tiennm99/DocsGPT
1
0 Fork 0
mirror of https://github.com/tiennm99/DocsGPT.git synced 2026-10-03 09:12:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: one-command installers for macOS, Linux and Windows

Browse Source 
deployment/install.sh (curl | bash) and install.ps1 (irm | iex) check for
Docker, install uv when it is missing or older than 0.8 (pinned 0.12.15 via
Astral's installer), install or upgrade the docsgpt package with
`uv tool install`, and hand the terminal to `docsgpt up` with any arguments.
On Linux without Docker the shell installer offers get.docker.com. Both run
entirely inside a function, so a download cut short runs nothing.

Releases attach both scripts next to the Compose file, which is where
docs.ac/install and docs.ac/install.ps1 will point. installer-lint.yml runs
shellcheck and the PowerShell parser; docker-image-verify.yml now installs
through install.sh. README, Quickstart, Docker-Deploying and the changelog
lead with the one-liner.
This commit is contained in:
Alex committed 2026-09-16 01:10:11 +01:00
1 parent 6b6bd1b0fb
commit 4f0bf2cca8
9 files changed
+455 -101
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.github/workflows/ci.yml
+9 -2
View File
@@ -206,9 +206,16 @@ jobs:
ref: ${{ inputs.version && format('refs/tags/{0}', inputs.version) || github.ref }}
persist-credentials: false
- name: Attach the standalone compose file to the release
# The installers are served from these assets: docs.ac/install redirects to
# releases/latest/download/install.sh (and install.ps1), so the script a
# user runs always comes from the newest release.
- name: Attach the standalone compose file and the installers to the release
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
TAG: ${{ env.RELEASE_TAG }}
run: |
gh release upload "$TAG" deployment/docker-compose-standalone.yaml --clobber
gh release upload "$TAG" \
deployment/docker-compose-standalone.yaml \
deployment/install.sh \
deployment/install.ps1 \
--clobber
.github/workflows/docker-image-verify.yml
+18 -29
View File
@@ -23,6 +23,7 @@ on:
- 'frontend/**'
- 'scripts/build_frontend.sh'
- 'deployment/docker-compose-standalone.yaml'
- 'deployment/install.sh'
- 'docsgpt/deploy/**'
- 'docsgpt/cli.py'
- 'docsgpt/core/paths.py'
@@ -98,41 +99,29 @@ jobs:
curl -fsS "$base/settings" | grep -q 'src="/config.js"'
echo "API and UI served on $base"
- name: Set up uv
if: matrix.variant == ''
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6.8.0
with:
# No cache: a cache restored into a job that runs the built image is a poisoning risk.
enable-cache: false
- name: docsgpt up runs the same image from the installed package
- name: The installer runs docsgpt up on the same image
if: matrix.variant == ''
env:
DOCSGPT_NO_MODIFY_PATH: "1"
run: |
set -euo pipefail
# Same Compose project name as the step above; stop that stack first.
docker compose -f deployment/docker-compose-standalone.yaml down -v
uv build --wheel --out-dir "$RUNNER_TEMP/dist"
uv venv "$RUNNER_TEMP/venv"
uv pip install --python "$RUNNER_TEMP/venv/bin/python" "$RUNNER_TEMP"/dist/*.whl
docsgpt="$RUNNER_TEMP/venv/bin/docsgpt"
stack="$RUNNER_TEMP/stack"
"$docsgpt" up --yes --dir "$stack" --image-tag verify
"$docsgpt" status --dir "$stack"
pipx run build --wheel --outdir "$RUNNER_TEMP/dist"
export DOCSGPT_PACKAGE="$(ls "$RUNNER_TEMP"/dist/docsgpt-*.whl)"
# No uv is set up beforehand, so the installer's pinned uv download runs too.
# Without a terminal the installer passes --yes to docsgpt up.
bash deployment/install.sh --image-tag verify </dev/null
docsgpt="$HOME/.local/bin/docsgpt"
stack="$HOME/.docsgpt/server"
"$docsgpt" status
curl -fsS http://127.0.0.1:7091/ | grep -q 'src="/config.js"'
# Each secret must appear exactly once with a value: a missing or empty one
# falls back to a default silently.
check_secrets() {
for key in POSTGRES_PASSWORD JWT_SECRET_KEY; do
[ "$(grep -Ec "^$key=.+$" "$stack/.env")" -eq 1 ]
done
}
check_secrets
secrets=$(grep -E '^(POSTGRES_PASSWORD|JWT_SECRET_KEY)=.+$' "$stack/.env" | sort)
# Running up again keeps them; a changed database password locks the stack out of its volume.
"$docsgpt" up --yes --dir "$stack" --image-tag verify
check_secrets
[ "$(grep -E '^(POSTGRES_PASSWORD|JWT_SECRET_KEY)=.+$' "$stack/.env" | sort)" = "$secrets" ]
"$docsgpt" uninstall --yes --purge --dir "$stack"
grep -q '^POSTGRES_PASSWORD=' "$stack/.env"
# Running the installer again upgrades in place and keeps the generated secrets.
before=$(grep '^JWT_SECRET_KEY=' "$stack/.env")
bash deployment/install.sh --image-tag verify </dev/null
[ "$(grep '^JWT_SECRET_KEY=' "$stack/.env")" = "$before" ]
"$docsgpt" uninstall --yes --purge
test ! -e "$stack"
- name: Stack logs
.github/workflows/installer-lint.yml
+47
View File
@@ -0,0 +1,47 @@
name: Lint the installers
# deployment/install.sh runs as `curl | bash` on macOS (bash 3.2) and Linux, and
# deployment/install.ps1 as `irm | iex` on Windows; a syntax error in either
# breaks every install at once. The end-to-end run through install.sh is in
# docker-image-verify.yml.
on:
pull_request:
paths:
- 'deployment/install.sh'
- 'deployment/install.ps1'
- '.github/workflows/installer-lint.yml'
push:
branches: [main]
paths:
- 'deployment/install.sh'
- 'deployment/install.ps1'
- '.github/workflows/installer-lint.yml'
permissions:
contents: read
jobs:
lint:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4.4.0
with:
persist-credentials: false
- name: shellcheck install.sh
run: |
bash -n deployment/install.sh
shellcheck --shell=bash deployment/install.sh
- name: Parse install.ps1
shell: pwsh
run: |
$tokens = $null
$errors = $null
[System.Management.Automation.Language.Parser]::ParseFile("$PWD/deployment/install.ps1", [ref]$tokens, [ref]$errors) | Out-Null
if ($errors.Count) {
$errors | ForEach-Object { Write-Host "install.ps1:$($_.Extent.StartLineNumber): $($_.Message)" }
exit 1
}
Write-Host 'install.ps1 parses'
README.md
+26 -2
View File
@@ -80,9 +80,33 @@ Calling all developers and GenAI innovators! The **DocsGPT Lighthouse Program**
## QuickStart
> [!Note]
> Make sure you have [Docker](https://docs.docker.com/engine/install/) installed
> DocsGPT runs on [Docker](https://docs.docker.com/engine/install/). The installer checks for it first.
A more detailed [Quickstart](https://docs.docsgpt.cloud/quickstart) is available in our documentation
**macOS and Linux:**
```bash
curl -fsSL https://docs.ac/install | bash
```
**Windows (PowerShell):**
```powershell
irm https://docs.ac/install.ps1 | iex
```
The installer gets [uv](https://docs.astral.sh/uv/), installs the `docsgpt` Python package with it, and runs `docsgpt up`. That asks who should reach DocsGPT (only this computer, your network, or a domain with HTTPS) and which model provider to use, then starts it, at http://localhost:7091 for a local install. Afterwards, `docsgpt status`, `docsgpt logs`, `docsgpt upgrade`, `docsgpt down` and `docsgpt uninstall` manage it.
To read the script before running it:
```bash
curl -fsSL https://docs.ac/install -o install.sh
less install.sh
bash install.sh
```
A more detailed [Quickstart](https://docs.docsgpt.cloud/quickstart) is available in our documentation.
### From a clone, with the setup script
1. **Clone the repository:**
deployment/install.ps1
+94
View File
@@ -0,0 +1,94 @@
# DocsGPT installer for Windows.
#
# irm https://docs.ac/install.ps1 | iex
#
# Installs uv when it is missing or too old, installs the docsgpt Python
# package with it, then runs `docsgpt up`, which sets up DocsGPT on Docker
# Desktop and starts it. Running it again upgrades the package and keeps your
# settings. To pass options to `docsgpt up`:
#
# & ([scriptblock]::Create((irm https://docs.ac/install.ps1))) --domain docs.example.com --yes
#
# Environment:
# DOCSGPT_VERSION package version to install (default: the latest release)
# DOCSGPT_PACKAGE install this instead of docsgpt from PyPI (a wheel path or URL)
# DOCSGPT_NO_MODIFY_PATH set to 1 to leave PATH alone
#
# Everything runs inside a function, so a download cut short runs nothing, and
# nothing calls `exit`, which would close the window `iex` runs in.
function Install-DocsGPT {
param([string[]]$UpArguments)
$ErrorActionPreference = 'Stop'
$UvVersion = '0.12.15'
$UvMinVersion = [version]'0.8.0'
function Say([string]$Message) { Write-Host "==> $Message" }
if (-not (Get-Command docker -ErrorAction SilentlyContinue)) {
throw 'DocsGPT runs on Docker. Install Docker Desktop (https://docs.docker.com/desktop/setup/install/windows-install/), start it, and run this again.'
}
# uv installs and upgrades the package, and brings Python 3.12 when the system has none.
$uv = $null
$candidates = @(
(Get-Command uv -ErrorAction SilentlyContinue | Select-Object -ExpandProperty Source -First 1),
(Join-Path $HOME '.local\bin\uv.exe'),
(Join-Path $HOME '.cargo\bin\uv.exe')
) | Where-Object { $_ -and (Test-Path $_) }
foreach ($candidate in $candidates) {
$found = "$(& $candidate --version 2>$null)" -replace '^uv\s+([0-9.]+).*$', '$1'
if ($found -match '^\d+\.\d+(\.\d+)?$' -and [version]$found -ge $UvMinVersion) {
$uv = $candidate
break
}
}
if (-not $uv) {
$uvDir = Join-Path $HOME '.local\bin'
Say "Installing uv $UvVersion into $uvDir"
$env:UV_INSTALL_DIR = $uvDir
$env:UV_NO_MODIFY_PATH = '1'
$env:UV_PRINT_QUIET = '1'
# A child PowerShell, so nothing the uv installer does can end this session.
$shell = (Get-Process -Id $PID).Path
& $shell -NoProfile -ExecutionPolicy Bypass -Command "irm https://astral.sh/uv/$UvVersion/install.ps1 | iex"
$uv = Join-Path $uvDir 'uv.exe'
if (-not (Test-Path $uv)) { throw "uv did not install into $uvDir" }
}
if ($env:DOCSGPT_VERSION -and $env:DOCSGPT_PACKAGE) {
throw 'Set DOCSGPT_VERSION or DOCSGPT_PACKAGE, not both.'
}
if ($env:DOCSGPT_PACKAGE) {
Say "Installing docsgpt from $env:DOCSGPT_PACKAGE"
& $uv tool install --reinstall --python 3.12 $env:DOCSGPT_PACKAGE
} elseif ($env:DOCSGPT_VERSION) {
Say "Installing docsgpt $env:DOCSGPT_VERSION"
& $uv tool install --force --python 3.12 "docsgpt==$env:DOCSGPT_VERSION"
} else {
Say 'Installing the latest docsgpt'
& $uv tool install --upgrade --python 3.12 docsgpt
}
if ($LASTEXITCODE -ne 0) { throw 'Installing the docsgpt package failed.' }
$binDir = "$(& $uv tool dir --bin)".Trim()
$docsgpt = Join-Path $binDir 'docsgpt.exe'
if (-not (Test-Path $docsgpt)) { throw "The docsgpt command is missing from $binDir." }
if (($env:Path -split ';') -notcontains $binDir) {
if ($env:DOCSGPT_NO_MODIFY_PATH -eq '1') {
Say "Add $binDir to PATH to run docsgpt from a new terminal"
} else {
& $uv tool update-shell *> $null
Say "Added $binDir to PATH for new terminals"
}
$env:Path = "$binDir;$env:Path"
}
& $docsgpt up @UpArguments
if ($LASTEXITCODE -ne 0) {
Write-Error "docsgpt up exited with code $LASTEXITCODE. Run it again after fixing the problem above: docsgpt up" -ErrorAction Continue
}
}
Install-DocsGPT -UpArguments $args
deployment/install.sh
Executable
+169
View File
@@ -0,0 +1,169 @@
#!/usr/bin/env bash
# DocsGPT installer for macOS and Linux.
#
# curl -fsSL https://docs.ac/install | bash
#
# Installs uv when it is missing or too old, installs the `docsgpt` Python
# package with it, then runs `docsgpt up`, which sets up DocsGPT on Docker and
# starts it. Running it again upgrades the package and keeps your settings.
# Arguments go to `docsgpt up` (see `docsgpt up --help`):
#
# curl -fsSL https://docs.ac/install | bash -s -- --domain docs.example.com --yes
#
# Environment:
# DOCSGPT_VERSION package version to install (default: the latest release)
# DOCSGPT_PACKAGE install this instead of docsgpt from PyPI (a wheel path or URL)
# DOCSGPT_NO_MODIFY_PATH set to 1 to leave shell profiles alone
# DOCSGPT_INSTALL_DOCKER set to 1 to install Docker on Linux without asking
#
# Everything runs inside main(), so a download cut short runs nothing.
UV_VERSION="0.12.15"
UV_MIN_VERSION="0.8.0"
main() {
set -euo pipefail
local bold="" red="" reset=""
if [ -t 2 ]; then
bold=$'\033[1m' red=$'\033[31m' reset=$'\033[0m'
fi
say() { printf '%s==>%s %s\n' "$bold" "$reset" "$*" >&2; }
die() { printf '%serror:%s %s\n' "$red" "$reset" "$*" >&2; exit 1; }
has() { command -v "$1" >/dev/null 2>&1; }
have_tty() { (exec </dev/tty) 2>/dev/null; }
ask_yes() {
local answer
printf '%s [y/N] ' "$1" >/dev/tty
read -r answer </dev/tty || return 1
case "$answer" in y | Y | yes | YES) return 0 ;; *) return 1 ;; esac
}
download() {
if has curl; then
curl -fsSL --retry 3 "$1"
elif has wget; then
wget -qO- "$1"
else
die "curl or wget is needed to download $1"
fi
}
# version_ge A B: A >= B for dotted version numbers.
version_ge() {
local -a left right
IFS=. read -r -a left <<<"$1"
IFS=. read -r -a right <<<"$2"
local i x y
for i in 0 1 2; do
x="${left[i]:-0}" y="${right[i]:-0}"
x="${x%%[!0-9]*}" y="${y%%[!0-9]*}"
if (( 10#${x:-0} > 10#${y:-0} )); then return 0; fi
if (( 10#${x:-0} < 10#${y:-0} )); then return 1; fi
done
return 0
}
local os
os="$(uname -s)"
case "$os" in
Linux | Darwin) ;;
*) die "this installer is for macOS and Linux. On Windows, in PowerShell: irm https://docs.ac/install.ps1 | iex" ;;
esac
# Docker first: without it nothing below is useful.
local docker_group_pending=0
if ! has docker; then
if [ "$os" = Darwin ]; then
die "DocsGPT runs on Docker. Install Docker Desktop (https://docs.docker.com/desktop/setup/install/mac-install/) or OrbStack (https://orbstack.dev), start it, and run this again."
fi
if [ "${DOCSGPT_INSTALL_DOCKER:-}" = 1 ] || { have_tty && ask_yes "Docker is not installed. Install it now with Docker's script from get.docker.com?"; }; then
local sudo=""
if [ "$(id -u)" -ne 0 ]; then
has sudo || die "installing Docker needs root. Install it (https://docs.docker.com/engine/install/) and run this again."
sudo="sudo"
fi
say "Installing Docker"
download https://get.docker.com | $sudo sh
$sudo systemctl enable --now docker >/dev/null 2>&1 || true
if [ -n "$sudo" ]; then
$sudo usermod -aG docker "$(id -un)"
docker_group_pending=1
fi
else
die "DocsGPT runs on Docker. Install it (https://docs.docker.com/engine/install/) and run this again."
fi
fi
# uv installs and upgrades the package, and brings Python 3.12 when the system has none.
local uv="" candidate found
for candidate in "$(command -v uv 2>/dev/null || true)" "$HOME/.local/bin/uv" "$HOME/.cargo/bin/uv"; do
[ -n "$candidate" ] && [ -x "$candidate" ] || continue
found="$("$candidate" --version 2>/dev/null | awk '{print $2}')" || continue
if [ -n "$found" ] && version_ge "$found" "$UV_MIN_VERSION"; then
uv="$candidate"
break
fi
done
if [ -z "$uv" ]; then
local uv_dir="${XDG_BIN_HOME:-$HOME/.local/bin}"
say "Installing uv $UV_VERSION into $uv_dir"
download "https://astral.sh/uv/$UV_VERSION/install.sh" | env UV_INSTALL_DIR="$uv_dir" UV_NO_MODIFY_PATH=1 UV_PRINT_QUIET=1 sh
uv="$uv_dir/uv"
[ -x "$uv" ] || die "uv did not install into $uv_dir"
fi
if [ -n "${DOCSGPT_VERSION:-}" ] && [ -n "${DOCSGPT_PACKAGE:-}" ]; then
die "set DOCSGPT_VERSION or DOCSGPT_PACKAGE, not both"
fi
if [ -n "${DOCSGPT_PACKAGE:-}" ]; then
say "Installing docsgpt from $DOCSGPT_PACKAGE"
"$uv" tool install --reinstall --python 3.12 "$DOCSGPT_PACKAGE"
elif [ -n "${DOCSGPT_VERSION:-}" ]; then
say "Installing docsgpt $DOCSGPT_VERSION"
"$uv" tool install --force --python 3.12 "docsgpt==$DOCSGPT_VERSION"
else
say "Installing the latest docsgpt"
"$uv" tool install --upgrade --python 3.12 docsgpt
fi
local bin_dir docsgpt
bin_dir="$("$uv" tool dir --bin)"
docsgpt="$bin_dir/docsgpt"
[ -x "$docsgpt" ] || die "the docsgpt command is missing from $bin_dir"
case ":$PATH:" in
*":$bin_dir:"*) ;;
*)
if [ "${DOCSGPT_NO_MODIFY_PATH:-}" = 1 ]; then
say "Add $bin_dir to PATH to run docsgpt from a new terminal"
else
"$uv" tool update-shell >/dev/null 2>&1 || true
say "Added $bin_dir to PATH for new terminals"
fi
;;
esac
if [ "$docker_group_pending" = 1 ]; then
if has sg; then
# The docker group applies to new logins; sg gives it to this command now.
local command
command="$(printf '%q ' "$docsgpt" up "$@")"
if have_tty; then
exec sg docker -c "$command </dev/tty"
fi
exec sg docker -c "$command --yes"
fi
say "Docker is installed and your user joined the docker group. Log out and back in, then run: docsgpt up"
exit 0
fi
# Hand the terminal to docsgpt up: when this script is piped into bash, its
# standard input is the script, not the keyboard.
if [ -t 0 ]; then
exec "$docsgpt" up "$@"
fi
if have_tty; then
exec "$docsgpt" up "$@" </dev/tty
fi
exec "$docsgpt" up --yes "$@"
}
main "$@"
docs/content/Deploying/Docker-Deploying.mdx
+12 -2
View File
@@ -20,8 +20,18 @@ Docker is the recommended method for deploying DocsGPT, providing a consistent a
## Run it with `docsgpt up`
The `docsgpt` Python package can set up and run the stack described below for
you. It needs Docker with Compose 2.24 or newer, and Python 3.12 or newer (uv
installs one when it is missing):
you. It needs Docker with Compose 2.24 or newer. The installer gets
[uv](https://docs.astral.sh/uv/), installs the package with it and runs
`docsgpt up`:
```bash
curl -fsSL https://docs.ac/install | bash # macOS and Linux
irm https://docs.ac/install.ps1 | iex # Windows (PowerShell)
```
Both scripts are attached to every [release](https://github.com/arc53/DocsGPT/releases)
as `install.sh` and `install.ps1`. To install the package yourself instead
(Python 3.12 or newer; uv brings one when it is missing):
```bash
uv tool install docsgpt # or: pipx install docsgpt
docs/content/changelog.mdx
+7
View File
@@ -13,6 +13,13 @@ request, and [Upgrading](/upgrading) covers the steps an existing deployment has
## Unreleased
### Install with one command
`curl -fsSL https://docs.ac/install | bash` on macOS and Linux, or `irm https://docs.ac/install.ps1 | iex`
in Windows PowerShell, installs uv and the `docsgpt` package and runs `docsgpt up`. Running it again
upgrades and keeps your settings. On Linux it offers to install Docker when it is missing. Both
scripts are attached to every release. See the [Quickstart](/quickstart).
### `docsgpt up` runs DocsGPT on Docker
The Python package now sets up and runs the Docker stack: `uv tool install docsgpt`, then
docs/content/quickstart.mdx
+73 -66
View File
@@ -1,40 +1,91 @@
---
title: Quickstart - Launching DocsGPT Web App
description: Get started with DocsGPT quickly by launching the web application using the setup script.
description: Install and start DocsGPT with one command, or from a clone with the setup script.
---
import { Callout } from 'nextra/components'
# Quickstart
**Prerequisites:**
* **Docker:** Ensure you have Docker installed and running on your system.
* **Docker:** DocsGPT runs on Docker, with Docker Compose 2.24 or newer. On macOS and Windows install [Docker Desktop](https://docs.docker.com/desktop/) (or [OrbStack](https://orbstack.dev) on macOS); on Linux, [Docker Engine](https://docs.docker.com/engine/install/). On Linux the installer offers to install Docker for you.
## Launching DocsGPT (macOS and Linux)
## Install with one command
The easiest way to launch DocsGPT is using the provided `setup.sh` script. This script automates the configuration process and offers several setup options.
**macOS and Linux:**
**Steps:**
```bash
curl -fsSL https://docs.ac/install | bash
```
1. **Download the DocsGPT Repository:**
**Windows (PowerShell):**
First, you need to download the DocsGPT repository to your local machine. You can do this using Git:
```powershell
irm https://docs.ac/install.ps1 | iex
```
The installer:
1. Checks for Docker.
2. Installs [uv](https://docs.astral.sh/uv/) if it is missing or too old. uv installs Python packages and brings its own Python when the system has none.
3. Installs the `docsgpt` Python package with `uv tool install`.
4. Runs `docsgpt up`, which asks two questions:
* **Who should reach DocsGPT:** only this computer; other machines on your network (plain HTTP, with an access token); or a domain name with HTTPS (a certificate from Let's Encrypt, with an access token).
* **Which model provider:** the DocsGPT public API (no key needed), OpenAI, Anthropic, Google Gemini, OpenRouter, Groq, or an OpenAI-compatible server such as Ollama or vLLM.
It then starts DocsGPT and prints its address, [http://localhost:7091](http://localhost:7091) for a local install. Settings and generated secrets are in `~/.docsgpt/server/.env`.
<Callout type="info">
To read the script before running it, download it first: `curl -fsSL https://docs.ac/install -o install.sh`, then `bash install.sh`. On Windows: `irm https://docs.ac/install.ps1 -OutFile install.ps1`, then `.\install.ps1`.
</Callout>
**Options.** Arguments after `bash -s --` go to `docsgpt up`, so a server can be set up without questions:
```bash
curl -fsSL https://docs.ac/install | bash -s -- --yes --domain docs.example.com --provider openai --api-key "$OPENAI_API_KEY"
```
`DOCSGPT_VERSION` installs a specific release, and `DOCSGPT_NO_MODIFY_PATH=1` leaves your shell profile alone. `docsgpt up --help` lists every option.
**Afterwards:**
| Command | What it does |
| --- | --- |
| `docsgpt status` | Version, address, and whether DocsGPT answers |
| `docsgpt logs -f` | Follow the logs |
| `docsgpt token` | The access token, for installs reachable beyond this computer |
| `docsgpt up --reconfigure` | Ask the setup questions again |
| `docsgpt upgrade` | Upgrade to the latest release, keeping your settings and data |
| `docsgpt down` | Stop DocsGPT |
| `docsgpt uninstall` | Remove it; `--purge` also deletes settings and data |
Running the install command again also upgrades. See [Run it with `docsgpt up`](/Deploying/Docker-Deploying#run-it-with-docsgpt-up) for the details.
## From a clone, with the setup script
To work from the source tree, for example to build the images yourself, use `setup.sh` (macOS and Linux) or `setup.ps1` (Windows).
1. **Clone the repository:**
```bash
git clone https://github.com/arc53/DocsGPT.git
cd DocsGPT
```
2. **Run the `setup.sh` script:**
Navigate to the DocsGPT directory in your terminal and execute the `setup.sh` script:
2. **Run the setup script:**
```bash
./setup.sh
```
3. **Follow the interactive setup:**
On Windows:
The `setup.sh` script will guide you through an interactive menu with the following options:
```powershell
PowerShell -ExecutionPolicy Bypass -File .\setup.ps1
```
3. **Follow the interactive setup:**
```
Welcome to DocsGPT Setup!
@@ -47,73 +98,29 @@ The easiest way to launch DocsGPT is using the provided `setup.sh` script. This
Choose option (1-5):
```
Let's break down each option:
* **1) Use DocsGPT Public API Endpoint (simple and free):** This is the simplest option to get started. It utilizes the DocsGPT public API, requiring no API keys or local model downloads.
* **1) Use DocsGPT Public API Endpoint (simple and free):** This is the simplest option to get started. It utilizes the DocsGPT public API, requiring no API keys or local model downloads. Choose this for a quick and easy setup.
* **2) Serve Local (with Ollama):** Runs a Large Language Model locally using [Ollama](https://ollama.com/). You'll be prompted to choose between CPU or GPU for Ollama and select a model to download.
* **2) Serve Local (with Ollama):** This option allows you to run a Large Language Model locally using [Ollama](https://ollama.com/). You'll be prompted to choose between CPU or GPU for Ollama and select a model to download. This is a good option for local processing and experimentation.
* **3) Connect Local Inference Engine:** If you already run a local inference engine like Llama.cpp, Text Generation Inference (TGI), vLLM, or others, choose this option and provide the connection details.
* **3) Connect Local Inference Engine:** If you are already running a local inference engine like Llama.cpp, Text Generation Inference (TGI), vLLM, or others, choose this option. You'll be asked to select your engine and provide the necessary connection details. This is for users with existing local LLM infrastructure.
* **4) Connect Cloud API Provider:** Connect DocsGPT to a Cloud API provider such as OpenAI, Google (Vertex AI/Gemini), Anthropic (Claude), Groq, HuggingFace Inference API, or Azure OpenAI. You will need an API key from your chosen provider.
* **4) Connect Cloud API Provider:** This option lets you connect DocsGPT to a commercial Cloud API provider such as OpenAI, Google (Vertex AI/Gemini), Anthropic (Claude), Groq, HuggingFace Inference API, or Azure OpenAI. You will need an API key from your chosen provider. Select this if you prefer to use a powerful cloud-based LLM.
* **5) Modify DocsGPT's source code and rebuild the Docker images locally.** Instead of pulling prebuilt images from Docker Hub, you build the backend and frontend from source, to customize how DocsGPT works internally or to run it in an environment without internet access.
* **5) Modify DocsGPT's source code and rebuild the Docker images locally.** Instead of pulling prebuilt images from Docker Hub or using the hosted/public API, you build the entire backend and frontend from source, customizing how DocsGPT works internally, or run it in an environment without internet access.
After selecting an option and providing any required information (like API keys or model names), the script configures your `.env` file and starts DocsGPT using Docker Compose.
After selecting an option and providing any required information (like API keys or model names), the script will configure your `.env` file and start DocsGPT using Docker Compose.
4. **Access DocsGPT in your browser:** open [http://localhost:5173/](http://localhost:5173/).
4. **Access DocsGPT in your browser:**
Once the setup is complete and Docker containers are running, navigate to [http://localhost:5173/](http://localhost:5173/) in your web browser to access the DocsGPT web application.
5. **Stopping DocsGPT:**
To stop DocsGPT, simply open a new terminal in the `DocsGPT` directory and run:
5. **Stopping DocsGPT:** in the `DocsGPT` directory, run the `docker compose down` command the script printed at the end, for example:
```bash
docker compose -f deployment/docker-compose-hub.yaml down
```
(or the specific `docker compose` command shown at the end of the `setup.sh` execution, which may include optional compose files depending on your choices).
## Launching DocsGPT (Windows)
**Important for Windows:** Ensure Docker Desktop is installed and running before you start. The script tries to start Docker if it is not running, but you may need to start it manually.
For Windows users, we provide a PowerShell script that offers the same functionality as the macOS/Linux setup script.
**Steps:**
1. **Download the DocsGPT Repository:**
First, you need to download the DocsGPT repository to your local machine. You can do this using Git:
```powershell
git clone https://github.com/arc53/DocsGPT.git
cd DocsGPT
```
2. **Run the `setup.ps1` script:**
Execute the PowerShell setup script:
```powershell
PowerShell -ExecutionPolicy Bypass -File .\setup.ps1
```
3. **Follow the interactive setup:**
Just like the Linux/macOS script, the PowerShell script will guide you through setting DocsGPT.
The script will handle environment configuration and start DocsGPT based on your selections.
4. **Access DocsGPT in your browser:**
Once the setup is complete and Docker containers are running, navigate to [http://localhost:5173/](http://localhost:5173/) in your web browser to access the DocsGPT web application.
5. **Stopping DocsGPT:**
To stop DocsGPT run the Docker Compose down command displayed at the end of the setup script's execution.
**Important for Windows:** Ensure Docker Desktop is installed and running correctly on your Windows system before proceeding. The script will attempt to start Docker if it's not running, but you may need to start it manually if there are issues.
**Alternative Method:**
If you prefer a more manual approach, you can follow our [Docker Deployment documentation](/Deploying/Docker-Deploying) for detailed instructions on setting up DocsGPT on Windows using Docker commands directly.
**Alternative Method:** To run the pre-built images with Docker Compose yourself, follow the [Docker Deployment documentation](/Deploying/Docker-Deploying).
## Advanced Configuration