@llm_endpoint = http://localhost:12000 @openai_endpoint = https://api.openai.com @access_key = {{$dotenv OPENAI_API_KEY}} ### openai request POST {{openai_endpoint}}/v1/chat/completions HTTP/1.1 Content-Type: application/json Authorization: Bearer {{access_key}} { "messages": [ { "role": "user", "content": "hello" } ], "model": "gpt-4o-mini", "stream": true } ### openai request (streaming) POST {{openai_endpoint}}/v1/chat/completions HTTP/1.1 Content-Type: application/json Authorization: Bearer {{access_key}} { "messages": [ { "role": "user", "content": "hello" } ], "model": "gpt-4o-mini", "stream": true } ### llm gateway request POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1 Content-Type: application/json { "messages": [ { "role": "user", "content": "hello" } ] } ### llm gateway request (streaming) POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1 Content-Type: application/json { "messages": [ { "role": "user", "content": "hello" } ], "stream": true } ### llm gateway request (provider hint) POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1 Content-Type: application/json x-arch-llm-provider-hint: gpt-3.5-turbo-0125 { "messages": [ { "role": "user", "content": "hello" } ] } ### llm gateway request with function calling (default target) POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1 Content-Type: application/json { "stream": true, "model": "None", "messages": [ { "role": "user", "content": "how is the weather in seattle" } ], "tools": [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get current weather at a location.", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The location to get the weather for", "format": "City, State" }, "unit": { "type": "string", "description": "The unit to return the weather in.", "enum": ["celsius", "fahrenheit"], "default": "celsius" }, "days": { "type": "string", "description": "The number of days for the request." } }, "required": ["location", "days"] } } } ] }