13 RAG chunking strategies for better retrieval
Discover 13 RAG chunking strategies that help you optimize context windows, improve retrieval precision, and boost overall RAG pipeline performance.
Maya Shin
RAG for medical data: improving healthcare AI accuracy
Discover how RAG for medical data grounds AI in trusted clinical sources to reduce hallucinations and improve healthcare outcomes.
Maya Shin
What is context distillation in AI & how does it improve LLM efficiency?
Learn what context distillation is, how it works in large language models, and why it helps reduce prompt size, cost, and latency in modern AI systems.
Maya Shin
Query rewriting for RAG: how to improve retrieval accuracy
Learn how query rewriting for RAG improves retrieval accuracy, reduces hallucinations, & boosts LLM-powered search, with practical implementation guidance.
Maya Shin
RAG guardrails: the foundation of trustworthy AI applications
Learn what RAG guardrails are, why they matter, and how to use them to reduce hallucinations, protect data, and deploy trustworthy RAG systems in production.
Maya Shin
RAG for structured data: benefits, challenges, examples, & more
Discover how RAG for structured data improves AI accuracy and how to implement it effectively.
Maya Shin
RAG reranking explained: better context, better answers
Learn what RAG reranking is, how it works, and why it’s critical for improving relevance, accuracy, and reliability in retrieval-augmented generation systems.
Maya Shin
How RAG for customer support improves accuracy at scale
Discover how RAG for customer support improves accuracy, reduces hallucinations, and powers scalable AI support systems.
Maya Shin
AI-powered workplace search: how it works, benefits, and more
Learn how AI-powered workplace search helps teams find information faster, connect siloed tools, and improve productivity across the organization.
Maya Shin
RAG-as-a-Service: what it is, use cases, providers & more
Learn what RAG-as-a-Service is, why it matters, common use cases, key benefits, and how to evaluate providers to build more accurate AI applications faster.
Maya Shin
Self-RAG explained: how self-reflective retrieval boosts AI outputs
Learn what self-RAG is, how it works, and why self-reflective retrieval-augmented generation reduces hallucinations and improves reliability in LLM systems.
Maya Shin
How to build and optimize RAG in AI for reliable answers
Learn how RAG in AI works in practice, how to improve retrieval relevance, evaluate quality, secure data, and keep results up to date in production.
Maya Shin
The challenge isn't connecting to an LLM. It's figuring out what people actually mean.
Intent understanding is where most conversational search implementations quietly fail. Here's why the translation layer between natural language and structured queries is where the real differentiation lives.
Thomas Payet
Knowledge graph vs. vector database for RAG: which is best?
Learn the key differences between knowledge graphs and vector databases for RAG, when to use each, and how to combine them for optimal results.
Maya Shin
Retrieval-Augmented Generation (RAG) for business: Full guide
Explore how RAG for business boosts AI accuracy and delivers smarter, context-driven insights.
Maya Shin
Understanding hybrid search RAG for better AI answers
Learn what hybrid search RAG is, how it blends semantic and keyword search for more accurate retrieval, and how it works, challenges, implementation & more.
Maya Shin
Naive RAG vs. advanced RAG: What are the differences?
Explore the key distinctions between naive RAG and advanced RAG, including how they differ in process, accuracy, scalability, performance & more.
Maya Shin
Retrieve and gain: Three RAG use-case patterns you can ship today
Building real RAG systems isn’t about flashy demos – it’s about shipping features that stay fast, accurate, and reliable as your product grows.
Luis Serrano
RAG vs. long-context LLMs: A side-by-side comparison
Compare the key differences between RAG and long-context LLMs. See which approach best suits your needs, where to apply them, and more.
Maya Shin
RAG indexing: Structure and evaluate for grounded LLM answers
Guide to what RAG indexing is, how it works, key strategies, when to refresh, and how to measure performance for grounded LLM answers.
Maya Shin
Semantic search vs. RAG: A side-by-side comparison
Explore the differences between semantic search and RAG. Learn when to use each, common trade-offs, benefits, evaluations, and more.
Maya Shin
RAG vs. prompt engineering: choosing the right approach for you
Explore the key differences between RAG and prompt engineering. See which approach best suits your needs, where to apply them, and more.
Maya Shin
GraphRAG vs. Vector RAG: Side-by-side comparison guide
A practical guide comparing GraphRAG and Vector RAG – how they work, key differences, pros/cons, top tools, and when to combine them for better answers.
Maya Shin
Introducing Meilisearch Chat: conversational search for your data
Introducing Meilisearch Chat: turn your Meilisearch index into a conversational AI with a single /chat endpoint. Faster launches, lower costs, and direct answers your users actually want.
Maya Shin
RAG vs CAG: The smarter choice for your AI stack
Discover the main differences between retrieval-augmented generation (RAG) and cache-augmented generation (CAG), and which one is best for you.
Maya Shin
How to build RAG applications using Ruby: A developer’s guide
Discover how to build RAG applications in Ruby with this developer’s guide, covering essentials, tools, step-by-step setup, and how Ruby compares to Python.
Maya Shin
How to Build RAG Applications on Rails: Step-by-Step Guide
Step-by-step guide to building RAG applications with Ruby on Rails, covering core concepts, pitfalls, and best practices for production-ready AI apps.
Maya Shin
RAG evaluation: Metrics, methodologies, best practices & more
Discover what RAG evaluation is, what methodologies, frameworks and best practices are used, how to implement it and more.
Maya Shin
Modular RAG: What it is, how it works, architecture & more
A guide to modular RAG. Discover what it is, how it works, its advantages and disadvantages, how to implement it, and much more.
Maya Shin
![What is GraphRAG: Complete guide [2026]](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fmeilisearch%2Fimage%2Fupload%2Fv1786462437%2Fblog%2Fcovers%2Fgraph-rag-feature-2026.png&w=3840&q=75)
What is GraphRAG: Complete guide [2026]
Discover how GraphRAG improves traditional RAG by using graph-based reasoning to deliver more accurate, explainable, and context-rich AI responses.
Maya Shin
What is agentic RAG? How it works, benefits, challenges & more
Discover what agentic RAG is, how it works, the benefits, the challenges, the drawbacks, common tools used in agentic RAG pipelines & much more.
Maya Shin
From RAG to riches: Building a practical workflow with Meilisearch’s all-in-one tool
Walk through a practical RAG workflow with Meilisearch – query rewriting, hybrid retrieval, and LLM response generation – simplified by a single, low-latency platform.
Luis Serrano
Adaptive RAG explained: What to know in 2026
Learn how adaptive RAG improves retrieval accuracy by dynamically adjusting to user intent, query type, and context, ideal for real-world AI applications.
Maya Shin
Speculative RAG: A faster retrieval-augmented generation
Discover how speculative RAG improves traditional RAG with faster drafts, smarter retrieval, and better performance for advanced AI workflows.
Maya Shin
Corrective RAG (CRAG): Workflow, implementation, and more
Learn what Corrective RAG (CRAG) is, how it works, how to implement it, and why it improves accuracy in retrieval-augmented generation workflows.
Maya Shin
14 types of RAG (Retrieval-Augmented Generation)
Discover 14 types of RAG (Retrieval-Augmented Generation), their uses, pros and cons, and more.
Maya Shin
![9 advanced RAG techniques to know & how to implement them [2026]](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fmeilisearch%2Fimage%2Fupload%2Fv1766418889%2Fblog%2Fcovers%2Frag-techniques-feature.png&w=3840&q=75)
9 advanced RAG techniques to know & how to implement them [2026]
Discover 9 advanced RAG techniques for 2026 and learn which tools can help you implement them.
Maya Shin
![10 best RAG tools and platforms: full comparison [2026]](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fmeilisearch%2Fimage%2Fupload%2Fv1785940851%2Fblog%2Fcovers%2Frag-tools-feature-2026.png&w=3840&q=75)
10 best RAG tools and platforms: full comparison [2026]
Discover 10 of the best RAG tools for 2026, with key features, pricing, pros and cons (based on real users), integrations, and more.
Maya Shin
What is RAG (Retrieval-Augmented Generation) & how it works?
A complete guide to RAG (Retrieval-Augmented Generation). Learn what it is, how it works, the different RAG types, the components of a RAG system & more.
Maya Shin
Mastering RAG: unleashing precision and recall with Meilisearch's hybrid search
Learn how to enhance LLM accuracy using Retrieval Augmented Generation (RAG) with Meilisearch's hybrid search capabilities. Reduce hallucinations and improve search relevance.
Luis Serrano
How do you search in a database with LLMs?
Discover how do you search in a database with LLM using MCP, RAG, and SQL translation. Unlock fast, natural language access to your business data now!
Quentin de Quelen
Multimodal RAG: A simple guide
Discover how multimodal RAG transforms search by unifying text, images, audio, and video. Learn to build smarter, human-like AI experiences today.
Quentin de Quelen
LlamaIndex RAG tutorial: step-by-step implementation
Build smarter AI search with LlamaIndex RAG. Learn step-by-step how to create, optimize, and scale reliable retrieval-augmented generation systems.
Quentin de Quelen
Fine-tuning vs RAG: Choosing the right approach
Explore the key differences between fine-tuning and RAG. Find out which approach best suits your needs and learn how to improve performance, accuracy, and cost.
Quentin de Quelen
How to build a RAG pipeline: А step-by-step guide
Learn how to build a RAG pipeline to boost AI accuracy, reduce hallucinations, and deliver reliable, real-time answers. Start building smarter AI today!
Quentin de Quelen
Why traditional hybrid search falls short (and how we fixed it)
Meilisearch's innovative scoring system revolutionizes hybrid search by properly combining full-text and semantic search, delivering more relevant results than traditional rank fusion methods.
Louis Dureuil
🚀 How we're making AI work at Meilisearch
Struggling to make AI truly valuable at your company? Discover how we turned scattered AI usage into systematic success at Meilisearch, with a practical framework you can implement today.
Gillian McAuliffe
Why you shouldn't use vector databases for RAG
The contrarian take on building better retrieval augmented generation systems.
Thomas Payet
![AI-powered search: What you need to know [2026]](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fmeilisearch%2Fimage%2Fupload%2Fv1766418744%2Fblog%2Fcovers%2Fai-powered-search-feature.png&w=3840&q=75)
AI-powered search: What you need to know [2026]
Unlock the power of AI-powered search for your SaaS business. Learn key features, budgeting tips, and implementation strategies to boost user engagement
Maya Shin
![The 10 best AI enterprise search tools and platforms [2026]](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fmeilisearch%2Fimage%2Fupload%2Fv1766418743%2Fblog%2Fcovers%2Fai-enterprise-search-feature.png&w=3840&q=75)
The 10 best AI enterprise search tools and platforms [2026]
Discover the ten best AI tools for enterprise search in 2026. See how they compare in terms of features, capabilities, use cases, pricing, and more.
Maya Shin
Building the future of search with Meilisearch AI
We're transforming how developers build search with Meilisearch AI. No more complex infrastructure – just powerful, intelligent search that works out of the box.
Quentin de Quelen
![What are vector embeddings? A complete guide [2026]](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fmeilisearch%2Fimage%2Fupload%2Fv1766418936%2Fblog%2Fcovers%2Fwhat-are-vector-embeddings-feature.png&w=3840&q=75)
What are vector embeddings? A complete guide [2026]
Discover what you need to know about vector embeddings. See what they are, the different types, how to create them, applications, and more.
Carolina Ferreira
![How to choose the best embedding model for semantic search [2026]](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fmeilisearch%2Fimage%2Fupload%2Fv1766418762%2Fblog%2Fcovers%2Fchoosing-the-best-model-for-semantic-search-feature.png&w=3840&q=75)
How to choose the best embedding model for semantic search [2026]
Discover the best embedding model for semantic search in 2026. See our model performance, cost, and relevancy comparison for building semantic search.
Maya Shin
![What is a vector database? What you need to know [2026]](/_next/image?url=https%3A%2F%2Fres.cloudinary.com%2Fmeilisearch%2Fimage%2Fupload%2Fv1766418937%2Fblog%2Fcovers%2Fwhat-is-a-vector-database-feature.png&w=3840&q=75)
What is a vector database? What you need to know [2026]
Discover what you need to know about vector databases. See what they are, how they work, their benefits, examples, use cases, and more.
Carolina Ferreira
What is latent semantic indexing (LSI) and how does it work?
Learn how LSI works under the hood, see a practical Python implementation, and discover why this foundational technique remains relevant in today's AI-driven search landscape.
Maya Shin
How we made Meilisearch talk to AI: introducing our MCP server
We've built a bridge between Meilisearch and AI assistants using the Model Context Protocol (MCP), enabling developers to manage search infrastructure through natural language.
Thomas Payet
Building a RAG system with Meilisearch: a comprehensive guide
Discover best practices for building a RAG system, with tips on optimizing documents, integrating AI, and why effective retrieval is key to success.
Carolina Ferreira
Software engineering predictive search: a complete guide
Learn how to implement predictive search in your software applications. Discover key concepts, optimization techniques, and real-world examples.
Quentin de Quelen
Searching across multiple languages
Discover how easy it can be to implement advanced multilingual search and give your users the seamless, relevant results they deserve – regardless of language.
Quentin de Quelen
How to add AI-powered search to a React app
Build a React movie search and recommendation app with Meilisearch's AI-powered search.
Carolina Ferreira
How Meilisearch updates a database with millions of vector embeddings in under a minute
How we implemented incremental indexing in our vector store.
Tamo
Introducing hybrid search: combining full-text and semantic search for optimal balance
Meilisearch's AI journey began last summer with vector search and storage. Today, we unveil hybrid search with autogenerated embedders, advancing our AI capabilities.
Maya Shin
Meilisearch expands search power with Arroy's Filtered Disk ANN
How we implemented Meilisearch filtering capabilities with Arroy's Filtered Disk ANN
Clément Renault
Multithreading and Memory-Mapping: Refining ANN performance with Arroy
Overcoming the challenges to enhance ANN performance with Rust.
Clément Renault
Hugging Face facilitates AI accessibility with Meilisearch
Meilisearch powers the discovery of 2M AI models, datasets, and demos in the Hugging Face repository.
Maya Shin
Introducing Meilisearch's vector search and vector database to navigate the future of search
This release introduces semantic and hybrid search capabilities to further enhance the search experience.
Maya Shin
Vector storage is coming to Meilisearch to empower search through AI
We're thrilled to release vector storage for Meilisearch to bring fast, relevant search to AI-powered applications.
Laurent Cazanove