Movatterモバイル変換

[0]ホーム
URL:

Loading
  1. Elastic Docs/
  2. Solutions and use cases/
  3. Search use case

RAG

Retrieval Augmented Generation (RAG) is a technique for improving language model responses by grounding the model with additional, verifiable sources of information. It works by first retrieving relevant context from an external datastore, which is then added to the model’s context window.

RAG is a form ofin-context learning, where the model learns from information provided at inference time. Compared to fine-tuning or continuous pre-training, RAG can be implemented more quickly and cheaply, and offers several advantages.

RAG sits at the intersection of information retrieval and generative AI

RAG sits at the intersection ofinformation retrieval and generative AI. Elasticsearch is an excellent tool for implementing RAG, because it offers various retrieval capabilities, such as full-text search, vector search, and hybrid search, as well as other tools like filtering, aggregations, and security features.

Implementing RAG with Elasticsearch has several advantages:

  • Improved context: Enables grounding the language model with additional, up-to-date, and/or private data.
  • Reduced hallucination: Helps minimize factual errors by enabling models to cite authoritative sources.
  • Cost efficiency: Requires less maintenance compared to fine-tuning or continuously pre-training models.
  • Built-in security: Controls data access by leveraging Elasticsearch'suser authorization features, such as role-based access control and field/document-level security.
  • Simplified response parsing: Eliminates the need for custom parsing logic by letting the language model handle parsing Elasticsearch responses and formatting the retrieved context.
  • Flexible implementation: Works with basicfull-text search, and can be gradually updated to add more advanced and computationally intensivesemantic search capabilities.

The following diagram illustrates a simple RAG system using Elasticsearch.

Components of a simple RAG system using Elasticsearch

The workflow is as follows:

  1. The user submits a query.
  2. Elasticsearch retrieves relevant documents using full-text search, vector search, or hybrid search.
  3. The language model processes the context and generates a response, using custom instructions. Examples of custom instructions include "Cite a source" or "Provide a concise summary of thecontent field in markdown format."
  4. The model returns the final response to the user.
Tip

A more advanced setup might include query rewriting between steps 1 and 2. This intermediate step could use one or more additional language models with different instructions to reformulate queries for more specific and detailed responses.

Building RAG applications

You can build RAG applications with Elasticsearch by retrieving relevant context from your indices and passing it to a language model. The basic approach works across all deployment types, solutions, and project types:

  1. Use Elasticsearch search capabilities (full-text, vector, semantic, or hybrid search) to retrieve relevant documents
  2. Pass the retrieved content as context to your language model
  3. The language model generates a response grounded in your data

Core search options

ES|QLCOMPLETION command: Use theCOMPLETION command to send prompts and context directly to language models within your ES|QL queries.

Agent Builder: Create AI agents that can search your Elasticsearch indices, use tools, and maintain conversational context. Agent Builder provides a complete framework for building stateful RAG applications. Learn more in theAgent Builder documentation.

Custom implementation: Retrieve documents using any Elasticsearchsearch approach (Query DSL, ES|QL, or retrievers), then integrate with your choice of language model provider in your application's code using their APIs or SDKs.

Elasticsearch solution UI tools

If you're using the Elasticsearch solution or serverless project type, these additional tools enable RAG workflows:

Playground: Build, test, and deploy RAG interfaces with a UI that automatically selects retrieval methods and provides full control over queries and model instructions. Download Python code to integrate with your applications. Learn more in thePlayground documentation.

Learn more

Learn more about building RAG systems using Elasticsearch in these blog posts:

[8]ページ先頭
©2009-2026 Movatter.jp