{"id":7485,"date":"2026-08-19T19:10:09","date_gmt":"2026-08-19T19:10:09","guid":{"rendered":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/integrations\/api\/"},"modified":"2026-08-19T19:10:09","modified_gmt":"2026-08-19T19:10:09","slug":"api","status":"publish","type":"wvn_doc","link":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/integrations\/api\/","title":{"rendered":"API developer"},"content":{"rendered":"

API developer<\/h1>\n

An HTTP API allows you to integrate WivenLLM into your applications: to feed
\nspaces, ask questions, manage users, leverage the
\nconversations.<\/p>\n

\n

Available for server or hosted deployment.<\/p>\n<\/blockquote>\n

\n

Authentication<\/h2>\n

Create a key in Settings \u2192 API Keys<\/code>. It is only displayed at the
\ncreation.<\/p>\n

Each request carries the key in the header. Authorization<\/code> :<\/p>\n

curl https:\/\/your-instance\/api\/v1\/workspaces -H "Authorization: Bearer YOUR_API_KEY"\"\n<\/code><\/pre>\n
A key provides full access to the API.<\/strong> Create one per integration,
\nRevoke what is no longer needed, and never publish it in shared code.
\nKey creations and deletions are logged.<\/p>\n
\n
Interactive documentation<\/h2>\n
Interactive API documentation is provided by the instance itself.
\nlists all entry points with their parameters and allows you to try them out.
\nThis is the up-to-date reference for your<\/strong> version.<\/p>\n
It can be disabled in production via configuration.<\/p>\n
\n
Main entry points<\/h2>\n
All addresses are relative to \/api<\/code>.<\/p>\n
Workspaces<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n
Method<\/th>\nPath<\/th>\nRole<\/th>\n<\/tr>\n<\/thead>\n
GET<\/code><\/td>\n\/v1\/workspaces<\/code><\/td>\nList the spaces<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/workspace\/new<\/code><\/td>\nCreate a space<\/td>\n<\/tr>\n
GET<\/code><\/td>\n\/v1\/workspace\/{slug}<\/code><\/td>\nDetail of a space<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/update<\/code><\/td>\nChange your settings<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/update-embeddings<\/code><\/td>\nAdd or remove documents<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/update-pin<\/code><\/td>\nPin or unpin a document<\/td>\n<\/tr>\n
DELETE<\/code><\/td>\n\/v1\/workspace\/{slug}<\/code><\/td>\nDelete a space<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
Conversation<\/h3>\n\n\n\n\n\n\n\n\n
Method<\/th>\nPath<\/th>\nRole<\/th>\n<\/tr>\n<\/thead>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/chat<\/code><\/td>\nAsk a question, get a full answer<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/stream-chat<\/code><\/td>\nLikewise, continuous flow response<\/td>\n<\/tr>\n
GET<\/code><\/td>\n\/v1\/workspace\/{slug}\/chats<\/code><\/td>\nHistory of space<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/vector-search<\/code><\/td>\nDocumentary research alone, without generation<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
Example :<\/strong><\/p>\n
curl -X POST https:\/\/your-instance\/api\/v1\/workspace\/dupont-folder\/chat -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application\/json" -d '{ "message": "What is the lease termination period?", "mode": "query" }'\"\n<\/code><\/pre>\n
The response contains the generated text and the sources<\/strong> used.<\/p>\n
vector-search<\/code> is useful when you only want to find the passages
\nrelevant and process them yourself, without going through a template.<\/p>\n
Discussion thread<\/h3>\n\n\n\n\n\n\n\n\n\n
Method<\/th>\nPath<\/th>\nRole<\/th>\n<\/tr>\n<\/thead>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/thread\/new<\/code><\/td>\nCreate a thread<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/thread\/{threadSlug}\/chat<\/code><\/td>\nWrite in a thread<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/workspace\/{slug}\/thread\/{threadSlug}\/stream-chat<\/code><\/td>\nLikewise, in continuous flow<\/td>\n<\/tr>\n
GET<\/code><\/td>\n\/v1\/workspace\/{slug}\/thread\/{threadSlug}\/chats<\/code><\/td>\nHistory of the thread<\/td>\n<\/tr>\n
DELETE<\/code><\/td>\n\/v1\/workspace\/{slug}\/thread\/{threadSlug}<\/code><\/td>\nDelete the thread<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
The threads allow for multiple independent conversations to be maintained for
\ndifferent end users within the same space.<\/p>\n
Documents<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n
Method<\/th>\nPath<\/th>\nRole<\/th>\n<\/tr>\n<\/thead>\n
POST<\/code><\/td>\n\/v1\/document\/upload<\/code><\/td>\nUpload a file<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/document\/upload-link<\/code><\/td>\nImport a URL<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/document\/raw-text<\/code><\/td>\nInject raw text<\/td>\n<\/tr>\n
GET<\/code><\/td>\n\/v1\/documents<\/code><\/td>\nList the documents<\/td>\n<\/tr>\n
GET<\/code><\/td>\n\/v1\/document\/accepted-file-types<\/code><\/td>\nAccepted formats<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/document\/create-folder<\/code><\/td>\nCreate a folder<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/document\/move-files<\/code><\/td>\nMove documents<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n
Reminder :<\/strong> Uploading a document does not make it searchable. Next, you need to...
\nadd it to a space via update-embeddings<\/code>.<\/p>\n<\/blockquote>\n
Administration<\/h3>\n\n\n\n\n\n\n\n\n\n
Method<\/th>\nPath<\/th>\nRole<\/th>\n<\/tr>\n<\/thead>\n
GET<\/code><\/td>\n\/v1\/admin\/users<\/code><\/td>\nList users<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/admin\/users\/new<\/code><\/td>\nCreate a user<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/admin\/invite\/new<\/code><\/td>\nCreate an invitation<\/td>\n<\/tr>\n
GET<\/code><\/td>\n\/v1\/admin\/workspace-chats<\/code><\/td>\nConversations within the body<\/td>\n<\/tr>\n
POST<\/code><\/td>\n\/v1\/admin\/workspaces\/{id}\/update-users<\/code><\/td>\nManaging the members of a space<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
Widgets<\/h3>\n
Creation, consultation and monitoring of widgets and their conversations.<\/p>\n
System<\/h3>\n
Information about the instance, number of vectors, export of conversations.<\/p>\n
\n
OpenAI compatibility<\/h2>\n
A set of entry points replicates the interface of the OpenAI standard:<\/p>\n
    \n
  • POST \/v1\/openai\/chat\/completions<\/code><\/li>\n
  • POST \/v1\/openai\/embeddings<\/code><\/li>\n
  • GET \/v1\/openai\/models<\/code><\/li>\n<\/ul>\n
    The advantage: an application already written for this standard works with
    \nWivenLLM by changing the base address and the key<\/strong>. The model name
    \ncorresponds to the workspace to be queried, which allows you to benefit from
    \nits documentary context.<\/p>\n
    This is the shortest way to connect an existing tool to your base
    \nprivate documentary.<\/p>\n
    \n
    Best practices for integration<\/h2>\n
    One space per use.<\/strong> Isolate areas exposed to application from spaces
    \nused by your employees.<\/p>\n
    One thread per end user.<\/strong> If your application serves multiple people,
    \nCreate a separate thread for each person: contexts should not mix.<\/p>\n
    Process the mode.<\/strong> The parameter fashion<\/code> (cat<\/code> Or query<\/code>is decisive for a
    \nintegration: query<\/code> avoids invented answers when the database does not contain
    \ninformation.<\/p>\n
    Manage errors and latency.<\/strong> A response may take several seconds.,
    \nmore with an agent. Expect appropriate waiting times and processing
    \nmodel provider failures.<\/p>\n
    Use continuous flow<\/strong> for any interface where a human is waiting: the
    \nThe response appears as it is displayed, the perceived wait is much shorter.<\/p>\n
    Utilize the sources.<\/strong> The responses return the extracts used:
    \nDisplay them, that's what makes the integration verifiable.<\/p>","protected":false},"parent":7452,"menu_order":602,"template":"","meta":[],"class_list":["post-7485","wvn_doc","type-wvn_doc","status-publish","hentry"],"yoast_head":"\nAPI d\u00e9veloppeur \u2014 Documentation WivenLLM<\/title>\n<meta name=\"description\" content=\"Piloter WivenLLM depuis vos applications \u2014 authentification, principaux points d'entr\u00e9e et compatibilit\u00e9 OpenAI.\" \/>\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\/integrations\/api\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"API d\u00e9veloppeur \u2014 Documentation WivenLLM\" \/>\n<meta property=\"og:description\" content=\"Piloter WivenLLM depuis vos applications \u2014 authentification, principaux points d'entr\u00e9e et compatibilit\u00e9 OpenAI.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/integrations\/api\/\" \/>\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\\\/integrations\\\/api\\\/\",\"url\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/integrations\\\/api\\\/\",\"name\":\"API d\u00e9veloppeur \u2014 Documentation WivenLLM\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/#website\"},\"datePublished\":\"2026-08-19T19:10:09+00:00\",\"description\":\"Piloter WivenLLM depuis vos applications \u2014 authentification, principaux points d'entr\u00e9e et compatibilit\u00e9 OpenAI.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/integrations\\\/api\\\/#breadcrumb\"},\"inLanguage\":\"en\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/integrations\\\/api\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/integrations\\\/api\\\/#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\":\"Int\u00e9grations\",\"item\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/integrations\\\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"API d\u00e9veloppeur\"}]},{\"@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":"Developer API \u2014 WivenLLM Documentation","description":"Control WivenLLM from your applications \u2014 authentication, main entry points and OpenAI compatibility.","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\/integrations\/api\/","og_locale":"en_US","og_type":"article","og_title":"API d\u00e9veloppeur \u2014 Documentation WivenLLM","og_description":"Piloter WivenLLM depuis vos applications \u2014 authentification, principaux points d'entr\u00e9e et compatibilit\u00e9 OpenAI.","og_url":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/integrations\/api\/","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\/integrations\/api\/","url":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/integrations\/api\/","name":"Developer API \u2014 WivenLLM Documentation","isPartOf":{"@id":"https:\/\/www.wiven.ai\/#website"},"datePublished":"2026-08-19T19:10:09+00:00","description":"Control WivenLLM from your applications \u2014 authentication, main entry points and OpenAI compatibility.","breadcrumb":{"@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/integrations\/api\/#breadcrumb"},"inLanguage":"en","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wiven.ai\/wiven-llm\/docs\/integrations\/api\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/integrations\/api\/#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":"Int\u00e9grations","item":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/integrations\/"},{"@type":"ListItem","position":4,"name":"API d\u00e9veloppeur"}]},{"@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\/7485","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\/7452"}],"wp:attachment":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/media?parent=7485"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}