Link Search Menu Expand Document Documentation Menu
Documentation

Tutorials

Using the OpenSearch machine learning (ML) framework, you can build various applications, from implementing semantic search to building your own chatbot. To learn more, explore the following ML tutorials.

Vector search 101

Getting started with vector search

Getting started with semantic and hybrid search

Vector operations

Generating embeddings from arrays of objects

  • Platform: OpenSearch
  • Model: Amazon Titan
  • Deployment: Amazon Bedrock

Semantic search using byte-quantized vectors

  • Platform: OpenSearch
  • Model: Cohere Embed v3
  • Deployment: Provider API

Optimizing vector search using Cohere compressed embeddings

  • Platform: OpenSearch
  • Model: Cohere Embed Multilingual v3
  • Deployment: Amazon Bedrock
Semantic search

Semantic search using the OpenAI embedding model

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: OpenAI embedding
  • Deployment: Provider API

Semantic search using Cohere Embed

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Cohere Embed
  • Deployment: Provider API

Semantic search using Cohere Embed on Amazon Bedrock

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Cohere Embed
  • Deployment: Amazon Bedrock

Semantic search using Amazon Bedrock Titan

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Amazon Titan
  • Deployment: Amazon Bedrock

Semantic search using Amazon Bedrock Titan in another account

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Amazon Titan
  • Deployment: Amazon Bedrock

Semantic search using a model in Amazon SageMaker

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Custom
  • Deployment: Amazon SageMaker

Semantic search using AWS CloudFormation and Amazon SageMaker

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Custom
  • Deployment: Amazon SageMaker + CloudFormation

Semantic search using an asymmetric model

  • Platform: OpenSearch
  • Model: Hugging Face Multilingual-E5-small
  • Deployment: Local cluster

Semantic search using text chunking

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Amazon Titan Text Embeddings
  • Deployment: Amazon Bedrock
Conversational search with RAG

Conversational search using Cohere Command

  • Platform: OpenSearch
  • Model: Cohere Command
  • Deployment: Provider API
Search result reranking

Reranking search results using Cohere Rerank

  • Platform: OpenSearch
  • Model: Cohere Rerank
  • Deployment: Provider API

Reranking search results using Cohere Rerank on Amazon Bedrock

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Cohere Rerank
  • Deployment: Amazon Bedrock

Reranking search results using Amazon Bedrock models

  • Platform: OpenSearch
  • Model: Amazon Bedrock reranker models
  • Deployment: Amazon Bedrock

Reranking search results using a cross-encoder in Amazon SageMaker

  • Platform: OpenSearch
  • Model: Hugging Face MS MARCO
  • Deployment: Amazon SageMaker

Reranking search results using a reranker in Amazon SageMaker

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Hugging Face BAAI/bge-reranker
  • Deployment: Amazon SageMaker

Reranking search results by a field

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: Cohere Rerank
  • Deployment: Provider API
RAG

Retrieval-augmented generation (RAG) using the DeepSeek Chat API

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: DeepSeek Chat
  • Deployment: Provider API

RAG using DeepSeek-R1 on Amazon Bedrock

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: DeepSeek-R1
  • Deployment: Amazon Bedrock

RAG using DeepSeek-R1 in Amazon SageMaker

  • Platform: OpenSearch, Amazon OpenSearch Service
  • Model: DeepSeek-R1
  • Deployment: Amazon SageMaker
Chatbots and agents

RAG chatbot

  • Platform: OpenSearch
  • Model: Anthropic Claude
  • Deployment: Amazon Bedrock

RAG with a conversational flow agent

  • Platform: OpenSearch
  • Model: Anthropic Claude
  • Deployment: Amazon Bedrock

Build your own chatbot

  • Platform: OpenSearch
  • Model: Anthropic Claude
  • Deployment: Amazon Bedrock
Model controls

Amazon Bedrock guardrails

  • Platform: OpenSearch
  • Model: Anthropic Claude
  • Deployment: Amazon Bedrock
350 characters left

Have a question? .

Want to contribute? or .