Machine Learning

Intelligent Search - Cross-Searching Internal Knowledge with Amazon Kendra

Learn how to build enterprise search with Amazon Kendra. Covers natural language queries, data source connectors, RAG (Retrieval-Augmented Generation) integration, and when to choose Kendra vs. OpenSearch.

約 5 分で読めます

Enterprise Search Challenges and Where Kendra Fits

Enterprise knowledge is scattered across numerous systems - S3, SharePoint, Confluence, internal wikis, FAQ sites, and databases. Traditional keyword search requires users to know the right search terms and can't handle natural language questions like "How do I apply for paid leave?" Amazon Kendra is an ML-based intelligent search service that supports 40+ data source connectors and 14 languages, understands natural language questions, and extracts answers directly from documents. For example, given the question "By when do new employees need to complete their health checkup?", Kendra identifies the relevant section in an internal policy PDF and presents the answer. While OpenSearch (Elasticsearch-based) excels at keyword matching via inverted indexes and aggregation/analytics, Kendra specializes in semantic search powered by natural language understanding (NLU) and machine learning. OpenSearch for engineers doing log analysis and metrics search, and Kendra for non-technical business users searching internal knowledge - the two are complementary.

Data Source Connectors and Index Building

Kendra provides 40+ data source connectors out of the box, enabling no-code connections to major data sources. Supported sources include S3 (PDF, Word, HTML, text), RDS/Aurora (text columns in databases), SharePoint Online, Confluence, Salesforce, ServiceNow, Google Drive, OneDrive, Slack, and GitHub. Custom connector APIs let you integrate proprietary data sources as well. Data source synchronization runs on a configurable schedule (hourly, daily, weekly), automatically reflecting new, updated, and deleted documents in the index. The ACL (Access Control List) auto-import feature pulls access permissions directly from data sources like SharePoint and Confluence, so those permissions are transparently applied to Kendra search results. Documents that User A doesn't have permission to view won't appear in their search results. This transparent access control is a critical feature for enterprise environments with strict security requirements.

Search Features and RAG Integration

Kendra returns search results in three types. Suggested Answer extracts a direct answer from a document with the relevant passage highlighted. FAQ Answer returns answers from a pre-registered FAQ database. Document returns a list of highly relevant documents, similar to traditional search results. For search tuning, you can configure field boosting (weighting specific metadata fields), faceted search (filtering by category, date, author), and synonym dictionaries (thesaurus). Kendra can serve as a retriever in Bedrock's RAG (Retrieval-Augmented Generation) pattern. Kendra searches for relevant documents in response to a user's question, then passes those documents as context to a Bedrock LLM, generating accurate answers grounded in internal knowledge. Kendra's high-precision search results directly improve RAG answer quality. To understand Kendra's model design, related books on Amazon can be helpful.

Pricing and Edition Selection

Kendra offers two editions: Developer Edition and Enterprise Edition. Developer Edition costs $1.125 per hour (approximately $810/month) and supports up to 5 indexes, 40,000 documents, and 4,000 queries per day. It's suitable for development/testing environments and small-scale internal search. Enterprise Edition costs $1.40 per hour (approximately $1,008/month) and supports up to 5 indexes, 500,000 documents, and 8,000 queries per day, with high availability (multi-AZ). Additional document storage and query capacity can be purchased on demand. To reduce costs, you can control index uptime by stopping indexes during nights and weekends. Compared to OpenSearch Serverless, Kendra offers superior natural language search accuracy but at a higher cost. If your search targets are structured log data, OpenSearch is the better fit; for unstructured internal documents, Kendra is the rational choice.

Summary - Guidelines for Using Kendra

Amazon Kendra is an intelligent search service that cross-searches internal knowledge using ML-based natural language understanding. Its key strengths are 40+ data source connectors, transparent access control via ACLs, FAQ functionality, and RAG integration with Bedrock. It's most effective in scenarios where information retrieval is a business bottleneck - reducing internal helpdesk inquiries, improving knowledge management efficiency, and enhancing customer support answer quality. We recommend starting small with Developer Edition, validating the results, and then scaling up to Enterprise Edition.

Related Services

Amazon KendraAn intelligent enterprise search service powered by machine learningAmazon BedrockA fully managed generative AI service providing access to leading foundation models via APIAmazon OpenSearch ServiceA managed search and analytics service for easy log analysis and full-text search

Related Articles

Data Search and Analytics in Practice - Building Full-Text Search and Visualization with OpenSearchLearn about data search and analytics design with Amazon OpenSearch Service, including how to build an analytics foundation with full-text search, log analysis, and dashboard visualization.Generative AI Platform - Building an Enterprise AI Foundation with Amazon BedrockLearn how to build generative AI applications using Amazon Bedrock. This guide covers foundation model selection, RAG pattern implementation, safety guardrails, and SageMaker integration for designing enterprise-grade AI infrastructure.Building RAG Applications with Amazon Bedrock Knowledge Bases - Implementing Retrieval-Augmented GenerationAutomatically index documents on S3 and unify search and generation with the RetrieveAndGenerate API. Covers chunking strategy selection and safety enforcement with Guardrails.

More on This Topic

GPU-Based Machine Learning Training with AWS Batch - Cost-Efficient Large-Scale TrainingRun GPU training with your existing Docker containers, and cut costs by up to 90% using Spot Instances and checkpointing. Includes guidance on when to choose Batch over SageMaker.Using Claude on Amazon Bedrock - Model Selection, Prompt Design, and Cost OptimizationCompares the Anthropic Claude models available on Amazon Bedrock, provides model selection guidelines by use case, and covers prompt design best practices and cost optimization.Building RAG Applications with Amazon Bedrock Knowledge Bases - Implementing Retrieval-Augmented GenerationAutomatically index documents on S3 and unify search and generation with the RetrieveAndGenerate API. Covers chunking strategy selection and safety enforcement with Guardrails.Getting Started with Quantum Computing on Amazon Braket - Designing and Simulating Quantum CircuitsPrototype for free with local simulators, then run quantum circuits on IonQ and Rigetti hardware. Covers implementing VQE and QAOA with hybrid jobs.Privacy-Preserving ML with AWS Clean Rooms ML - Build Models Without Sharing DataLearn how to build lookalike models with Clean Rooms ML, apply differential privacy, and leverage the results for ad targeting.Implementing Natural Language Processing with Amazon Comprehend - Sentiment Analysis and Entity ExtractionLearn about sentiment analysis, entity extraction, and building custom classification models with Comprehend.Building Conversational Bots - Natural Conversation Interfaces with Amazon Lex and PollyLearn how to build conversational bots using Amazon Lex and Amazon Polly.Demand Forecasting - Predicting the Future from Time Series Data with Amazon ForecastInput historical time series data and related variables to automatically build ML-based demand forecasting models. This guide covers forecast accuracy evaluation metrics and patterns for leveraging forecast results through S3 and QuickSight integration.

Similar Articles and Services

Building Enterprise Search with Amazon Kendra - Natural Language Queries and FAQ Auto-ExtractionBuild an enterprise search platform that lets you search internal documents using natural language. This article covers data source connector configuration, search accuracy tuning, and RAG integration.Amazon KendraA machine learning-powered enterprise search service that returns accurate answers to natural language questionsBuilding an Enterprise AI Assistant with Amazon Q Business - Internal Knowledge Search and Workflow AutomationConnect data sources like internal documents, Confluence, and SharePoint to enable RAG-based enterprise search and question answering. Learn how to build a secure generative AI platform with guardrails and access controls.Building RAG Applications with Amazon Bedrock Knowledge Bases - Implementing Retrieval-Augmented GenerationAutomatically index documents on S3 and unify search and generation with the RetrieveAndGenerate API. Covers chunking strategy selection and safety enforcement with Guardrails.