Query Expansion And Refinement For Improved Retrieval

via “multi-step reasoning search with iterative refinement”

AI search engine — direct answers with citations, Pro Search, Focus modes, research Spaces.

Unique: Implements explicit query decomposition and iterative refinement where the model generates its own follow-up searches based on intermediate results, rather than executing a single retrieval pass. This mirrors human research behavior (asking follow-up questions based on initial findings) and is architecturally distinct from single-pass RAG systems that retrieve once and generate once.

vs others: Outperforms single-pass search engines and basic RAG systems on complex research questions by dynamically identifying information gaps and filling them, whereas Google Search requires manual query reformulation and ChatGPT lacks real-time web access for iterative refinement.

via “multi-stage query transformation and expansion”

<p align="center"> <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" /> </p> <h1 align="center">LlamaIndex.TS</h1> <h3 align="center"> Data framework for your LLM application. </h3>

Unique: Implements query transformation as a composable pipeline where decomposition, expansion, and rewriting stages can be chained and combined, with built-in deduplication and result merging across multiple query variants

vs others: More flexible than LangChain's query transformation because it supports multiple transformation strategies in sequence (not just expansion), and provides automatic result merging across variants

via “query expansion and clarification with user feedback”

Advanced AI research agent with deep web search.

Unique: Generates clarifying questions proactively rather than waiting for user feedback — uses semantic analysis to detect ambiguity before searching. Allows users to select from multiple interpretations rather than forcing a single interpretation.

vs others: More interactive than ChatGPT's approach (which typically assumes one interpretation); more efficient than traditional search engines (which return results for all interpretations)

via “query rewriting for improved retrieval”

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

Unique: Integrates query rewriting as a first-class pipeline step in the LangGraph workflow rather than an optional post-processing layer, ensuring all queries benefit from optimization before retrieval and enabling conditional routing based on rewrite confidence

vs others: More transparent than implicit query expansion in vector databases because the rewritten query is visible and debuggable, allowing developers to understand and tune retrieval behavior

via “query expansion and reformulation for improved retrieval”

LangChain reference RAG implementation from scratch.

Unique: Implements query expansion using LLM-based rewriting that generates semantically equivalent query variants (e.g., 'What is X?' → 'Explain X', 'How does X work?', 'Define X'), and merges results from all variants to improve recall without requiring manual expansion rules.

vs others: More flexible than fixed expansion rules because LLM-based rewriting adapts to query content; more practical than single-query retrieval because it captures multiple valid interpretations of ambiguous queries.

via “query transformation and expansion for improved retrieval”

LlamaIndex starter pack for common RAG use cases.

Unique: LlamaIndex's query transformation modules are composable, enabling chaining of multiple transformation strategies (expansion, decomposition, rewriting) in a single pipeline, whereas most RAG systems apply a single transformation

vs others: More sophisticated than simple query expansion because LlamaIndex supports query decomposition for multi-part questions, enabling retrieval of context for each sub-question separately before synthesis

via “semantic and hybrid retrieval with query expansion”

Unified framework for building enterprise RAG pipelines with small, specialized models

Unique: Implements query expansion at retrieval time using small specialized models (SLIM models) to inject synonyms and related concepts, improving recall without expensive reranking. Hybrid retrieval combines vector similarity with keyword matching through configurable alpha weighting, enabling both semantic and exact-match queries in a single call.

vs others: Built-in query expansion via SLIM models improves recall vs static vector-only retrieval; hybrid approach handles both semantic and keyword queries vs pure vector solutions like Pinecone; integrated with llmware's small model ecosystem for on-device expansion.

via “query-transformation-and-enhancement”

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Unique: Provides implementations of HyDE and HyPE techniques that use LLMs to generate synthetic documents or passages from queries, improving retrieval without modifying the embedding model or document index — a novel approach compared to traditional query expansion

vs others: More effective than simple query expansion (synonyms, stemming) because it uses LLM understanding to generate contextually relevant synthetic documents, whereas traditional methods rely on lexical similarity

via “query expansion with multiple expansion strategies and module variants”

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

Unique: Treats query expansion as a pluggable node type with multiple competing module implementations (MultiQueryExpansion, HyDE, QueryDecomposition, etc.). Enables empirical evaluation of whether expansion helps or hurts retrieval for your specific queries and domain.

vs others: More flexible than fixed expansion strategies because multiple strategies can be tested; more transparent than black-box expansion because expansion outputs are visible; enables cost-benefit analysis because latency and accuracy impacts are measured.

via “deep-search-with-iterative-refinement”

Search the web and codebases to get precise, up-to-date context for programming and research. Find examples, API usage, and documentation from real repositories and sites to ship faster with fewer mistakes. Extend investigations with deep search, crawling, and business or profile lookups when needed

Unique: Supports search result caching and context preservation across multiple queries, allowing agents to reference previous findings when formulating follow-up searches. Enables stateful research workflows where each search builds on prior knowledge.

vs others: More effective than single-query search for complex research because it allows agents to refine understanding iteratively, similar to how human researchers conduct investigations by following leads and validating findings.

via “multi-query retrieval with llm-generated query variants”

Everything you need to know to build your own RAG application

Unique: Leverages LLM-in-the-loop query expansion with parallel retrieval and union-based deduplication, avoiding hand-crafted query expansion rules and adapting dynamically to domain-specific terminology

vs others: More effective than single-query retrieval for sparse corpora, and more flexible than static query expansion templates because the LLM adapts variants to the specific query context

via “query transformation and expansion”

A data framework for building LLM applications over external data.

Unique: Provides LLM-based query transformation as a first-class pipeline stage with support for multiple strategies (expansion, decomposition, rewriting) and pluggable custom transformers. Integrates seamlessly with retrieval pipelines to improve end-to-end relevance without manual query engineering.

vs others: More sophisticated than simple query expansion; built-in decomposition and rewriting strategies reduce manual prompt engineering compared to implementing custom LLM calls.

Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 30 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).

Unique: Integrates query expansion into the MCP server's search interface, allowing agents to benefit from improved retrieval without explicitly requesting expansion, and supporting both LLM-based and rule-based expansion strategies

vs others: More effective than single-query retrieval for complex information needs, and more efficient than requiring agents to manually reformulate queries because expansion happens transparently

via “llm-powered query refinement for dark web search optimization”

AI-Powered Dark Web OSINT Tool

Unique: Integrates domain-specific prompt engineering for dark web terminology expansion rather than generic query expansion; supports four LLM providers via unified abstraction layer (llm_utils.get_llm()) enabling provider switching without code changes, and contextualizes refinement within OSINT investigation workflows rather than generic search

vs others: Outperforms generic query expansion tools (e.g., Elasticsearch query DSL) by leveraging LLM semantic understanding of dark web marketplace conventions, payment tracking terminology, and threat actor naming patterns specific to OSINT investigations

via “context-aware query expansion”

Deepseek V4 Flash and Non-Flash Out on HuggingFace

Unique: Incorporates advanced NLU techniques to dynamically expand queries based on contextual understanding.

vs others: More contextually aware than traditional keyword-based search systems, leading to higher relevance in results.

via “contextual query refinement”

Paste in my prompt to Claude Code with an embedded API key for accessing my public readonly SQL+vector database, and you have a state-of-the-art research tool over Hacker News, arXiv, LessWrong, and dozens of other high-quality public commons sites. Claude whips up the monster SQL queries that safel

Unique: Utilizes a dynamic feedback mechanism that adapts to user interactions, enhancing the relevance of search results through contextual understanding.

vs others: Offers a more interactive and adaptive search experience compared to static query systems that do not learn from user input.

via “query expansion and semantic rewriting”

Self-learning vector database for Node.js — hybrid search, Graph RAG, FlashAttention-3, HNSW, 50+ attention mechanisms

Unique: Integrates query expansion directly into the vector search pipeline with attention-based rewriting, whereas most systems treat expansion as a separate preprocessing step

vs others: More sophisticated than simple synonym expansion because it uses semantic rewriting; simpler than building custom query understanding pipelines

via “query expansion and reformulation”

Mind engine adapter for KB Labs Mind (RAG, embeddings, vector store integration).

Unique: Combines multiple query expansion strategies (synonym generation, paraphrasing, semantic decomposition) with parallel search and result merging, improving retrieval coverage without requiring query rewriting

vs others: More effective than single-query search because it explores multiple semantic interpretations of the user's intent, improving recall for ambiguous or complex queries

via “context-aware-query-reformulation”

** - Lightning-Fast, High-Accuracy Deep Research Agent 👉 8–10x faster 👉 Greater depth & accuracy 👉 Unlimited parallel runs

Unique: Implements a feedback loop where the research agent analyzes initial findings to identify gaps and automatically generates follow-up queries that address those gaps. Uses semantic similarity and iteration limits to prevent infinite loops while maximizing coverage.

vs others: More thorough than single-query research because it autonomously expands scope based on findings rather than relying on users to identify gaps and request follow-up research.

via “query engine with multi-stage retrieval and reranking”

Interface between LLMs and your data

Unique: Implements multi-stage retrieval pipeline with pluggable rerankers and response synthesis modes, supporting query decomposition (SubQuestionQueryEngine) and routing (RouterQueryEngine) without requiring custom orchestration code. Integrates reranking as a first-class abstraction rather than post-processing.

vs others: More sophisticated than basic vector search by supporting reranking, query decomposition, and response synthesis in a unified pipeline; enables complex multi-hop queries and improves answer quality through multi-stage filtering.