Data platforms · llms.txt file breakdown
Meilisearch Documentation organizes Meilisearch documentation around OpenAPI Specs.
The actual file
The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.
Showing the first 18000 characters. Load the complete file to read the remainder.
# Meilisearch Documentation
- [Welcome to Meilisearch](https://www.meilisearch.com/docs/getting_started/overview.md): Meilisearch indexes your content and makes it accessible to both humans and AI through search, conversational interfaces, and APIs.
- [First Project](https://www.meilisearch.com/docs/getting_started/first_project.md): Learn how to create your first Meilisearch Cloud project.
- [Features](https://www.meilisearch.com/docs/getting_started/features.md): Explore all Meilisearch capabilities - index your content and make it accessible to humans and AI through search, conversational interfaces, and APIs.
- [Glossary](https://www.meilisearch.com/docs/getting_started/glossary.md): Definitions of key Meilisearch concepts and search terminology including full-text search, semantic search, hybrid search, and more.
- [Good practices](https://www.meilisearch.com/docs/getting_started/good_practices.md): Best practices for formatting documents, chunking content, batching requests, and optimizing indexing performance in Meilisearch.
- [JavaScript quick start](https://www.meilisearch.com/docs/getting_started/sdks/javascript.md): Get started with Meilisearch using the JavaScript SDK in 5 minutes.
- [Python quick start](https://www.meilisearch.com/docs/getting_started/sdks/python.md): Get started with Meilisearch using the Python SDK in 5 minutes.
- [PHP quick start](https://www.meilisearch.com/docs/getting_started/sdks/php.md): Get started with Meilisearch using the PHP SDK in 5 minutes.
- [Ruby quick start](https://www.meilisearch.com/docs/getting_started/sdks/ruby.md): Get started with Meilisearch using the Ruby SDK in 5 minutes.
- [Go quick start](https://www.meilisearch.com/docs/getting_started/sdks/go.md): Get started with Meilisearch using the Go SDK in 5 minutes.
- [Rust quick start](https://www.meilisearch.com/docs/getting_started/sdks/rust.md): Get started with Meilisearch using the Rust SDK in 5 minutes.
- [Java quick start](https://www.meilisearch.com/docs/getting_started/sdks/java.md): Get started with Meilisearch using the Java SDK in 5 minutes.
- [.NET quick start](https://www.meilisearch.com/docs/getting_started/sdks/dotnet.md): Get started with Meilisearch using the .NET SDK in 5 minutes.
- [Swift quick start](https://www.meilisearch.com/docs/getting_started/sdks/swift.md): Get started with Meilisearch using the Swift SDK in 5 minutes.
- [Dart quick start](https://www.meilisearch.com/docs/getting_started/sdks/dart.md): Get started with Meilisearch using the Dart SDK in 5 minutes.
- [Instant-meilisearch](https://www.meilisearch.com/docs/getting_started/instant_meilisearch/javascript.md): Build search interfaces with instant-meilisearch and InstantSearch.
- [React quick start](https://www.meilisearch.com/docs/getting_started/instant_meilisearch/react.md): Integrate a search-as-you-type experience into your React app.
- [Vue quick start](https://www.meilisearch.com/docs/getting_started/instant_meilisearch/vue.md): Integrate a search-as-you-type experience into your Vue app.
- [Integrate a relevant search bar to your documentation](https://www.meilisearch.com/docs/getting_started/instant_meilisearch/docsearch.md): Use Meilisearch to index content in a text-heavy website. Covers installing Meilisearch, configuring a text scraper, and creating a simple front end.
- [Laravel Scout guide](https://www.meilisearch.com/docs/getting_started/frameworks/laravel.md): Learn how to use Meilisearch with Laravel Scout.
- [Strapi v4 guide](https://www.meilisearch.com/docs/getting_started/frameworks/strapi.md): Learn how to use Meilisearch with Strapi v4.
- [Ruby on Rails quick start](https://www.meilisearch.com/docs/getting_started/frameworks/rails.md): Integrate Meilisearch into your Ruby on Rails app.
- [Symfony](https://www.meilisearch.com/docs/getting_started/frameworks/symfony.md): Integrate Meilisearch with Symfony using the official bundle.
- [Model Context Protocol (MCP)](https://www.meilisearch.com/docs/getting_started/integrations/mcp.md): Search Meilisearch indexes from AI agents and LLM clients using the built-in MCP server.
- [AI SDK](https://www.meilisearch.com/docs/getting_started/integrations/ai_sdk.md): Give AI agents a Meilisearch search tool using the Vercel AI SDK and @meilisearch/ai-sdk.
- [LangChain integration](https://www.meilisearch.com/docs/getting_started/integrations/langchain.md): Use Meilisearch as a LangChain vector store for semantic search with OpenAI embeddings.
- [Firebase](https://www.meilisearch.com/docs/getting_started/integrations/firebase.md): Sync your Firestore documents to Meilisearch using the official Firebase extension.
- [Integrate Meilisearch Cloud with Vercel](https://www.meilisearch.com/docs/getting_started/integrations/vercel.md): Link Meilisearch Cloud to a Vercel Project.
- [Postman collection for Meilisearch](https://www.meilisearch.com/docs/getting_started/integrations/postman.md): Import Meilisearch's OpenAPI specification into Postman to test and debug the API with a ready-made collection.
- [Meilisearch Importer](https://www.meilisearch.com/docs/getting_started/integrations/meilisearch_importer.md): Efficiently import large CSV, NDJSON, or JSON datasets into Meilisearch using the official CLI tool.
- [Sync data to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/overview.md): Keep Meilisearch in sync with your data sources using declarative Kestra workflows.
- [Connect PostgreSQL to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/postgresql.md): Backfill and incrementally sync a PostgreSQL table into Meilisearch with Kestra.
- [Connect MongoDB to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/mongodb.md): Backfill and incrementally sync a MongoDB collection into Meilisearch with Kestra.
- [Connect Amazon S3 to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/amazon_s3.md): Backfill and event-driven sync of Amazon S3 objects into Meilisearch with Kestra.
- [Connect Kafka to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/kafka.md): Real-time indexing of a Kafka topic into Meilisearch with Kestra.
- [Connect a REST API to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/rest_api.md): Backfill and incrementally sync a REST API into Meilisearch with Kestra.
- [Migrate Elasticsearch to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/elasticsearch.md): Migrate an existing Elasticsearch index into Meilisearch with a safe, re-runnable Kestra workflow.
- [Migrate OpenSearch to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/opensearch.md): Migrate an existing OpenSearch index into Meilisearch with a safe, re-runnable Kestra workflow.
- [Connect RabbitMQ to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/rabbitmq.md): Real-time indexing of a RabbitMQ (AMQP) queue into Meilisearch with Kestra.
- [Connect Shopify to Meilisearch with Kestra](https://www.meilisearch.com/docs/getting_started/integrations/kestra/shopify.md): Backfill and incrementally sync a Shopify product catalog into Meilisearch with Kestra.
- [Capabilities overview](https://www.meilisearch.com/docs/capabilities/overview.md): Explore all Meilisearch capabilities, from full-text and semantic search to filtering, curation, analytics, and multi-tenancy.
- [Full-text search](https://www.meilisearch.com/docs/capabilities/full_text_search/overview.md): Meilisearch's full-text search returns relevant results in milliseconds with built-in typo tolerance, prefix matching, and multi-criteria ranking.
- [Your first search](https://www.meilisearch.com/docs/capabilities/full_text_search/getting_started/basic_search.md): Perform your first full-text search query in Meilisearch and understand the response format.
- [Placeholder search](https://www.meilisearch.com/docs/capabilities/full_text_search/getting_started/placeholder_search.md): Placeholder search returns results when users submit an empty query, allowing you to display default or trending content before the user types anything.
- [Search with snippets](https://www.meilisearch.com/docs/capabilities/full_text_search/getting_started/search_with_snippets.md): Return highlighted and cropped result snippets to show users exactly where their query matched in each document.
- [Phrase search](https://www.meilisearch.com/docs/capabilities/full_text_search/getting_started/phrase_search.md): Use exact phrase matching with quotes to find documents containing a specific sequence of words.
- [Configure searchable attributes](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/configure_searchable_attributes.md): Choose which document fields Meilisearch scans during a search query by setting the searchableAttributes index setting.
- [Configure stop words](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/configure_stop_words.md): Set up stop words to ignore common terms like "the", "a", and "is" during search, improving both performance and relevance.
- [Configure prefix search](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/configure_prefix_search.md): Enable or disable prefix matching to control whether Meilisearch matches partial words as the user types.
- [Configure a custom dictionary](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/configure_dictionary.md): Teach Meilisearch to treat groups of strings as a single term by supplying a supplementary dictionary of user-defined words.
- [Highlight search results](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/highlight_search_results.md): Highlight and crop matched terms in search results to help users quickly see why a document was returned.
- [Use matching strategy](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/use_matching_strategy.md): Control how Meilisearch matches query terms using the matchingStrategy parameter to balance precision and recall.
- [Configure search cutoff](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/configure_search_cutoff.md): Set a maximum search time to ensure consistent response times for large datasets.
- [Configure displayed attributes](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/configure_displayed_attributes.md): Choose which document fields appear in search results by setting the displayedAttributes index setting.
- [Configure distinct attribute](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/configure_distinct_attribute.md): Use the distinct attribute to deduplicate search results by returning only one document per unique value of a given field.
- [Paginate search results](https://www.meilisearch.com/docs/capabilities/full_text_search/how_to/paginate_search_results.md): Implement pagination for search results using offset/limit or page/hitsPerPage.
- [Relevancy](https://www.meilisearch.com/docs/capabilities/full_text_search/relevancy/relevancy.md): Relevancy refers to the accuracy of search results. If search results tend to be appropriate for a given query, then they can be considered relevant.
- [Built-in ranking rules](https://www.meilisearch.com/docs/capabilities/full_text_search/relevancy/ranking_rules.md): Built-in ranking rules are the core of Meilisearch's relevancy calculations.
- [Custom ranking rules](https://www.meilisearch.com/docs/capabilities/full_text_search/relevancy/custom_ranking_rules.md): Custom ranking rules promote certain documents over other search results that are otherwise equally relevant.
- [Ranking score](https://www.meilisearch.com/docs/capabilities/full_text_search/relevancy/ranking_score.md): Learn how Meilisearch computes the _rankingScore for each document and which index settings influence it.
- [Attribute ranking order](https://www.meilisearch.com/docs/capabilities/full_text_search/relevancy/attribute_ranking_order.md): This article explains how the order of attributes in the `searchableAttributes` array impacts search result relevancy.
- [Typo tolerance](https://www.meilisearch.com/docs/capabilities/full_text_search/relevancy/typo_tolerance_settings.md): Configure typo tolerance to control how Meilisearch handles spelling mistakes in search queries.
- [Synonyms](https://www.meilisearch.com/docs/capabilities/full_text_search/relevancy/synonyms.md): Use Meilisearch synonyms to indicate sets of query terms which should be considered equivalent during search.
- [Ranking pipeline](https://www.meilisearch.com/docs/capabilities/full_text_search/advanced/ranking_pipeline.md): Understand how Meilisearch's multi-criteria bucket sort works step by step to rank search results.
- [Performance tuning](https://www.meilisearch.com/docs/capabilities/full_text_search/advanced/performance_tuning.md): Optimize full-text search speed for large datasets with practical configuration tips ordered by impact.
- [Debug search performance](https://www.meilisearch.com/docs/capabilities/full_text_search/advanced/debug_search_performance.md): Use the showPerformanceDetails parameter to get detailed timing breakdowns for each stage of a search query.
- [Hybrid and semantic search](https://www.meilisearch.com/docs/capabilities/hybrid_search/overview.md): Combine full-text keyword search with AI-powered semantic search to deliver results that match both exact terms and meaning.
- [Getting started with AI-powered search](https://www.meilisearch.com/docs/capabilities/hybrid_search/getting_started.md): Configure an embedding model and perform your first semantic search with Meilisearch. This tutorial uses OpenAI, but Meilisearch supports many providers.
- [Which embedder should I choose?](https://www.meilisearch.com/docs/capabilities/hybrid_search/how_to/choose_an_embedder.md): How to choose the right embedding model for your use case, balancing cost, speed, quality, and specialization.
- [Use AI-powered search with user-provided embeddings](https://www.meilisearch.com/docs/capabilities/hybrid_search/how_to/search_with_user_provided_embeddings.md): This guide shows how to perform AI-powered searches with user-generated embeddings instead of relying on a third-party tool.
- [Image search with multimodal embeddings](https://www.meilisearch.com/docs/capabilities/hybrid_search/how_to/image_search_with_multimodal.md): This article shows you the main steps for performing multimodal text-to-image searches
- [Image search with user-provided embeddings](https://www.meilisearch.com/docs/capabilities/hybrid_search/how_to/image_search_with_user_embeddings.md): This article shows you the main steps for performing multimodal text-to-image searches
- [Semantic vs hybrid search](https://www.meilisearch.com/docs/capabilities/hybrid_search/advanced/semantic_vs_hybrid.md): When to use pure semantic search vs hybrid search, and how to tune the balance between keyword and vector results.
- [Document template best practices](https://www.meilisearch.com/docs/capabilities/hybrid_search/advanced/document_template_best_practices.md): This guide shows you what to do and what to avoid when writing a `documentTemplate`.
- [Custom hybrid ranking](https://www.meilisearch.com/docs/capabilities/hybrid_search/advanced/custom_hybrid_ranking.md): Tune semanticRatio and embedder weights to control how keyword and vector results are merged in hybrid search.
- [Composite embedders](https://www.meilisearch.com/docs/capabilities/hybrid_search/advanced/composite_embedders.md): Use different embedding providers for indexing and search to optimize cost, latency, and throughput independently.
- [Binary quantization](https://www.meilisearch.com/docs/capabilities/hybrid_search/advanced/binary_quantization.md): Compress embedding vectors to reduce storage and improve indexing speed while using larger, more capable models.
- [Multiple embedders](https://www.meilisearch.com/docs/capabilities/hybrid_search/advanced/multiple_embedders.md): Configure multiple embedders on a single index to combine text search, image search, and semantic search with different models.
- [Tune the `distribution` of semantic scores](https://www.meilisearch.com/docs/capabilities/hybrid_search/advanced/tune_distribution.md): Learn how to use the `distribution` embedder setting to correct `_rankingScore` values for semantic hits and surface more relevant results.
- [Configure OpenAI embedder](https://www.meilisearch.com/docs/capabilities/hybrid_search/how_to/configure_openai_embedder.md): Set up the OpenAI embedder to use models like text-embedding-3-small for semantic and hybrid search.
- [Configure Cohere embedder](https://www.meilisearch.com/docs/capabilities/hybrid_search/how_to/configure_cohere_embedder.md): Set up the Cohere embedder for semantic and hybrid search using Cohere's embedding models.
- [Configure HuggingFace embedder](https://www.meilisearch.com/docs/capabilities/hybrid_search/how_to/configure_huggingface_embedder.md): Run open-source embedding models locally with the HuggingFace embedder for semantic search without external API dependencies.
- [Configure a REST embedder](https://www.meilisearch.com/docs/capabilities/hybrid_search/how_to/configure_rest_embedder.md): Create Meilisearch embedders using any provider with a REST API
- [Semantic Search with Mistral Embeddings](https://www.meilisearch.com/docs/capabilities/hybrid_search/providers/mistral.md): This guide will walk you through the process of setting up Meilisearch with Mistral embeddings to enable semantic search capabilities.
- [Semantic Search with Gemini Embeddings](https://www.meilisearch.com/docs/capabilities/hybrid_search/providers/gemini.md): This guide will walk you through the process of setting up Meilisearch with GemMeasured from the saved file
Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.
Context architecture
1 H2 sections organize 478 parsed Markdown links. 443 links point to .md or .markdown paths; 7 link occurrences use another hostname. Linked destinations have not been recursively validated.
| H2 section | Links | UTF-8 bytes | Tokens |
|---|---|---|---|
| OpenAPI SpecsLine 447 | 16 | 956 | 263 |
Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.
Embedded material
Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.
Publisher prioritization
No H2 section named “Optional” was detected in this file.
The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.
Machine-readable routes
MCP-related text was detected in the captured file. 3 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
These are text and link observations. No MCP server connection, authentication or tool call was tested.
Index and bundle
Verified text companion
A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.
Change evidence
This capture establishes a baseline. Update frequency cannot be determined from one observation.
12 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
516bc923edaf2b4d3de84e64de4c662345fb39828975db09906896370b003e50Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.