AI API Examples

This repository contains examples and documentation for integrating with AI Chat APIs. Examples are provided for both OpenWebUI (local/self-hosted) and Expedient AI Cloud Gateway.

OpenWebUI Quick Start (v3)

For OpenWebUI v0.6.32+ (local or self-hosted deployments)

Get your API key or JWT token from OpenWebUI:
- Click on your User icon (top right)
- Select Settings
- Go to Account tab
- Under API Keys section, click Show to reveal your keys
- Copy either the API Key (sk-...) or JWT Token (eyJ...)

Create and activate a virtual environment:

# Create virtual environment
python -m venv venv

# Activate virtual environment
# On macOS/Linux:
source venv/bin/activate

# On Windows:
venv\Scripts\activate

Install dependencies: pip install -r requirements.txt
Update the configuration in the v3 example files:
- Set chat_url to your OpenWebUI URL (e.g., "http://localhost:3000")
- Set api_key or jwt_token with your credentials

Run the OpenWebUI examples:

# Quick test (simplest)
python v3_quick_start.py

# Standard streaming with API Key
python v3_example.py

# Using JWT Token authentication
python v3_example_jwt.py

Expedient AI Cloud Gateway Quick Start (v1)

For Expedient AI hosted service

Get your API key from Expedient AI
Create and activate a virtual environment (see above)
Install dependencies: pip install -r requirements.txt
Update the API key in the example file that you are running

Run the examples:

# Quick test (simplest)
python quick_start.py

# Standard streaming models
python example.py

# Reasoning models (for complex analysis)
python reasoning_example.py

# Web access models with citations (for live web search)
python citation_example.py

# OR use cURL commands directly (see curl.md)
curl -X POST "[ ENTER_CHAT_URL_HERE ]/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer [ ENTER_API_KEY_HERE ]" \
  -d '{"model": "gpt-4.1", "messages": [{"role": "user", "content": "Hello!"}]}'

Files in this Repository

OpenWebUI Examples (v3)

📄 `v3_quick_start.py`

Minimal OpenWebUI example for immediate testing. Features:

Ultra-simple code (~40 lines)
OpenWebUI API endpoint configuration
Perfect for local/self-hosted OpenWebUI instances
Copy-paste ready

📄 `v3_example.py`

Complete OpenWebUI streaming example with API Key authentication. Features:

Real-time streaming responses
API Key authentication (recommended for scripts)
Detailed comments and explanations
Works with any OpenWebUI-compatible model

📄 `v3_example_jwt.py`

OpenWebUI streaming example with JWT Token authentication. Features:

Same streaming functionality as v3_example.py
JWT Token authentication (session-based)
Demonstrates alternative authentication method
Useful for web applications

Expedient AI Cloud Examples (v1)

📄 `quick_start.py`

Minimal example for immediate testing. Features:

Ultra-simple code (30 lines)
No comments or explanations
Just the essentials for quick API testing
Perfect for copy-paste and quick modifications

📄 `example.py`

Complete Python script demonstrating streaming AI responses with standard models. Features:

Real-time streaming responses
Standard AI models (GPT, Claude, Gemini, Perplexity)
Detailed comments and explanations
Production-ready streaming implementation

📄 `reasoning_example.py`

Advanced reasoning models with animated thinking indicators. Features:

Complex analytical problem solving
Step-by-step reasoning processes
Animated thinking dots while processing
Models: o4-mini, o3, Claude 4, Gemini 2.5

📄 `citation_example.py`

Perplexity web reasoning models with real-time data and citations. Features:

Real-time web search during AI responses
Current events and fact-checking capabilities
Automatic citation detection and reporting
Animated search indicators

Documentation

📄 `postman.md`

Complete Postman collection documentation with:

8 ready-to-use API request examples
All supported AI models and providers
Parameter explanations and usage tips
Import instructions for Postman

📄 `curl.md`

Command-line cURL examples for developers and scripters. Features:

8 cURL commands matching all Postman examples
Advanced options and streaming processing
Environment variable setup for security
Batch processing and error handling examples

📄 `.gitignore`

Python-specific gitignore file that excludes:

Virtual environments
API keys and sensitive files
Python cache files
IDE configuration files

Supported AI Providers

Both OpenWebUI and Expedient AI Cloud Gateway support models from multiple providers:

OpenAI: GPT-4.1, GPT-5, o3, o4-mini (reasoning), GPT-4o, GPT-4o-mini, GPT-3.5-turbo
Anthropic: Claude-Sonnet-4, Claude-Sonnet-4.5, Claude-3.7-Sonnet, Claude-3-Haiku, Claude-3-Opus
Google: Gemini-2.5-Pro, Gemini-2.5-Flash, Gemini-1.5-Pro, Gemini-1.5-Flash
Perplexity: Sonar-Pro, Sonar-Reasoning-Pro, Sonar (web-connected with real-time data)

Note: Available models depend on your OpenWebUI configuration or Expedient AI subscription.

Key Features

✅ Unified Interface - One API for multiple AI providers
✅ Real-time Streaming - See responses as they're generated
✅ Multiple Models - Choose the best model for your use case
✅ Web Access & Citations - Real-time data with source transparency
✅ Quick Start - Ultra-simple 30-line example for immediate testing
✅ Enterprise Ready - Production-grade error handling
✅ Easy Integration - Simple REST API with JSON

API Endpoints

OpenWebUI

http://localhost:3000/api/v1/chat/completions

Or replace localhost:3000 with your OpenWebUI instance URL.

Expedient AI Cloud Gateway

[ ENTER_CHAT_URL_HERE ]/chat/completions

Authentication

OpenWebUI

Get your credentials from OpenWebUI:

Click on your User icon → Settings → Account
Under API Keys, click Show
Copy either:
- API Key (sk-...) - Recommended for scripts and automation
- JWT Token (eyJ...) - For session-based authentication

All requests require a Bearer token:

Authorization: Bearer YOUR_API_KEY_OR_JWT_TOKEN

Expedient AI Cloud Gateway

All requests require a Bearer token in the Authorization header:

Authorization: Bearer [ ENTER_API_KEY_HERE ]

Basic Usage Examples

OpenWebUI

import requests
import json

# Simple streaming request to OpenWebUI
response = requests.post(
    "http://localhost:3000/api/v1/chat/completions",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer YOUR_API_KEY"
    },
    json={
        "model": "gpt-4.1",
        "messages": [{"role": "user", "content": "Hello, world!"}],
        "stream": True
    },
    stream=True
)

# Process streaming response
for line in response.iter_lines(decode_unicode=True):
    if line and line.startswith("data: "):
        data_str = line[6:]
        if data_str.strip() == "[DONE]":
            break
        try:
            data = json.loads(data_str)
            if "choices" in data and data["choices"]:
                delta = data["choices"][0].get("delta", {})
                if "content" in delta:
                    print(delta["content"], end="", flush=True)
        except:
            continue

Expedient AI Cloud Gateway

import requests
import json

# Simple streaming request to Expedient AI
response = requests.post(
    "[ ENTER_CHAT_URL_HERE ]/chat/completions",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer [ ENTER_API_KEY_HERE ]"
    },
    json={
        "model": "gpt-4.1",
        "messages": [{"role": "user", "content": "Hello, world!"}],
        "stream": True
    },
    stream=True
)

# Process streaming response (same as OpenWebUI)
for line in response.iter_lines(decode_unicode=True):
    if line and line.startswith("data: "):
        data_str = line[6:]
        if data_str.strip() == "[DONE]":
            break
        try:
            data = json.loads(data_str)
            if "choices" in data and data["choices"]:
                delta = data["choices"][0].get("delta", {})
                if "content" in delta:
                    print(delta["content"], end="", flush=True)
        except:
            continue

Getting Started

Prerequisites

Python 3.6 or higher
requests library (pip install requests)
Either:
- Running OpenWebUI instance (v0.6.32+), OR
- Valid Expedient AI API key

Installation

Clone this repository

Create and activate a virtual environment:

# Create virtual environment
python -m venv venv

# Activate virtual environment
# On macOS/Linux:
source venv/bin/activate

# On Windows:
venv\Scripts\activate

Install dependencies:
```
pip install -r requirements.txt
```

For OpenWebUI Users

Get your API key from OpenWebUI: User → Settings → Account → API Keys → Show
Update chat_url and api_key in the v3 scripts

Run the OpenWebUI examples:

python v3_quick_start.py   # or v3_example.py or v3_example_jwt.py

For Expedient AI Users

Copy your API key from the Expedient AI dashboard
Update the api_key variable in the script you want to use

Run the examples:

# Quick test
python quick_start.py

# Standard streaming models  
python example.py

# Reasoning models
python reasoning_example.py

# Web search with citations
python citation_example.py

Model Selection Guide

Choose the right model for your needs:

Use Case	Recommended Models
Advanced Reasoning & Logic	`o4-mini`, `claude-sonnet-4-20250514`, `gemini/gemini-2.5-pro`
Complex Analysis	`gpt-4.1`, `gpt-4o`, `claude-3-7-sonnet-20250219`, `gemini/gemini-1.5-pro`
Large Text Processing	`gemini/gemini-2.5-flash` (1M+ token context)
Creative Writing	`claude-sonnet-4-20250514`, `claude-3-7-sonnet-20250219`, `gpt-4o`
Code Generation	`gpt-4.1`, `claude-sonnet-4-20250514`, `gpt-4o`
Fast Responses	`gpt-4o-mini`, `claude-3-haiku-20240307`, `gemini/gemini-1.5-flash`
Current Events & Web Data	`perplexity/sonar-reasoning-pro`, `perplexity/sonar-pro`
General Purpose	`gpt-4.1` (default), `gpt-3.5-turbo`

Documentation

OpenWebUI (v3)

v3 Quick Start - Minimal OpenWebUI example
v3 API Key Example - Detailed OpenWebUI implementation with API key
v3 JWT Example - OpenWebUI with JWT token authentication

Expedient AI Cloud Gateway (v1)

Postman Collection - Complete API testing examples
cURL Examples - Command-line examples for terminal and scripts
Quick Start - Minimal example for immediate testing
Standard Streaming Example - Detailed implementation with comments
Reasoning Example - Advanced reasoning with thinking animation
Citation Example - Web search with real-time citations
Live Swagger API Documentation - Visit [ ENTER_CHAT_URL_HERE ]/docs in your browser for interactive API documentation
API Documentation - Contact Expedient AI for detailed API docs

Support

For technical support and API access:

Website: Expedient AI
Documentation: See postman.md for comprehensive examples
Issues: Use this repository's issue tracker for code-related questions

Security Notes

🔒 Never commit API keys to version control
🔒 Use environment variables for production deployments
🔒 Rotate API keys regularly
🔒 Monitor API usage and costs

License

This example code is provided for demonstration purposes. Please check with Expedient AI for licensing terms for the API service itself.

Name		Name	Last commit message	Last commit date
Latest commit History 8 Commits
.gitignore		.gitignore
README.md		README.md
citation_example.py		citation_example.py
curl.md		curl.md
example.py		example.py
exp-ai-api-examples.code-workspace		exp-ai-api-examples.code-workspace
postman.md		postman.md
quick_start.py		quick_start.py
reasoning_example.py		reasoning_example.py
requirements.txt		requirements.txt
v3_example.py		v3_example.py
v3_example_jwt.py		v3_example_jwt.py
v3_quick_start.py		v3_quick_start.py

Expedient/exp-ai-api-examples

Folders and files

Latest commit

History

Repository files navigation

AI API Examples

OpenWebUI Quick Start (v3)

Expedient AI Cloud Gateway Quick Start (v1)

Files in this Repository

OpenWebUI Examples (v3)

📄 v3_quick_start.py

📄 v3_example.py

📄 v3_example_jwt.py

Expedient AI Cloud Examples (v1)

📄 quick_start.py

📄 example.py

📄 reasoning_example.py

📄 citation_example.py

Documentation

📄 postman.md

📄 curl.md

📄 .gitignore

Supported AI Providers

Key Features

API Endpoints

OpenWebUI

Expedient AI Cloud Gateway

Authentication

OpenWebUI

Expedient AI Cloud Gateway

Basic Usage Examples

OpenWebUI

Expedient AI Cloud Gateway

Getting Started

Prerequisites

Installation

For OpenWebUI Users

For Expedient AI Users

Model Selection Guide

Documentation

OpenWebUI (v3)

Expedient AI Cloud Gateway (v1)

Support

Security Notes

License

About

Resources

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Languages

📄 `v3_quick_start.py`

📄 `v3_example.py`

📄 `v3_example_jwt.py`

📄 `quick_start.py`

📄 `example.py`

📄 `reasoning_example.py`

📄 `citation_example.py`

📄 `postman.md`

📄 `curl.md`

📄 `.gitignore`

Packages