Installation Options

Package Install

This is the recommended installation method for developers who want to run PrivateGPT against an existing LLM server (Ollama, LM Studio, etc.) without cloning the repository.

PrivateGPT package files are hosted at https://wheels.privategpt.dev/packages/. uv uses that location to find the PrivateGPT release and continues to resolve public dependencies from PyPI by default.

Install

$brew tap zylon-ai/tap
$brew install private-gpt

Upgrade:

$brew upgrade private-gpt

Python 3.11 is required. PrivateGPT does not support Python 3.10 or 3.12+.

Verify

$command -v private-gpt

Run

After installing, set OPENAI_API_BASE to your LLM server and start:

$OPENAI_API_BASE=http://localhost:11434/v1 private-gpt serve

PrivateGPT starts on port 8080 by default. Change it with private-gpt serve --port <port>.

Data storage

All application data (vector store, ingested documents, models, caches) is stored under a single home directory:

PlatformDefault path
macOS / Linux~/.local/share/private-gpt/
Windows%LOCALAPPDATA%\private-gpt\
Docker/home/worker/app/ (fixed)

Override the location with PGPT_HOME:

$PGPT_HOME=/data/private-gpt private-gpt serve

Key environment variables

VariableDefaultDescription
OPENAI_API_BASEhttps://api.openai.com/v1Base URL of your OpenAI-compatible LLM server
OPENAI_API_KEY(empty)API key, if your server requires one
OPENAI_EMBEDDING_API_BASEsame as OPENAI_API_BASEOverride for the embeddings endpoint
PORT8080Port the server listens on (also settable via private-gpt serve --port)
PGPT_HOME~/.local/share/private-gptRoot directory for all local data (vector store, models, caches)
PGPT_LLM_AUTO_DISCOVER_MODELStrueDiscover LLM models from /v1/models on startup

What’s next?