rag-pipeline

Stars6

Forks0

UpdatedFebruary 23, 2026 at 13:32

RAG setup with Elasticsearch as the retrieval backend

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

patrykkopycinski

patrykkopycinski/elastic-cursor-plugin

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Data ScientistsComputer and Mathematical Occupations·SOC 15-2051

SKILL.md

readonly

name	rag-pipeline
description	RAG setup with Elasticsearch as the retrieval backend

RAG Pipeline with Elasticsearch

Use when the user wants to build a RAG (retrieval-augmented generation) system using Elasticsearch.

1. Prompt

Clarify: chunking strategy, embedding model, and whether they use Elasticsearch only or with an LLM.

2. Provision

Create an index with a dense_vector field and a text field for chunks.
Create an ingest pipeline with an inference processor to generate embeddings from the text field.
Or use application-side embeddings and index precomputed vectors.

3. Integrate

Bulk index document chunks (with or without pipeline). Use bulk_index for large corpora.
At query time: embed the user question (same model), then run search with a kNN query against the vector field.
Return top-k hits to the LLM as context.

4. Validate

Run a test query and verify retrieved chunks are relevant.
Suggest ELSER/sparse for keyword-style semantics if appropriate.

More from this repository

same repository

llm-eval-observatory

patrykkopycinski/elastic-cursor-plugin

Debug and analyze LLM eval runs — view traces, compare runs, investigate failures, track costs. Use when debugging @kbn/evals failures, comparing eval runs, or analyzing LLM performance.

2026-03-276

security-inbox

patrykkopycinski/elastic-cursor-plugin

Start your security session with a personalized briefing — attacks, alerts, cases, rules, threat intel. Use as the first thing when starting security work.

2026-03-276

cluster-onboarding

patrykkopycinski/elastic-cursor-plugin

Guide users from zero to a working Elastic cluster — Cloud or on-prem, connection config, first queries, and next steps.

2026-03-276

o11y-service-dashboard

patrykkopycinski/elastic-cursor-plugin

Interactive guide for creating an APM service overview dashboard — discovers service data, presents metrics, and creates a tailored dashboard.

2026-03-276

o11y-slo-setup

patrykkopycinski/elastic-cursor-plugin

Interactive guide for creating SLOs from discovered APM and metric data — identifies candidates, lets user configure targets, and creates SLOs.

2026-03-276

search-index-management

patrykkopycinski/elastic-cursor-plugin

Create, configure, and manage Elasticsearch indices — mappings, settings, templates, data streams, and lifecycle policies.

2026-03-276

name	rag-pipeline
description	RAG setup with Elasticsearch as the retrieval backend

RAG Pipeline with Elasticsearch

Use when the user wants to build a RAG (retrieval-augmented generation) system using Elasticsearch.

1. Prompt

Clarify: chunking strategy, embedding model, and whether they use Elasticsearch only or with an LLM.

2. Provision

Create an index with a dense_vector field and a text field for chunks.
Create an ingest pipeline with an inference processor to generate embeddings from the text field.
Or use application-side embeddings and index precomputed vectors.

3. Integrate

Bulk index document chunks (with or without pipeline). Use bulk_index for large corpora.
At query time: embed the user question (same model), then run search with a kNN query against the vector field.
Return top-k hits to the LLM as context.

4. Validate

Run a test query and verify retrieved chunks are relevant.
Suggest ELSER/sparse for keyword-style semantics if appropriate.