--- title: The open way of Percona Search for MongoDB | daily.dev description: Percona has launched a Technical Preview (version 1.70.3-1) of Percona Search for MongoDB, a downstream distribution of mongot — the same search engine... canonical: https://daily.dev/posts/the-open-way-of-percona-search-for-mongodb-ocg8oei4i twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The open way of Percona Search for MongoDB | daily.dev og:description: Percona has launched a Technical Preview (version 1.70.3-1) of Percona Search for MongoDB, a downstream distribution of mongot — the same search engine... og:url: https://daily.dev/posts/the-open-way-of-percona-search-for-mongodb-ocg8oei4i og:image: https://api.daily.dev/og/posts/ocg8oEi4I.png og:image:alt: The open way of Percona Search for MongoDB og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # The open way of Percona Search for MongoDB **[Percona Blog](https://daily.dev/sources/percona)** · 10 min read · 0 upvotes · 0 comments ## Summary Percona has launched a Technical Preview (version 1.70.3-1) of Percona Search for MongoDB, a downstream distribution of mongot — the same search engine powering MongoDB Atlas Search. It enables full-text and vector search for self-managed MongoDB deployments without vendor lock-in. Key gaps Percona plans to address include: expanding automatic embedding support beyond Voyage AI to any OpenAI-compatible API and eventually 25,000+ open-weight models; bringing the $rerank stage (currently Atlas-only) to self-managed deployments starting with BAAI/bge-reranker-large; adding contextual chunking and multimodal pipeline support; automating search-index backups via Percona Backup for MongoDB; and shipping turnkey monitoring dashboards and alert rules via Percona Monitoring and Management. The release requires Percona Server for MongoDB 8.3 and is not yet production-ready. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What embedding models does automatic embedding support in MongoDB's self-managed mongot search release? Automatic embeddings (the autoEmbed index type) currently work only with Voyage AI models: voyage-4-large, voyage-4, voyage-4-lite, and voyage-code-3. No other embedding providers are supported yet in the self-managed GA release of mongot, MongoDB's full-text and vector search engine. _Track which embedding providers get added as vector search options evolve, via daily.dev._ ### Is the $rerank stage available for self-managed MongoDB deployments? No, the $rerank stage that reranks vector search candidates for better relevance is available only on MongoDB Atlas, not for self-managed deployments running mongot directly. Percona has stated an intention to open reranking with BAAI/bge-reranker-large, a cross-encoder model released under the MIT license on Hugging Face, but this is a roadmap item, not shipped. _Compare cloud-only versus self-hosted retrieval features on daily.dev before committing to a search stack._ ### What is Percona Search for MongoDB and what version does it require? Percona Search for MongoDB is Percona's downstream, source-available distribution of mongot, the search engine powering MongoDB Atlas Search, released as a Technical Preview at version 1.70.3-1. It requires Percona Server for MongoDB 8.3, itself a Technical Preview, which carries the $search, $searchMeta, $vectorSearch, $rankFusion, and $scoreFusion stages. It is not recommended for production yet. _Follow self-hosted MongoDB search tooling as it matures from preview to production on daily.dev._ ## Similar posts on daily.dev - [Percona Server for MongoDB 8.3 Technical Preview Is Now Available](https://daily.dev/posts/percona-server-for-mongodb-8-3-technical-preview-is-now-available-pmrazupg9) · Percona Blog · 1 upvotes · 0 comments - [MongoDB releases mongot source code to boost RAG and AI workloads](https://daily.dev/posts/mongodb-releases-mongot-source-code-to-boost-rag-and-ai-workloads-ycyvr9ct2) · InfoWorld · 0 upvotes · 0 comments - [MongoDB Introduces Embedding and Reranking API on Atlas](https://daily.dev/posts/mongodb-introduces-embedding-and-reranking-api-on-atlas-ow0bpzewc) · InfoQ · 0 upvotes · 0 comments - [Exploring MongoT](https://daily.dev/posts/exploring-mongot-hhqr4opaw) · Foojay.io · 1 upvotes · 0 comments - [MongoDB targets AI’s retrieval problem](https://daily.dev/posts/mongodb-targets-ai-s-retrieval-problem-fdiya16um) · InfoWorld · 0 upvotes · 0 comments --- Tags: [#mongodb](https://daily.dev/tags/mongodb), [#vector-search](https://daily.dev/tags/vector-search), [#embeddings](https://daily.dev/tags/embeddings), [#full-text-search](https://daily.dev/tags/full-text-search) [View this post on daily.dev](https://daily.dev/posts/the-open-way-of-percona-search-for-mongodb-ocg8oei4i) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"The open way of Percona Search for MongoDB","url":"https://daily.dev/posts/the-open-way-of-percona-search-for-mongodb-ocg8oei4i","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-open-way-of-percona-search-for-mongodb-ocg8oei4i"},"datePublished":"2026-08-07T15:24:45.829Z","dateModified":"2026-09-14T06:05:11.987Z","description":"Percona has launched a Technical Preview (version 1.70.3-1) of Percona Search for MongoDB, a downstream distribution of mongot — the same search engine...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bea1e9c9baa56c8ab614f82d57749715?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bea1e9c9baa56c8ab614f82d57749715?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Percona Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Percona Blog","logo":"https://media.daily.dev/image/upload/s--Lb3XkBh3--/f_auto,q_auto/v1780213412/logos/percona?_a=BAMAMiWQ0","url":"https://daily.dev/sources/percona"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-open-way-of-percona-search-for-mongodb-ocg8oei4i","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"mongodb,vector-search,embeddings,full-text-search","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Percona Blog","item":"https://daily.dev/sources/percona"},{"@type":"ListItem","position":3,"name":"The open way of Percona Search for MongoDB"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-open-way-of-percona-search-for-mongodb-ocg8oei4i#faq","mainEntity":[{"@type":"Question","name":"What embedding models does automatic embedding support in MongoDB's self-managed mongot search release?","acceptedAnswer":{"@type":"Answer","text":"Automatic embeddings (the autoEmbed index type) currently work only with Voyage AI models: voyage-4-large, voyage-4, voyage-4-lite, and voyage-code-3. No other embedding providers are supported yet in the self-managed GA release of mongot, MongoDB's full-text and vector search engine. Track which embedding providers get added as vector search options evolve, via daily.dev."}},{"@type":"Question","name":"Is the $rerank stage available for self-managed MongoDB deployments?","acceptedAnswer":{"@type":"Answer","text":"No, the $rerank stage that reranks vector search candidates for better relevance is available only on MongoDB Atlas, not for self-managed deployments running mongot directly. Percona has stated an intention to open reranking with BAAI/bge-reranker-large, a cross-encoder model released under the MIT license on Hugging Face, but this is a roadmap item, not shipped. Compare cloud-only versus self-hosted retrieval features on daily.dev before committing to a search stack."}},{"@type":"Question","name":"What is Percona Search for MongoDB and what version does it require?","acceptedAnswer":{"@type":"Answer","text":"Percona Search for MongoDB is Percona's downstream, source-available distribution of mongot, the search engine powering MongoDB Atlas Search, released as a Technical Preview at version 1.70.3-1. It requires Percona Server for MongoDB 8.3, itself a Technical Preview, which carries the $search, $searchMeta, $vectorSearch, $rankFusion, and $scoreFusion stages. It is not recommended for production yet. Follow self-hosted MongoDB search tooling as it matures from preview to production on daily.dev."}}]} ```