@aj-archipelago/cortex/config/default.example.json

Cortex is a GraphQL API for AI. It provides a simple, extensible interface for using AI services from OpenAI, Azure and others.

{
    "defaultModelName": "oai-gpturbo",
    "models": {
        "azure-translate": {
            "type": "AZURE-TRANSLATE",
            "url": "https://api.cognitive.microsofttranslator.com/translate?api-version=3.0",
            "headers": {
                "Ocp-Apim-Subscription-Key": "{{ARCHIPELAGO_TRANSLATE_KEY}}",
                "Ocp-Apim-Subscription-Region": "eastus",
                "Content-Type": "application/json"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 2000
        },

        "gemini-pro-chat": {
            "type": "GEMINI-CHAT",
            "url": "https://us-central1-aiplatform.googleapis.com/v1/projects/project-id/locations/us-central1/publishers/google/models/gemini-pro:streamGenerateContent",
            "headers": {
                "Content-Type": "application/json"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 32768,
            "maxReturnTokens": 8192,
            "supportsStreaming": true
        },
        "gemini-pro-vision": {
            "type": "GEMINI-VISION",
            "url": "https://us-central1-aiplatform.googleapis.com/v1/projects/project-id/locations/us-central1/publishers/google/models/gemini-pro-vision:streamGenerateContent",
            "headers": {
                "Content-Type": "application/json"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 32768,
            "maxReturnTokens": 2048,
            "supportsStreaming": true
        },
        "gemini-pro-15-vision": {
            "type": "GEMINI-VISION",
            "url": "https://us-central1-aiplatform.googleapis.com/v1/projects/project-id/locations/us-central1/publishers/google/models/gemini-1.5-pro:streamGenerateContent",
            "headers": {
                "Content-Type": "application/json"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 1048576,
            "maxReturnTokens": 2048,
            "supportsStreaming": true
        },
        "gemini-pro-25-vision": {
            "type": "GEMINI-VISION",
            "url": "https://us-central1-aiplatform.googleapis.com/v1/projects/project-id/locations/us-central1/publishers/google/models/gemini-2.5-pro:streamGenerateContent",
            "headers": {
                "Content-Type": "application/json"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 1048576,
            "maxReturnTokens": 65536,
            "supportsStreaming": true
        },
        "claude-3-haiku-vertex": {
            "type": "CLAUDE-3-VERTEX",
            "url": "https://us-central1-aiplatform.googleapis.com/v1/projects/project-id/locations/us-central1/publishers/anthropic/models/claude-3-haiku@20240307",
            "headers": {
                "Content-Type": "application/json"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 200000,
            "maxReturnTokens": 2048,
            "supportsStreaming": true
        },
        "claude-35-sonnet-vertex": {
            "type": "CLAUDE-3-VERTEX",
            "url": "https://us-central1-aiplatform.googleapis.com/v1/projects/project-id/locations/us-central1/publishers/anthropic/models/claude-3-5-sonnet@20240229",
            "headers": {
                "Content-Type": "application/json"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 200000,
            "maxReturnTokens": 2048,
            "supportsStreaming": true
        },
        "oai-gpturbo": {
            "type": "OPENAI-CHAT",
            "url": "https://api.openai.com/v1/chat/completions",
            "headers": {
                "Authorization": "Bearer {{OPENAI_API_KEY}}",
                "Content-Type": "application/json"
            },
            "params": {
                "model": "gpt-3.5-turbo"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 8192
        },
        "oai-gpt4": {
            "type": "OPENAI-CHAT",
            "url": "https://api.openai.com/v1/chat/completions",
            "headers": {
                "Authorization": "Bearer {{OPENAI_API_KEY}}",
                "Content-Type": "application/json"
            },
            "params": {
                "model": "gpt-4"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 8192
        },
        "oai-gpt4-32": {
            "type": "OPENAI-CHAT",
            "url": "https://api.openai.com/v1/chat/completions",
            "headers": {
                "Authorization": "Bearer {{OPENAI_API_KEY}}",
                "Content-Type": "application/json"
            },
            "params": {
                "model": "gpt-4-32"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 32768
        },
        "oai-gpt4o": {
            "type": "OPENAI-VISION",
            "url": "https://api.openai.com/v1/chat/completions",
            "headers": {
                "Authorization": "Bearer {{OPENAI_API_KEY}}",
                "Content-Type": "application/json"
            },
            "params": {
                "model": "gpt-4o"
            },
            "requestsPerSecond": 10,
            "maxTokenLength": 131072,
            "maxReturnTokens": 4096,
            "supportsStreaming": true
        },
        "local-llama13B": {
            "type": "LOCAL-CPP-MODEL",
            "executablePath": "../llm/llama.cpp/main",
            "args": [
                "-m", "../llm/llama.cpp/models/13B/ggml-model-q4_0.bin",
                "--repeat_penalty", "1.0",
                "--keep", "0",
                "-t", "8",
                "--mlock"
            ],
            "requestsPerSecond": 10,
            "maxTokenLength": 1024
        }
    },
    "enableCache": false,
    "enableRestEndpoints": false,
    "subscriptionKeepAlive": 10000
}