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

Chatdocs

Chatdocs is a Python application for chatting with documents using locally stored AI models. It indexes document folders into a local database and offers a web UI and command-line interface, with offline use after installation and model downloads.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Chatdocs — 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 Chatdocs when you want a locally run document-chat workflow and can install the tool and download models before working offline.

Who it is for

  • People who want to ask questions across personal or work document collections while keeping source files on their own system.
  • Developers setting up a self-hosted document-question-answering interface.

Documented uses

  • Add a folder of documents to a local searchable collection.
  • Ask questions about the collection through a browser UI or CLI.
  • Choose supported language-model and embeddings configurations.
Before you choose

Requirements & limits

The README documents installation with pip and use through a local web interface at localhost:5000 or the command line. Internet access is required to install the tool and download models; the project says it can then run offline.

  • Processed documents are stored in a local db directory by default.
  • The project supports GGML/GGUF through CTransformers, Transformers, and GPTQ models.
  • A configurable YAML file controls model choices and other settings.
  • CUDA settings are documented for embeddings and supported model backends; additional CUDA-enabled packages or PyTorch installation may be needed.

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

Set up a local document collection and open the chat

Install Chatdocs, prepare a document folder for local search, and open its web interface.

Before you start

  • Python package installation with pip
  • Internet access for installation and model downloads
  • A directory containing supported documents

Steps

  1. Install the package with the command below.

    Documented command
    pip install chatdocs

  2. Download AI models with chatdocs download.

  3. Add a document directory with chatdocs add /path/to/documents; processed files are stored in db by default.

  4. Run chatdocs ui and open http://localhost:5000 in a browser.

Expected outcome

A local web interface for chatting with the added documents; the README says Chatdocs can run offline after installation and model downloads.

Guide limitations

  • Installation and model downloads require an internet connection.
  • Changing the embeddings model requires deleting db and adding documents again.
Documentation 1 ↗
Evidence and transparency

Sources & review

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