{"id":7487,"date":"2026-08-19T19:10:10","date_gmt":"2026-08-19T19:10:10","guid":{"rendered":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/formats\/"},"modified":"2026-08-19T19:10:10","modified_gmt":"2026-08-19T19:10:10","slug":"formats","status":"publish","type":"wvn_doc","link":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/reference\/formats\/","title":{"rendered":"File formats"},"content":{"rendered":"

File formats<\/h1>\n
\n

Text and documentation<\/h2>\n\n\n\n\n\n\n\n\n\n\n
Scale<\/th>\nTreatment<\/th>\n<\/tr>\n<\/thead>\n
.txt<\/code><\/td>\nDirect reading<\/td>\n<\/tr>\n
.md<\/code><\/td>\nDirect reading, structure preserved<\/td>\n<\/tr>\n
.csv<\/code><\/td>\nDirect reading, line by line<\/td>\n<\/tr>\n
.json<\/code><\/td>\nDirect reading<\/td>\n<\/tr>\n
.html<\/code><\/td>\nText extracted, tags removed<\/td>\n<\/tr>\n
.org<\/code>, .adoc<\/code>, .rst<\/code><\/td>\nDirect reading<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n

Office Automation<\/h2>\n\n\n\n\n\n\n\n\n\n
Scale<\/th>\nTreatment<\/th>\n<\/tr>\n<\/thead>\n
.pdf<\/code><\/td>\nText extraction; character recognition if the PDF is an image<\/td>\n<\/tr>\n
.docx<\/code><\/td>\nExtracting the text and structure<\/td>\n<\/tr>\n
.pptx<\/code><\/td>\nExtracting text from slides<\/td>\n<\/tr>\n
.xlsx<\/code><\/td>\nExtracting cells, sheet by sheet<\/td>\n<\/tr>\n
.odt<\/code>, .odp<\/code><\/td>\nOpenDocument, text and presentation formats<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n

The format .doc<\/code> Word versions prior to 2007 are not supported. Convert
\nin .docx<\/code> beforehand.<\/p>\n<\/blockquote>\n

\n

Messaging and books<\/h2>\n\n\n\n\n\n\n
Scale<\/th>\nTreatment<\/th>\n<\/tr>\n<\/thead>\n
.mbox<\/code><\/td>\nEmail archive; each message becomes an indexable item<\/td>\n<\/tr>\n
.epub<\/code><\/td>\nDigital book, text extracted chapter by chapter<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n

Images<\/h2>\n\n\n\n\n\n
Extensions<\/th>\nTreatment<\/th>\n<\/tr>\n<\/thead>\n
.png<\/code>, .jpg<\/code>, .webp<\/code><\/td>\nCharacter recognition \u2014 the text in the image is extracted<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

The image itself is not indexed; only the text it contains is.
\nQuality depends directly on sharpness and resolution.<\/p>\n

\n

Audio and video<\/h2>\n\n\n\n\n\n\n
Extensions<\/th>\nTreatment<\/th>\n<\/tr>\n<\/thead>\n
.mp3<\/code>, .wav<\/code>, .m4a<\/code>, .ogg<\/code>, .opus<\/code>, .webm<\/code><\/td>\nAutomatic transcription<\/td>\n<\/tr>\n
.mp4<\/code>, .mpeg<\/code><\/td>\nExtracting the audio track and then transcribing it<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

The integrated transcription is running locally<\/strong>, without a key or network output.
\nThe processing time increases with the recording time.<\/p>\n

\n

Remote sources<\/h2>\n\n\n\n\n\n\n\n\n\n\n\n\n
Source<\/th>\nWhat is imported<\/th>\n<\/tr>\n<\/thead>\n
Web page<\/td>\nMain content, menus and advertisements kept out of the way as much as possible<\/td>\n<\/tr>\n
Full site<\/td>\nRecursive exploration, configurable depth and number of pages<\/td>\n<\/tr>\n
Code repositories (GitHub, GitLab)<\/td>\nFiles in a repository, filterable by branch and by extension<\/td>\n<\/tr>\n
Confluence<\/td>\nPages of a space<\/td>\n<\/tr>\n
Company Wikis<\/td>\nPages and tree structure<\/td>\n<\/tr>\n
Document management (Paperless-ngx)<\/td>\nDocuments and metadata<\/td>\n<\/tr>\n
Note chests (Obsidian)<\/td>\nNotes and links<\/td>\n<\/tr>\n
YouTube videos<\/td>\nTranscription<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n

This leads to poor results<\/h2>\n

Low-quality scanned PDFs.<\/strong> Character recognition is applied,
\nbut a tilted, smudged or low-resolution scan produces faulty text \u2014 therefore
\nincorrect answers.<\/p>\n

Complex spreadsheets.<\/strong> Merged cells, formulas, pivot tables and
\nVery wide sheets of paper do not linearize well. For tabular data
\nImportantly, the agent's SQL skills yield much better results.
\n\u2192 SKILLS<\/a><\/p>\n

Very rich layouts.<\/strong> The text is extracted; the information provided
\nsolely through visual arrangement \u2014 a diagram, a graphic chart \u2014
\nlose.<\/p>\n

Poor quality audio recordings.<\/strong> Distant voices, overlapping
\nSpeech and background noise severely degrade the transcription.<\/p>\n

Very large documents.<\/strong> A document of several thousand pages produced
\na large number of fragments dilutes the search. Break it down into units
\nconsistent when possible.<\/p>\n

\n

Check what has been extracted<\/h2>\n

The exact list of formats accepted by your<\/strong> instance is available in
\nthe import interface, and via the API.
\n\u2192 API developer<\/a><\/p>\n

After importing a difficult document, ask a question you know the answer to.
\nFind the answer and look at the quoted excerpt: it's the quickest way to find out
\nif the extraction was successful.<\/p>","protected":false},"parent":7453,"menu_order":701,"template":"","meta":[],"class_list":["post-7487","wvn_doc","type-wvn_doc","status-publish","hentry"],"yoast_head":"\nFormats de fichiers \u2014 Documentation WivenLLM<\/title>\n<meta name=\"description\" content=\"Ce que WivenLLM sait lire, comment chaque format est trait\u00e9, et ce qui donne de mauvais r\u00e9sultats.\" \/>\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\/formats\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Formats de fichiers \u2014 Documentation WivenLLM\" \/>\n<meta property=\"og:description\" content=\"Ce que WivenLLM sait lire, comment chaque format est trait\u00e9, et ce qui donne de mauvais r\u00e9sultats.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/reference\/formats\/\" \/>\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=\"3 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\\\/formats\\\/\",\"url\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/formats\\\/\",\"name\":\"Formats de fichiers \u2014 Documentation WivenLLM\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/#website\"},\"datePublished\":\"2026-08-19T19:10:10+00:00\",\"description\":\"Ce que WivenLLM sait lire, comment chaque format est trait\u00e9, et ce qui donne de mauvais r\u00e9sultats.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/formats\\\/#breadcrumb\"},\"inLanguage\":\"en\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/formats\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/reference\\\/formats\\\/#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\":\"Formats de fichiers\"}]},{\"@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":"File Formats \u2014 WivenLLM Documentation","description":"What WivenLLM can read, how each format is processed, and what gives bad results.","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\/formats\/","og_locale":"en_US","og_type":"article","og_title":"Formats de fichiers \u2014 Documentation WivenLLM","og_description":"Ce que WivenLLM sait lire, comment chaque format est trait\u00e9, et ce qui donne de mauvais r\u00e9sultats.","og_url":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/reference\/formats\/","og_site_name":"Wiven AI","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/formats\/","url":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/formats\/","name":"File Formats \u2014 WivenLLM Documentation","isPartOf":{"@id":"https:\/\/www.wiven.ai\/#website"},"datePublished":"2026-08-19T19:10:10+00:00","description":"What WivenLLM can read, how each format is processed, and what gives bad results.","breadcrumb":{"@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/formats\/#breadcrumb"},"inLanguage":"en","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/formats\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/reference\/formats\/#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":"Formats de fichiers"}]},{"@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\/7487","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=7487"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}