Adaptive Rag With Query Routing And Dynamic Context Selection

via “adaptive-retrieval-with-query-routing”

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

Unique: Implements query-aware routing that dynamically selects retrieval strategies based on query characteristics, allowing different query types to use optimized methods rather than forcing all queries through a single pipeline — an adaptive approach that improves both efficiency and quality

vs others: More efficient than applying all retrieval strategies to every query (fusion) because it selects the most appropriate strategy, and more effective than single-strategy systems because it adapts to query type

via “semantic and logical routing with runnablebranch”

Everything you need to know to build your own RAG application

Unique: Uses LangChain's RunnableBranch to declaratively define conditional routing logic without imperative control flow, enabling runtime inspection and modification of routing conditions

vs others: More maintainable than hard-coded if-else routing, and more transparent than learned routing models because conditions are explicit and auditable

via “agentic-rag-pattern-with-context-engineering”

12 Lessons to Get Started Building AI Agents

Unique: Frames RAG as an agentic decision (agents decide when to retrieve) rather than a static pipeline, and explicitly teaches context engineering techniques like chat summarization and scratchpad management to handle token constraints — most RAG tutorials treat retrieval as a fixed preprocessing step.

vs others: Covers the full context lifecycle (types, management, summarization) rather than just retrieval mechanics, making it more applicable to long-running agent conversations where context budgets are critical.

via “rag-sql hybrid query routing with semantic-to-sql translation”

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

Unique: Implements intelligent semantic-to-SQL routing using Cleanlab Codex rather than rule-based heuristics, enabling context-aware decisions about which retrieval path to use based on query intent and available data sources

vs others: More accurate than regex/keyword-based routing and faster than naive dual-retrieval approaches because it makes a single intelligent routing decision upfront rather than executing both paths and merging results

via “multi-strategy rag agent selection with automatic strategy routing”

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Unique: Implements three distinct RAG agent classes (NaiveRAG, ChainOfRAG, DeepSearch) with pluggable selection via configuration, enabling strategy swapping without code changes. DeepSearch agent specifically combines parallel search with LLM-based reranking and reflection loops — a pattern optimized for reasoning models like DeepSeek-R1 and Grok-3.

vs others: Offers more granular control over reasoning strategies than monolithic RAG systems; DeepSearch agent is specifically architected for reasoning models, whereas most RAG frameworks treat all LLMs equivalently

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 query routing as a first-class pipeline component that dynamically selects retrieval strategies based on query classification, enabling cost and latency optimization without sacrificing answer quality. Supports both rule-based routing (fast, deterministic) and LLM-based routing (flexible, learned).

vs others: More sophisticated than basic RAG for high-volume systems; avoids the overhead of always retrieving context. Pathway's dataflow engine enables efficient routing without external orchestration frameworks.

via “adaptive-context-window-management”

Agentic RAG is a different beast entirely.

Unique: Uses agent reasoning to dynamically decide document inclusion and compression rather than applying fixed heuristics, enabling context-aware prioritization that adapts to query complexity and available token budget

vs others: More efficient than fixed-size context windows because the agent can exclude low-relevance documents entirely rather than padding with marginal content, reducing wasted tokens

via “query classification and routing with judger components”

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Unique: Implements query classification as a composable judger component that routes queries to different pipeline branches in ConditionalPipeline, enabling adaptive RAG — most RAG frameworks use fixed retrieval-generation strategies regardless of query characteristics

vs others: Enables query-aware optimization compared to fixed-strategy RAG, though requires additional classification infrastructure and training data

via “adaptive agentic rag with dynamic strategy selection based on query characteristics”

Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.

Unique: Implements adaptive strategy selection where agents analyze query characteristics to determine optimal processing approach, rather than using uniform strategies for all queries, enabling efficient resource utilization by matching complexity to requirements.

vs others: More efficient than fixed-strategy systems by adapting to query characteristics, and more intelligent than simple routing by using query analysis to select strategies that balance multiple optimization objectives.

via “adaptive rag with query-dependent retrieval strategy selection”

Open-source Python library to build real-time LLM-enabled data pipeline.

Unique: Dynamically selects retrieval strategy based on query analysis, eliminating need for manual strategy selection. Integrates query analysis into the retrieval pipeline, enabling intelligent routing without separate preprocessing steps.

vs others: More effective than fixed retrieval strategies because it adapts to query characteristics; more efficient than trying all strategies because it selects the best one upfront.

via “dynamic endpoint routing”

MCP server: mcp-server

Unique: Employs a context-aware routing mechanism that adapts to incoming requests, improving response accuracy and efficiency.

vs others: More adaptable than static routing systems, allowing for real-time adjustments based on user interactions.

via “dynamic request routing”

MCP server: nextcloud-mcp-server

Unique: Employs a context-aware routing mechanism that analyzes request parameters to optimize model selection, enhancing efficiency.

vs others: More efficient than static routing systems, as it reduces processing overhead by directing requests intelligently.

via “dynamic api routing based on request context”

MCP server: mcp-server

Unique: Utilizes a context-aware routing algorithm that leverages machine learning to improve routing decisions over time based on historical data.

vs others: More adaptive than static routing systems, as it learns from usage patterns to enhance model selection efficiency.

via “dynamic model routing based on input context”

mcp.jina.ai/sse

Unique: Utilizes a context-aware routing mechanism to select the best model dynamically, improving response quality.

vs others: More intelligent than static routing methods, adapting to input variations for better performance.

via “dynamic model routing based on context”

MCP server: auto_llm_routing_server

Unique: Employs a context analysis engine that evaluates input semantics to dynamically select the best model, rather than relying on static routing rules.

vs others: More adaptive than static routing solutions, as it adjusts model selection based on real-time input analysis.

via “dynamic model endpoint routing”

MCP server: amap-mcp-server

Unique: Incorporates a flexible routing engine that evaluates user intent and context to dynamically select the best model, enhancing responsiveness and relevance.

vs others: More adaptable than static routing systems, allowing for real-time adjustments based on user interactions.

via “dynamic routing for model requests”

MCP server: lee-becky-github-io

Unique: Utilizes a configurable rule-based engine for routing, allowing developers to tailor the model selection process to their specific application needs.

vs others: More adaptable than static routing solutions, as it allows for real-time adjustments based on input context.

via “dynamic api routing based on request context”

MCP server: mcp-server-251215

Unique: Utilizes configurable routing rules that analyze request context to determine the best API endpoint, enhancing efficiency in API interactions.

vs others: More adaptable than static routing systems, allowing for real-time adjustments based on request data.

via “customizable query routing”

MCP server: db-map

Unique: Features a dynamic routing engine that evaluates query characteristics in real-time, allowing for optimized database interactions.

vs others: More flexible than static routing mechanisms, as it adapts to the nature of each query rather than applying a one-size-fits-all approach.

via “dynamic api routing”

MCP server: ms-365-mcp-server

Unique: Utilizes a middleware-based approach that allows for real-time adjustments to routing logic without server restarts.

vs others: More flexible than traditional static routing methods, allowing for rapid changes in response to user needs.