No description
  • Python 98%
  • Shell 1.4%
  • Dockerfile 0.6%
Find a file
2026-03-15 11:49:51 +01:00
example fix: improve state machine, reformat 2026-03-15 11:49:51 +01:00
ollama_prox fix: improve state machine, reformat 2026-03-15 11:49:51 +01:00
tests feat: add full worker dissociation from the proxy (#2) 2025-11-30 12:59:29 +00:00
.gitignore feat: add new user tool 2025-09-05 08:10:31 +02:00
build.sh feat: enforce keep_alive whatever the user says 2025-09-05 09:17:38 +02:00
CHANGELOG.md 1.18.0 2026-03-10 15:08:06 +01:00
Dockerfile chore: add Dockerfile for deployment 2025-09-05 09:00:11 +02:00
new-release.sh build: upgraded new-release with options 2026-01-12 07:42:19 +01:00
poetry.lock fix: update dependencies 2026-02-14 09:17:10 +01:00
pyproject.toml 1.18.0 2026-03-10 15:08:06 +01:00
pytest.ini feat: add full worker dissociation from the proxy (#2) 2025-11-30 12:59:29 +00:00
README.md doc(README): update the readme to add more launch instructions 2025-11-10 13:41:14 +01:00

Ollama Proxy Server

A secure, load-balanced proxy server for Ollama, designed to route requests to multiple Ollama instances while enforcing authentication, rate limiting, and monitoring.


Features

  • Load Balancing Distributes requests across multiple Ollama servers.
  • Authentication Secure API access with bcrypt-hashed keys.
  • Queue Management Limits concurrent requests to prevent overload.
  • Prometheus Metrics Monitor request counts, queue sizes, and active connections.
  • Logging Detailed request logging for auditing.
  • Allowed Paths Restricts access to specific Ollama endpoints.

Requirements

  • Python 3.11+
  • FastAPI
  • Uvicorn
  • Prometheus Client
  • bcrypt (for key hashing)

Installation

1. Clone the Repository

git clone https://git.aquila-consortium.org/guilhem_lavaux/ollama_proxy_2
cd ollama_proxy_2
poetry shell   # need the poetry shell plugin
poetry install
ollama_proxy

The API server is now running on the advertised port.