradyunsg's Furo