Training Example: Meilisearch – Review the Data, Give Your Score & Compare to the Real AI Evaluation

[H1] One platform to build, scale, and unify search and AI retrieval
Simplifying how teams build with search.Boost my search with AI
[IMG: Red One]
Red One2024
[IMG: Kraven the Hunter]
Kraven the Hunter2024
[IMG: Sonic the Hedgehog 3]
Sonic the Hedgehog 32024
[IMG: Amaran]
Amaran2024
[IMG: Alarum]
Alarum2025
[IMG: Star Trek: Section 31]
Star Trek: Section 312025
[IMG: Mufasa: The Lion King]
Mufasa: The Lion King2024
[IMG: Venom: The Last Dance]
Venom: The Last Dance20248 results in 0msGet startedRequest custom demo
[H2] Trusted by leading industry innovators
[H2] The next generation of search
Meilisearch is a flexible and powerful user-focused search engine that can be added to any website or application.
[IMG: Lightning fast]
[H3] Lightning fast
Search-as-you-type returns answers in less than 50 milliseconds. That's faster than the blink of an eye!
[IMG: Plug-n-play]
[H3] Plug-n-play
Deploy in a matter of minutes. Smart presets let you start searching through your data with zero configuration.
[IMG: Ultra relevant]
[H3] Ultra relevant
Take advantage of the most advanced full-text search engine with its out-of-the-box great relevancy that fits every use case.
[H2] Apps & sites
Leverage a unified information retrieval platform with AI-powered hybrid search.
Deliver fast, relevant results out-of-the-box across private or public data, in apps or websites.AppsEcommMediaEnterprise|⌘KOpen settings↵Create new projectSearch filesToggle theme
[H3] Full-text search
Leverage reliable and performant search with features like geosearch and faceting for improved relevancy.
[H3] Semantic search
Unlock deeper understanding and context in search queries for more meaningful results.
[H3] Hybrid search
Blend full-text search efficiency and semantic depth for an unparalleled search experience.
[H3] Multimodal search
Search across images, video, and audio alongside text with AI-powered embeddings.
[H3] Filtering, faceting and sorting
Build complex search interfaces with a powerful toolkit, integrating full-text and semantic search.
[H3] Vector storage
Store and retrieve vectors for advanced search, similarity queries, or RAG applications.
[H3] Federated search
Boost user experience and result relevancy by searching across multiple data sources at once.
[H3] Search analytics
Gain actionable insights and make data-driven decisions with comprehensive search analytics.
[H3] Geosearch
Deliver location-specific results by allowing users to filter and sort results based on the location.
[H2] Don't take our word for it
CarbonGraph customer spotlight
[H3] CarbonGraph consolidated its search by migrating to Meilisearch from Pinecone
Featured: Automated embeddings, Search consolidation, Straightforward setup
[IMG: CarbonGraph]
[H2] Easy to integrate
At Meilisearch, we take the developer experience to heart. That's why we work hard to make our API self-explanatory and develop our SDKs to let you concentrate on what matters the most.Documentation
[IMG: JavaScript]
JavaScript
[IMG: php]
php
[IMG: Python]
Python
[IMG: Ruby]
Ruby
[IMG: Java]
Java
[IMG: Go]
Go
[IMG: .NET]
.NET
[IMG: Dart]
Dart
[IMG: Rust]
Rust
[IMG: Swift]
Swift
[IMG: Instant meilisearch]
Instant meilisearch
[IMG: React]
React
[IMG: Vue]
Vue
[IMG: Angular]
Angular
[IMG: Rails]
Rails
[IMG: Symfony]
SymfonySee all Integrationsconst client = new MeiliSearch('http://localhost:7700', 'masterKey')
await client.index('movies').addDocuments([
{ 'id': 1, 'title': 'Carol' },
{ 'id': 2, 'title': 'Wonder Woman' },
{ 'id': 3, 'title': 'Life of Pi' },
{ 'id': 4, 'title': 'Mad Max: Fury Road' },
{ 'id': 5, 'title': 'Moana' },
{ 'id': 6, 'title': 'Philadelphia' }
])
// be aware this client is using the masterKey, it should not be used in front end

AI-powered search
[H1] Hybrid Search
Match how people actually search. Combine keyword precision with AI that understands meaning and intent.Start free trialGet custom demo|Website Performance: Make Your Site FasterLearn optimization techniques to speed up load times…semantickeywordCore Web Vitals Optimization GuideImprove LCP, FID, and CLS scores for better UX…semanticCDN and Caching Best PracticesReduce latency with edge caching strategies…semantic
[H2] Trusted by leading companies
[H2] Perfect for
Anywhere users search with both exact terms and natural language.
[H3] A custom shopping experience for every buyer
Every customer gets results tailored to their preferences. After just a few searches or clicks, shoppers see products that match their style, budget, and interests.↑ 23%Conversion rate↓ 40%Zero-result searches↑ 15%Average order valueFiltersCategoryElectronicsClothingHomeSportsPrice$0$500BrandNikeAdidasPuma|24 resultsE-commerceDocumentationSupportMediaMarketplace
[H2] Search that understands intent
When users know exactly what they want, we find it. When they're exploring, we help them discover. Meilisearch automatically detects intent and adapts.QueryIntentKeywordSemanticHybrid"Nike Air Max 90"Known itemExact match foundMay miss exactKeywordKeyword-firstSemantic"comfortable office footwear"DiscoveryFew or no resultsFinds relatedKeywordSemantic-firstSemantic"running shoes"AmbiguousExact matches onlyRelated conceptsKeywordBalancedSemantic
[H2] The best of both worlds
Keyword precision meets semantic understanding, tuned to your needs.
[H3] Understands meaning
"Affordable housing" matches "budget apartments". Find related results even when wording differs.
[H3] Tunable mix
Dial up keyword precision or semantic understanding for each use case. One setting, no code changes.
[H3] Any AI provider
Native integrations with OpenAI, Mistral, and more. Bring your own model through a simple endpoint.
[H3] Zero setup
Embeddings happen automatically when you add a document. No extra pipeline to build or maintain.
[H3] Scales to millions
Compressed vectors keep search fast and storage costs low, even with millions of documents.
[H3] Control what AI sees
Choose exactly which fields feed your AI model. Better inputs mean more accurate matches.
[H2] Works with all major embedding providers
Native integrations, no backend required for most providers.38 models from 11 providers
[H3] OpenAI
2 modelstext-embedding-3-largetext-embedding-3-small
[H3] Google
3 modelsgemini-embedding-2gemini-embedding-001text-embedding-005
[H3] Mistral AI
1 modelMistral Embed
[H3] Cohere
3 modelsEmbed 4Embed v3Embed Multilingual v3
[H3] Hugging Face
5 modelssentence-transformersall-MiniLM-L6-v2all-mpnet-base-v2e5-large-v2multilingual-e5-large
[H3] Ollama
5 modelsnomic-embed-textmxbai-embed-largebge-m3all-minilmsnowflake-arctic-embed
[H3] Together AI
1 modelBAAI bge-large
[H3] Cloudflare AI
1 modelbge-m3
[H3] Voyage AI
10 modelsvoyage-4-largevoyage-4voyage-4-litevoyage-4-nanovoyage-3.5voyage-3.5-litevoyage-multimodal-3.5voyage-code-3voyage-finance-2voyage-law-2
[H3] Jina AI
4 modelsjina-embeddings-v4jina-embeddings-v3jina-clip-v2jina-colbert-v2
[IMG: Mixedbread AI]
[H3] Mixedbread AI
3 modelsmxbai-embed-large-v1mxbai-embed-2d-large-v1mxbai-colbert-large-v1+
[H3] Custom
Any providerMeilisearch is compatible with any model offering a REST API and tool calling capabilities.
[H2] Frequently asked questions
What is hybrid search?Hybrid search combines traditional keyword search with AI-powered semantic search. Keywords find exact matches, while semantic search understands meaning and intent. Together, they deliver more relevant results than either approach alone.How do I tune the balance between keyword and semantic?Which embedding provider should I use?Does hybrid search affect performance?Do I need to manage embeddings myself?
[H2] Ready to get started?
Run Hybrid Search on Meilisearch Cloud, or self-host the open-source engine.Start free trialGet custom demo

[H2] Documentation Index
Fetch the complete documentation index at: https://www.meilisearch.com/docs/llms.txtUse this file to discover all available pages before exploring further.Meilisearch indexes your content and makes it accessible to both humans and AI. It stores your documents and embeddings, then exposes them through fast full-text search, semantic search, and conversational interfaces, all from a single API.
[H2] Start with Cloud
Get started in minutes with Meilisearch Cloud
[H2] Self-host
Deploy on your own infrastructure
[H2] ​How it works
Index once, access everywhere. You push your content to Meilisearch. It stores the documents, builds the search indexes, and when configured with an embedder, generates vector embeddings automatically. Your data becomes accessible to both end users and AI systems.
[H2] For humans
Search-as-you-type interfaces, faceted navigation, filtering, sorting, and personalized results, all in under 50ms.
[H2] For AI
Semantic search, RAG-powered conversational interfaces, and similar document retrieval so LLMs can answer questions grounded in your data.
[H2] ​What you can build
Search interfaces: instant, typo-tolerant search bars for websites, apps, and documentation.
AI assistants: connect LLMs to your content with built-in RAG. Users ask questions in natural language and get answers grounded in your data.
Recommendation systems: find similar documents and personalize results based on user preferences.
Internal tools: make company knowledge searchable across documents, databases, and APIs.
[H2] ​Why Meilisearch?
Meilisearch is built on three pillars:
[H3] ​Performance
Meilisearch is designed for speed at scale. Every query returns results in under 50 milliseconds, whether your index contains a thousand documents or tens of millions. The engine uses memory-mapped storage, multi-threaded indexing, and DiskANN-based vector search to maintain consistent performance as your data grows. Sharding and replication let you scale horizontally without sacrificing latency.
[H3] ​Relevancy
Getting the right results means combining multiple signals. Meilisearch chains seven default ranking rules (words, typo, proximity, attributeRank, sort, wordPosition, and exactness) with support for custom rules tailored to your domain. Hybrid search merges keyword and semantic results so users find what they’re looking for even when they don’t use the exact right words. Conversational search goes further: RAG-powered responses are grounded in your indexed data, so AI answers are sourced and verifiable.
[H3] ​Developer experience
Meilisearch is a single binary with a REST API. There is no cluster to configure, no schema to define, and no separate vector store to manage. Send your documents and Meilisearch handles tokenization, indexing, and vector generation through auto-embeddings. SDKs for 10+ languages, one-click deployment on Meilisearch Cloud, and sensible defaults mean you go from zero to production search in minutes, not weeks.
[H2] ​See it in action
[IMG: Search bar updating results]
Try our live demos:
E-commerce search - Browse millions of products
Where to Watch - Search the TMDB movie database
SaaS search - Multi-model search with Laravel
[H2] ​Get started with Meilisearch Cloud
Meilisearch Cloud gets you up and running in minutes with automatic scaling, updates, and maintenance. Start with a 14-day free trial.
[H2] ​Next steps
[H2] Explore features
See all Meilisearch capabilities
[H2] Good practices
Learn how to format, chunk, and index your data
[H2] Choose your SDK
Get started with your preferred language
[H2] Glossary
Key terms and concepts explainedWas this page helpful?YesNoFirst Project⌘I

Pricing
[H1] Predictable costs. Limitless scale.
Pay for what you use. Scale when you're ready.CloudStarting at$20/monthGet 14 days free trial for your project.14-day free trial, no credit card requiredUsage-based or resource-based billingFully managed Cloud infrastructureScale seamlessly from prototype to productionEmail support includedGet started for freeEnterpriseCustomMission-critical deployments with dedicated support and custom SLAs.Custom infra and dedicated resourcesUp to 99.999% uptime SLADedicated Slack support channelSSO SAML and SOC 2 complianceEnterprise-grade complianceAnalytics, Merchandizing, Personalisation, ChatContact us to get a quoteCost Estimator
[H2] Find the right instance for your workload
Estimate your monthly cost based on your documents, searches, and document size.
[H3] Not sure how to estimate?
Describe your business and we'll estimate your needsEstimate my usage
[H3] Estimate your usage
Adjust sliders to match your expected workloadMonthly documents100K10K500K10M+Monthly searches10K1K250K10M+Average document sizeSmall (1KB)Few filters, SaaS-likeMedium (3KB)Short text, ~10 filtersLarge (8KB)Articles, long documentsAI (12KB)Documents with embeddingsUsage-based$30/monthBase plan (100K docs, 50K searches)$30/moResource-based$23/monthXS instance (0.5 vCPU, 1 GB RAM)Instance$18/moDisk (32 GiB billed (2.9 GiB calculated))$5/moSee all server sizes & regions
[H2] Enterprise Benefits
Unlock premium features and support with our Enterprise plan
[H3] Slack Support
Direct access to our engineering team via dedicated Slack channel
[H3] Up to 99.999% SLA
Industry-leading availability guarantee for mission-critical applications
[H3] Volume Discounts
Significant cost savings for high-volume usage and multiple instances
[H3] SSO SAML
Enterprise-grade single sign-on with SAML 2.0 support
[H3] SOC 2 Compliance
SOC 2 Type II certified for security and compliance
[H3] Advisory Services
Dedicated customer success team and technical advisory
[H3] Advanced Analytics
Track clicks, conversions, and search performance with detailed analytics
[H3] Premium Compute
Access faster and bigger instance sizes for maximum performance
[H3] Sharding & Replication
Distribute data across shards and replicas for high availability at scale
[H3] Personalization
Adapt search results for each user based on their preferences and behavior
[H3] Dynamic Search Rules
Boost, pin, or bury results based on the context of each requestEven moreContact us to learn about all enterprise features
[H2] Frequently asked questions
Should I self-host or use Cloud?Self-hosting is free and gives you full infrastructure control, but you manage updates, backups, and scaling yourself. Cloud removes all of that. Fully managed, with automatic upgrades and email support included. Most teams start on Cloud and never need to self-host.Is there a free trial?How do I choose the right instance size?Can I self-host Meilisearch for free?I need to self-host for compliance reasons. Can I still get dedicated support?How do I get help choosing?
[H2] Still deciding?
Our team can recommend the pricing model that costs you the least as you grow.Talk to salesStart free trial