Open Bedrock Server

A unified, provider-agnostic chat completions API server supporting OpenAI and AWS Bedrock.

Find this useful? Star the repo to follow updates and show support!

Install from PyPI — pip install open-bedrock-server and run bedrock-chat serve. See CLI Reference for all options.

Quick Start

Installation

# From PyPI
pip install open-bedrock-server

# Or from source
git clone https://github.com/teabranch/open-bedrock-server.git
cd open-bedrock-server
uv pip install -e .

Configure

bedrock-chat config set

Or set environment variables:

export OPENAI_API_KEY=sk-your-key
export AWS_PROFILE=your-profile
export API_KEY=your-server-auth-key

Run

bedrock-chat serve --host 0.0.0.0 --port 8000

Verify:

curl http://localhost:8000/health

Basic Usage

curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": false
  }'

Unified Endpoint

The /v1/chat/completions endpoint is the only endpoint you need. It:

Auto-detects your input format (OpenAI, Bedrock Claude, Bedrock Titan)
Routes to the appropriate provider based on model ID
Converts between formats as needed
Streams responses in real-time when requested

Format Combinations

Input Format	Output Format	Use Case	Streaming
OpenAI	OpenAI	Standard OpenAI usage	Yes
OpenAI	Bedrock Claude	OpenAI clients to Bedrock response	Yes
OpenAI	Bedrock Titan	OpenAI clients to Titan response	Yes
Bedrock Claude	OpenAI	Bedrock clients to OpenAI response	Yes
Bedrock Claude	Bedrock Claude	Claude format preserved	Yes
Bedrock Titan	OpenAI	Titan clients to OpenAI response	Yes
Bedrock Titan	Bedrock Titan	Titan format preserved	Yes

Documentation

Core

Getting Started - Installation, setup, and first steps
API Reference - Complete API documentation
CLI Reference - Command-line interface guide

Advanced Features

Knowledge Bases (RAG) - Bedrock Knowledge Bases integration
Files API - File upload and management capabilities

Guides

Usage Guide - Programming examples and use cases
AWS Authentication - AWS credential configuration
Architecture - System design and architecture
Core Components - Detailed component documentation
Testing - Testing strategies and coverage
Packaging - Building and distributing the package

Development

Development Guide - Extending and customizing the server
Test Suite - Test suite organization
Real API Testing - Real API integration tests

Key Features

Unified Interface

Single Endpoint: /v1/chat/completions handles everything
Auto-Detection: Intelligent format detection
Model-Based Routing: Automatic provider selection
Format Conversion: Seamless translation between formats

File Query System

File Upload: Upload documents to S3 storage with OpenAI-compatible API
Smart Processing: Automatic content extraction from CSV, JSON, HTML, XML, Markdown, and text files
Chat Integration: Use file_ids parameter to include file content as context in conversations
File Management: Complete CRUD operations for uploaded files

Enterprise Ready

Authentication: Secure API key-based authentication
Streaming: Real-time response streaming
Error Handling: Comprehensive error management
Monitoring: Request/response logging and health checks

Developer Friendly

CLI Tools: Interactive chat, configuration, and server management
OpenAI Compatible: Drop-in replacement for OpenAI Chat Completions API
Extensible: Easy to add new providers and formats
Well Tested: Comprehensive test coverage

Quick Links

License

This project is licensed under the MIT License - see the LICENSE file for details.