Semantic And Hybrid Retrieval With Query Expansion

via “semantic search and retrieval with query-time reranking”

<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: Abstracts retrieval strategies behind a pluggable Retriever interface, allowing developers to compose vector search, BM25, and LLM-reranking without changing application code, and supporting query-time metadata filtering across heterogeneous vector stores

vs others: More composable than LangChain's retriever chain because it separates retrieval strategy from reranking logic, enabling A/B testing of different reranking models without modifying the retrieval pipeline

via “semantic-academic-database-search-with-query-expansion”

AI agent for automated systematic literature reviews.

Unique: Implements semantic query expansion using embeddings to generate contextually relevant search variants across heterogeneous academic databases with automatic deduplication by persistent identifiers, rather than simple keyword matching or single-database search

vs others: Covers more academic databases simultaneously than Google Scholar alone and uses semantic expansion to find related papers that keyword-only searches would miss

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 “hybrid search combining vector and full-text retrieval”

Serverless embedded vector DB — Lance format, multimodal, versioning, no server needed.

Unique: Integrates full-text and vector search at the storage layer using Lance's columnar format, avoiding separate indices and enabling single-pass retrieval; combines both modalities without requiring external search engines like Elasticsearch

vs others: Simpler than Elasticsearch + vector plugin because both search modes share the same columnar storage, but less mature than Pinecone's hybrid search in terms of tuning options and performance optimization

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 “hybrid retrieval with bm25 keyword search and semantic reranking”

LlamaIndex is the leading document agent and OCR platform

Unique: Combines vector search, BM25 keyword matching, and optional semantic reranking with configurable fusion algorithms and support for multiple reranker backends. Unlike LangChain's retriever composition (which chains retrievers sequentially), LlamaIndex's hybrid retrieval merges results with configurable fusion.

vs others: Provides integrated hybrid retrieval with automatic result fusion and optional reranking, whereas LangChain requires manual retriever composition and result merging.

via “sparse-embedding-generation-for-hybrid-search”

Framework for sentence embeddings and semantic search.

Unique: Provides sparse encoder models for hybrid search, enabling combination of dense semantic embeddings with sparse keyword-aware embeddings in unified framework; differentiates by supporting both embedding types without requiring separate libraries or complex integration

vs others: More flexible than dense-only search because it combines semantic understanding with keyword matching, and simpler than building custom hybrid systems with separate dense and sparse components

via “hybrid search combining full-text and vector results”

🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.

Unique: Implements score normalization and weighted combination of BM25 and cosine similarity in a single unified query interface, allowing developers to tune the balance without maintaining separate search endpoints. Most vector databases treat hybrid search as an afterthought; Orama makes it a first-class citizen with configurable weighting.

vs others: Simpler API than Elasticsearch's hybrid search which requires separate queries and manual score combination; more flexible than Pinecone's hybrid search which uses fixed weighting algorithms.

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 “hybrid retrieval with semantic and keyword search fusion”

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Unique: Decouples semantic and keyword retrieval into independent pipelines with pluggable reranking, allowing fine-grained control over fusion strategy per knowledge base. Supports multiple reranking backends (BM25, cross-encoder models) without requiring model retraining.

vs others: More flexible than pure semantic search (handles domain jargon better) and more intelligent than keyword-only search (understands intent), with configurable reranking that adapts to domain-specific precision/recall tradeoffs.

via “semantic search and retrieval with ranking”

A data framework for building LLM applications over external data.

Unique: Implements a pluggable Retriever abstraction supporting multiple retrieval strategies (similarity, MMR, fusion, custom) that can be composed and chained. Built-in support for re-ranking via LLM or cross-encoder, and hybrid search combining dense and sparse retrieval without custom integration code.

vs others: More flexible retrieval composition than LangChain's retrievers; built-in re-ranking and fusion strategies reduce boilerplate for advanced retrieval pipelines.

via “query expansion and refinement for improved retrieval”

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 “semantic-context-retrieval-with-hybrid-search”

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

Unique: Implements hybrid search combining vector similarity with structured SQL filters, enabling queries that blend semantic relevance with temporal and categorical constraints. Supports both programmatic API and UI-based search with configurable ranking and filtering.

vs others: More powerful than vector-only search because it enables structured filtering (date range, type) combined with semantic similarity, whereas vector-only databases lack efficient categorical filtering. More intelligent than SQL-only search because it understands semantic meaning rather than just keyword matching.

via “two-stage retrieval with dense-sparse hybrid search”

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Unique: Implements parallel dense+sparse search with reciprocal rank fusion (RRF) merging in a single Qdrant query, rather than maintaining separate indices or sequentially executing searches. The VectorDatabaseManager class abstracts the hybrid search logic, enabling transparent switching between retrieval strategies without changing the agent code.

vs others: Outperforms pure dense retrieval on keyword-heavy queries and pure BM25 on semantic queries; the hybrid approach captures both signal types in a single retrieval pass, reducing latency vs sequential search strategies.

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 “hybrid semantic and full-text search with reranking”

An open source, privacy focused alternative to NotebookLM for teams with no data limits. Join our Discord: https://discord.gg/ejRNvftDp9

Unique: Implements a true hybrid search combining vector embeddings with BM25 full-text indexing and explicit reranking, rather than relying on vector-only search. This architecture allows precise keyword matching (critical for technical documentation) while maintaining semantic understanding, with configurable scoring weights to tune the balance per use case.

vs others: More sophisticated than NotebookLM's document search (semantic-only) and more flexible than Perplexity's web search (which lacks internal document indexing); comparable to enterprise search platforms like Glean but open-source and self-hostable

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