{"id":7477,"date":"2026-08-19T19:10:11","date_gmt":"2026-08-19T19:10:11","guid":{"rendered":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/administration\/fournisseurs\/"},"modified":"2026-08-19T19:10:11","modified_gmt":"2026-08-19T19:10:11","slug":"fournisseurs","status":"publish","type":"wvn_doc","link":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/reference\/fournisseurs\/","title":{"rendered":"Supported providers"},"content":{"rendered":"

Supported providers<\/h1>\n

The exact list of suppliers available in your<\/strong> version is that
\nthat the settings screens display. This page provides an overview.<\/p>\n

\n

Language models<\/h2>\n

Local execution, managed by WivenLLM<\/h3>\n

A catalog of open models that the application downloads and runs
\nitself, without external dependencies. This is the only case where WivenLLM manages itself
\nthe model lifecycle.<\/p>\n

Local inference servers<\/h3>\n

The most common self-hosting solutions are supported \u2014
\ntemplate servers for both workstations and servers, including the
\nruntimes offered by hardware manufacturers. The common point: they
\nThey expose an API compatible with the OpenAI standard, and WivenLLM connects to it.
\nas a customer.<\/p>\n

Special case:<\/strong> any server exposing an OpenAI-compatible API can be
\ndeclared, even if it is not explicitly listed. It is sufficient to indicate
\nthe address.<\/p>\n

Commercial Suppliers<\/h3>\n

Major model publishers are supported, as well as platforms
\ncloud from major hosting providers and specialized suppliers
\nrapid inference.<\/p>\n

Aggregators<\/h3>\n

Gateways providing access to numerous models behind a single key are
\nalso supported, which allows you to change models without changing
\nconfiguration.<\/p>\n

European and Swiss accommodation<\/h3>\n

European providers, including a Swiss hosting company, are among the
\nintegrations \u2014 useful when a fully local solution is not feasible but the
\nlocation of treatments is important.<\/p>\n

\n

Embedding engines<\/h2>\n

Integrated<\/strong> (by default)<\/em> \u2014 runs locally, no key, no output
\nnetwork.<\/p>\n

Local<\/strong> \u2014 local inference servers exposing an embeddings service
\ncan be used.<\/p>\n

External<\/strong> \u2014 the main embedding suppliers on the market are taken in
\ncharge, as well as any service exposing an OpenAI-compatible API.<\/p>\n

\n

Reminder: changing your embedding engine invalidates existing indexes and imposes
\na complete reindexing.
\n\u2192 Vector base and embeddings<\/a><\/p>\n<\/blockquote>\n

\n

Vector bases<\/h2>\n

Integrated local base<\/strong> (by default)<\/em> \u2014 stored on disk, none
\ninfrastructure to be utilized.<\/p>\n

Self-hostable databases<\/strong> \u2014 the main open source solutions on the market
\nare supported, including the vector extension of PostgreSQL, which
\nallows you to reuse an existing database.<\/p>\n

Managed services<\/strong> \u2014 cloud offerings of the same solutions are also included
\nin charge.<\/p>\n

\n

A managed service means that your vectors and their metadata are out of your
\nperimeter.<\/p>\n<\/blockquote>\n

\n

Image generation<\/h2>\n

Local<\/strong> \u2014 an integrated engine managed by WivenLLM, as well as the servers of
\ngeneration of the most widespread self-hosted images.<\/p>\n

External<\/strong> \u2014 the main commercial image generation services.<\/p>\n

\n

Video generation<\/h2>\n

Local<\/strong> \u2014 self-hosted video generation chains and integrated engine.<\/p>\n

This function is significantly more demanding in terms of equipment and time than the
\nimage generation.<\/p>\n

\n

Text-to-speech<\/h2>\n
    \n
  • Navigator's voice (by default)<\/em> \u2014 no configuration, no output
    \n network.<\/li>\n
  • High-quality local voice, played in the browser.<\/li>\n
  • External text-to-speech services, including major publishers
    \n specialized services, as well as any service exposing an OpenAI compatible API.<\/li>\n<\/ul>\n
    \n

    Audio transcript<\/h2>\n
      \n
    • integrated motor (by default)<\/em> \u2014 runs locally, without a key.<\/li>\n
    • External transcription services.<\/li>\n<\/ul>\n
      \n

      Search engines for agents<\/h2>\n

      Web search capabilities rely on a configurable search engine.
      \nThe main search API services are supported, as well as
      \nself-hostable engines<\/strong> \u2014 which allows web searches to be maintained without
      \nto depend on a sales department.<\/p>\n

      \n

      Choosing: the question to ask yourself<\/h2>\n

      For each brick, a single question determines the choice:<\/p>\n

      \n

      Do I accept that this data is outside my scope?<\/strong><\/p>\n<\/blockquote>\n\n\n\n\n\n\n\n\n\n\n\n
      Brick<\/th>\nWhat comes out with an external supplier<\/th>\n<\/tr>\n<\/thead>\n
      Language model<\/td>\nThe messages and the documentary context<\/td>\n<\/tr>\n
      Embeddings engine<\/td>\nThe text of all indexed documents<\/strong><\/td>\n<\/tr>\n
      Vector base<\/td>\nVectors and their metadata<\/td>\n<\/tr>\n
      Transcription<\/td>\nAudio files<\/td>\n<\/tr>\n
      Text-to-speech<\/td>\nThe text of the answers<\/td>\n<\/tr>\n
      Image generation<\/td>\nThe descriptions<\/td>\n<\/tr>\n
      Web search<\/td>\nThe requests<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      The embeddings engine line is the one that's most often forgotten, and it's
      \nthe one that displays the most content.<\/p>","protected":false},"parent":7453,"menu_order":702,"template":"","meta":[],"class_list":["post-7477","wvn_doc","type-wvn_doc","status-publish","hentry"],"yoast_head":"\nFournisseurs support\u00e9s \u2014 Documentation WivenLLM<\/title>\n<meta name=\"description\" content=\"Mod\u00e8les de langage, embeddings, bases vectorielles, g\u00e9n\u00e9ration d'images et voix \u2014 la liste des int\u00e9grations disponibles.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/reference\/fournisseurs\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Fournisseurs support\u00e9s \u2014 Documentation WivenLLM\" \/>\n<meta property=\"og:description\" content=\"Mod\u00e8les de langage, embeddings, bases vectorielles, g\u00e9n\u00e9ration d'images et voix \u2014 la liste des int\u00e9grations disponibles.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/reference\/fournisseurs\/\" \/>\n<meta property=\"og:site_name\" content=\"Wiven AI\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/fournisseurs\\\/\",\"url\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/fournisseurs\\\/\",\"name\":\"Fournisseurs support\u00e9s \u2014 Documentation WivenLLM\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/#website\"},\"datePublished\":\"2026-08-19T19:10:11+00:00\",\"description\":\"Mod\u00e8les de langage, embeddings, bases vectorielles, g\u00e9n\u00e9ration d'images et voix \u2014 la liste des int\u00e9grations disponibles.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/fournisseurs\\\/#breadcrumb\"},\"inLanguage\":\"en\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/fournisseurs\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/fournisseurs\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.wiven.ai\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Documentation\",\"item\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"R\u00e9f\u00e9rence\",\"item\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Fournisseurs support\u00e9s\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/#website\",\"url\":\"https:\\\/\\\/www.wiven.ai\\\/\",\"name\":\"Wiven AI\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.wiven.ai\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Supported providers \u2014 WivenLLM documentation","description":"Language models, embeddings, vector databases, image generation and voice \u2014 the list of available integrations.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/reference\/fournisseurs\/","og_locale":"en_US","og_type":"article","og_title":"Fournisseurs support\u00e9s \u2014 Documentation WivenLLM","og_description":"Mod\u00e8les de langage, embeddings, bases vectorielles, g\u00e9n\u00e9ration d'images et voix \u2014 la liste des int\u00e9grations disponibles.","og_url":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/reference\/fournisseurs\/","og_site_name":"Wiven AI","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/fournisseurs\/","url":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/fournisseurs\/","name":"Supported providers \u2014 WivenLLM documentation","isPartOf":{"@id":"https:\/\/www.wiven.ai\/#website"},"datePublished":"2026-08-19T19:10:11+00:00","description":"Language models, embeddings, vector databases, image generation and voice \u2014 the list of available integrations.","breadcrumb":{"@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/fournisseurs\/#breadcrumb"},"inLanguage":"en","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/fournisseurs\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/fournisseurs\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.wiven.ai\/"},{"@type":"ListItem","position":2,"name":"Documentation","item":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/"},{"@type":"ListItem","position":3,"name":"R\u00e9f\u00e9rence","item":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/"},{"@type":"ListItem","position":4,"name":"Fournisseurs support\u00e9s"}]},{"@type":"WebSite","@id":"https:\/\/www.wiven.ai\/#website","url":"https:\/\/www.wiven.ai\/","name":"Wiven AI","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wiven.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en"}]}},"_links":{"self":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/wvn_doc\/7477","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/wvn_doc"}],"about":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/types\/wvn_doc"}],"up":[{"embeddable":true,"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/wvn_doc\/7453"}],"wp:attachment":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/media?parent=7477"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}