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

Dropbox AI Chat

Dropbox AI Chat is a self-hosted document-search and chat application that indexes files from a locally synced Dropbox or OneDrive folder and uses OpenAI embeddings and a language model to answer questions and summarize document content. It provides a Pathway backend API and a Streamlit web interface, with Docker Compose and source-based setup documented.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dropbox AI Chat — 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 it when the documents are available in a locally synced Dropbox or OneDrive folder and you want a self-hosted interface for document search, questions, and summaries.

Who it is for

  • People who want to ask questions across private documents stored in Dropbox or OneDrive.
  • Developers who want to run or adapt a self-hosted retrieval application using local cloud-storage folders.

Documented uses

  • Search multiple unstructured documents for relevant information.
  • Ask questions about indexed document contents.
  • Summarize private document collections.
  • Run the API and browser UI locally from source or through Docker Compose.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. The documented source setup requires an OpenAI account and API key; the Docker instructions also require an OpenAI API key.

  • The app reads a local folder, so Dropbox or OneDrive synchronization and a usable folder path are part of setup.
  • The README documents OpenAI embeddings and a language model, with model settings configurable through environment variables.
  • The project exposes a Pathway backend API and a separate Streamlit UI.
  • Documented launch options include Docker Compose and a Python source setup.

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

Run the app with Docker Compose

Configure and open the containerized app with a local Dropbox folder.

Before you start

  • Docker Compose
  • An OpenAI API key
  • A local Dropbox folder path

Steps

  1. Create a .env file in the project root.

  2. Set OPENAI_API_TOKEN to the OpenAI API key and DROPBOX_LOCAL_FOLDER_PATH to the local Dropbox folder path.

  3. From the project root, run the command below.

    Documented command
    docker compose up

  4. When the installation succeeds, open localhost:8501 in a browser.

Expected outcome

The API and browser UI run as a containerized local application.

Guide limitations

  • The documented Docker configuration uses a local Dropbox folder path; OneDrive adaptation requires configuring credentials and folder synchronization.
Documentation 1 ↗
Source-based practical guide

Set up and start from source

Install the source dependencies and start the backend API and Streamlit UI.

Before you start

  • Python 3.10 or later
  • pip
  • An OpenAI API key
  • A Dropbox or OneDrive account and a locally synced folder

Steps

  1. Clone the repository and change into its project directory.

  2. Create a .env file with the OpenAI API token and the local Dropbox folder path.

  3. Optionally create and activate a Python virtual environment.

  4. Install dependencies with the command below.

    Documented command
    pip install --upgrade -r requirements.txt

  5. Start the API with the command below, then start the UI separately with streamlit run ui.py.

    Documented command
    python main.py

Expected outcome

The Pathway API and Streamlit browser interface are started from source.

Guide limitations

  • The README describes Dropbox in the environment-variable example; using OneDrive requires configuring its credentials and folder synchronization.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
pathway-labs/dropbox-ai-chat · Official homepage title · retained in its source language
How we review sourcesSuggest a correction