Discussing and implementing techniques which may increase RAG performance. Part 2 of 2, focusing on querying and testing an advanced RAG pipeline.

Searching and Retrieving, Generating Answers

Enriching Queries with Synonyms

HyDE (Hypothetical Document Embedding)

Hybrid Search

Experiments

Summary of Results

Test 1: Who audits Elastic?

AdvancedRAG

SimpleRAG

Test 2:  total revenue 2023

Test 3: What product does growth primarily depend on? How much?

Test 4: Describe employee benefit plan

Test 5: Which companies did Elastic acquire?

Conclusion

Appendix

Prompts

RAG Question Answering Prompt

Elastic Query Generator Prompt

Potential Questions Generator Prompt

HyDE Generator Prompt

Sample Hybrid Search Query

Advanced RAG Techniques Part 2: Querying and Testing

Discussing and implementing techniques which may increase RAG performance. Part 1 of 2, focusing on the data processing and ingestion component of an advanced RAG pipeline.

Overview

Set-Up

Ingesting, Processing, and Embedding Documents

Data Ingestion

Sentence-level, Token-wise Chunking

Metadata Inclusion and Generation

Keyphrases extracted by TextRank

Potential questions generated by GPT-4o

Entities extracted by Spacy

Composite Multi-Field Embeddings

Indexing to Elastic

Cat Break

Definitions

Advanced RAG Techniques Part 1: Data Processing

Learn how to use LLMs to write Elastic Query DSL and query structured data with filters

Problem Statement

Solution

Prompt Design

1. Document Schema

2. Examples

3. Special Cases

4. Leniency and Coverage

Test Procedure

Test 1

Query:

Generated Elastic Query:

Results:

Test 2

Test 3

Discussion

Write Elastic Query DSL to search structured datasets

Automating traditional search with LLMs

Learn how to build an end-to-end RAG pipeline with the S3 Connector, semantic_text datatype, and Elastic Playground.

Collecting data

Setting up the S3 connector

Uploading an embedding model

Setting up your semantic_text index

Do RAG with the Elastic Playground

Query: Describe the fall from Grace of Melkor

Query: Who were the greatest students of Aule the Smith?

Build RAG with minimal code in Elastic 8.15

Build RAG quickly with minimal code in Elastic 8.15

Author

Han Xiang Choong

Articles

Advanced RAG Techniques Part 2: Querying and Testing

Advanced RAG Techniques Part 1: Data Processing

Automating traditional search with LLMs

Build RAG quickly with minimal code in Elastic 8.15