Multi Index Query Orchestration With Hybrid Retrieval Strategies

via “query orchestration engine”

Data framework for RAG and agents — 160+ data connectors, vector/keyword/graph indexing, query engines.

Unique: The event-driven architecture allows for real-time query management, adapting to changes in data sources and user requests dynamically.

vs others: More adaptable than static query systems found in other frameworks like Langchain.

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 “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 “multi-index query orchestration with hybrid retrieval strategies”

LlamaIndex is the leading document agent and OCR platform

Unique: Implements composable QueryEngine routers that can combine vector, keyword, graph, and structured queries through a unified interface with pluggable result merging strategies. Unlike LangChain's retriever composition (which chains retrievers sequentially), LlamaIndex's QueryEngine supports parallel multi-index querying with configurable fusion algorithms.

vs others: Enables true hybrid search with automatic result normalization and ranking, whereas LangChain requires manual result merging and score normalization across different retriever types.

via “hybrid retrieval combining vector and keyword search”

LlamaIndex starter pack for common RAG use cases.

Unique: LlamaIndex's retriever composition pattern enables pluggable fusion strategies and easy swapping of retrieval methods, whereas most RAG systems hard-code a single retrieval approach

vs others: More flexible than Elasticsearch's hybrid search because LlamaIndex's retriever abstraction decouples fusion logic from storage backend, enabling experimentation with different ranking strategies without re-indexing

via “multi-index federated search with result merging”

Lightning-fast search engine with vector search.

Unique: Implements federated search by executing queries in parallel across multiple indexes and merging results using configurable weighting, enabling cross-collection search without requiring index consolidation. Results are ranked by combined relevance scores from all indexes.

vs others: Simpler than Elasticsearch cross-cluster search because it operates on local indexes without network overhead; more flexible than Solr collection aliasing because it supports per-index weighting and dynamic index selection.

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.

via “hybrid vector + full-text search with combined ranking”

Low-cost vector database — pay-per-query, S3-backed, up to 10x cheaper at scale.

Unique: Provides native hybrid search combining vector and full-text signals in a single query without requiring application-level result merging or separate API calls, with unified ranking across both modalities within the same namespace isolation model

vs others: More efficient than querying vector and full-text search separately and merging results in application code because ranking is unified server-side, reducing latency and eliminating deduplication logic

via “fusion-retrieval-with-multi-strategy-ranking”

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

Unique: Implements Reciprocal Rank Fusion and weighted scoring to combine dense semantic retrieval with sparse keyword retrieval, allowing developers to balance semantic understanding with exact-match precision without choosing one strategy — a hybrid approach that's more robust than single-strategy retrieval

vs others: More comprehensive than pure semantic search because it captures both meaning and keywords, and more practical than pure BM25 because it includes semantic understanding; fusion is more maintainable than building a custom unified ranking function

via “multi-strategy document search with tree, metadata, semantic, and description-based retrieval”

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Unique: Implements four orthogonal search strategies (tree-based, metadata, semantic, description) all operating on the same hierarchical index, allowing composition and fallback mechanisms. Unlike vector-only systems, it provides explicit control over retrieval strategy and can combine multiple approaches for improved recall.

vs others: More flexible than single-strategy vector RAG because it supports metadata and description-based search without requiring separate indices, and allows explicit strategy composition rather than relying solely on embedding similarity.

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 “multi-index search and cross-index query federation”

A modular graph-based Retrieval-Augmented Generation (RAG) system

Unique: Enables querying multiple independent GraphRAG indexes with result aggregation and deduplication, supporting federated search scenarios without requiring index merging. Supports cost-optimized search by routing queries to appropriate indexes.

vs others: More flexible than single-index search, and more efficient than merging multiple indexes into one. Enables independent index management while supporting unified query interface.

via “hybrid-search-with-configurable-relevance-fusion”

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

Unique: Executes vector and FTS queries in parallel within the same Rust query engine, merging results using pluggable fusion strategies without materializing intermediate tables. Supports weighted sum fusion (default), reciprocal rank fusion, and extensible custom scoring via Rust plugins.

vs others: More efficient than separate vector + FTS queries because parallel execution and in-process merging avoid network overhead; more flexible than Weaviate's hybrid search because fusion weights are configurable per-query without schema changes.

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 “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 “hybrid vector and keyword indexing with efficient similarity search”

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.

Unique: Implements hybrid search through a unified query interface that abstracts over multiple index types, allowing dynamic selection of retrieval strategy (pure vector, pure keyword, or combined) at query time without re-indexing. Supports metadata filtering as a first-class retrieval primitive alongside similarity scoring.

vs others: More flexible than vector-only systems (Pinecone, Weaviate) for exact matching use cases; simpler than building separate keyword and vector pipelines. Pathway's configuration-driven approach enables switching retrieval strategies without code changes.

via “multi-index federated search with result merging”

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

Unique: Executes queries in parallel across multiple indexes and merges results using configurable weighting strategies, enabling unified search across logically separate indexes without requiring client-side aggregation or separate API calls

vs others: Simpler than Elasticsearch's cross-cluster search because Meilisearch's federated search is built into the core API and doesn't require separate cluster configuration, though less flexible for complex multi-cluster topologies

via “hybrid-search-with-configurable-fusion”

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

Unique: Implements hybrid search as a first-class SQL query primitive with query planner support, executing vector and BM25 searches in parallel and fusing results inside the database engine; unlike external fusion (e.g., LangChain), maintains transaction semantics and enables index-aware optimization.

vs others: More integrated than Elasticsearch + Pinecone because both search types share query planning and metadata; faster than sequential searches because vector and BM25 indices are queried in parallel within single transaction.

via “hybrid search combining dense and sparse retrieval”

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

Unique: Implements configurable fusion strategies (RRF, weighted sum) with per-query weight tuning, whereas most vector DBs treat hybrid search as an afterthought or require external re-ranking services

vs others: More flexible than Elasticsearch's dense_vector + text search because fusion weights are tunable per query; simpler than Vespa because it doesn't require complex ranking expressions

via “hybrid document-vector search with semantic ranking”

Local-first document and vector database for React, React Native, and Node.js

Unique: Implements dual-index hybrid search (text + vector) entirely client-side with configurable fusion strategies, whereas most local search libraries support only one modality or require separate infrastructure for each

vs others: Eliminates the need for separate Elasticsearch and vector database by unifying both search types in a single local index, reducing complexity and infrastructure costs compared to hybrid search stacks