OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Wdoc

Wdoc is an open-source Python retrieval-augmented generation application for summarizing, searching and querying documents across multiple file formats. It offers a CLI and a documented Gradio-based Docker web interface, and uses LangChain and LiteLLM as backends.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Wdoc — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Wdoc when you need to search, summarize or question a collection that spans multiple document types, or when you want a scriptable Python-based RAG workflow. Choose the relevant loaders based on your source formats.

Who it is for

  • Researchers, students and professionals working with large or varied document collections.
  • People who want to ask questions across sources such as PDFs, recordings, video lectures, EPUBs or Anki flashcards.
  • Developers seeking a scriptable RAG tool with selectable document loaders.

Documented uses

  • Search a document collection for relevant material.
  • Ask questions across multiple sources and receive answers that refer to source material.
  • Summarize documents or larger collections to keep up with substantial amounts of information.
  • Add support for particular document formats by selecting optional loaders.
Before you choose

Requirements & limits

Wdoc is a Python application with CLI installation instructions and a documented Docker web interface. The repository lists the AGPL-3.0 license.

  • The standard package includes PDF and URL/web loaders; additional formats require optional extras.
  • Python 3.11 or later is supported, with Python 3.13 recommended where possible.
  • Wdoc uses LangChain and LiteLLM and describes support for different LLM providers, including local providers.
  • The full extra excludes fasttext and pdftotext, which need special handling; pdftotext requires system libraries.
  • The project notes that fasttext is buggy on Windows.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Wdoc with its full set of loader extras

Set up the recommended Wdoc package with the documented loader extras.

Before you start

  • Python 3.11 or later; the project recommends Python 3.13 where possible.
  • uv, as referenced by the installation instructions.

Steps

  1. Install or use uv according to its documentation.

  2. Run the repository's recommended invocation: uvx wdoc[full].

Expected outcome

Wdoc is invoked with the full loader-extra bundle, excluding the separately handled fasttext and pdftotext extras.

Guide limitations

  • The full extra does not include fasttext or pdftotext.
  • The pdftotext extra requires system libraries; fasttext is noted as buggy on Windows.
Documentation 1 ↗
Source-based practical guide

Select loaders for specific document formats

Install Wdoc with optional loaders matching particular source formats.

Before you start

  • Python 3.11 or later; the project recommends Python 3.13 where possible.
  • uv, as referenced by the installation instructions.

Steps

  1. Choose the documented extras corresponding to the material: youtube for YouTube videos and playlists, audio for local audio/video transcription, anki for Anki collections, office for office formats and EPUB, or logseq for Logseq markdown graphs.

  2. Invoke uvx with the selected extras, combining them where needed; the repository gives uvx wdoc[youtube,audio,anki] as an example.

Expected outcome

Wdoc is invoked with the selected optional loaders rather than the full loader bundle.

Guide limitations

  • The plain package includes PDF and URL/web loaders; other listed formats require their corresponding extras.
  • The audio extra lists dependencies including Deepgram, pydub, torchaudio and ffmpeg-python; the repository does not establish that every setup works in every environment.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
WdocSearch a document collection for relevant material.CLIWdoc is a Python application with CLI installation instructions and a documented Docker web interface. The repository lists the AGPL-3.0 license.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
thiswillbeyourgithub/wdoc · Official homepage title · retained in its source language
How we review sourcesSuggest a correction