openapi.json

{
  "openapi": "3.0.3",
  "info": {
    "title": "Text Generation Inference",
    "description": "Text Generation Webserver",
    "contact": {
      "name": "Olivier Dehaene",
      "email": "olivier@huggingface.co"
    },
    "license": {
      "name": "Apache 2.0",
      "url": "https://www.apache.org/licenses/LICENSE-2.0"
    },
    "version": "0.3.0"
  },
  "paths": {
    "/generate": {
      "post": {
        "tags": [
          "Text Generation Inference"
        ],
        "summary": "Generate tokens",
        "description": "Generate tokens",
        "operationId": "generate",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/GenerateRequest"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "description": "Generated Text",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/GenerateResponse"
                }
              }
            }
          },
          "422": {
            "description": "Input validation error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "error": "Input validation error"
                }
              }
            }
          },
          "424": {
            "description": "Generation Error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "error": "Request failed during generation"
                }
              }
            }
          },
          "429": {
            "description": "Model is overloaded",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "error": "Model is overloaded"
                }
              }
            }
          },
          "500": {
            "description": "Incomplete generation",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "error": "Incomplete generation"
                }
              }
            }
          }
        },
        "deprecated": false
      }
    },
    "/generate_stream": {
      "post": {
        "tags": [
          "Text Generation Inference"
        ],
        "summary": "Generate a stream of token using Server-Sent Events",
        "description": "Generate a stream of token using Server-Sent Events",
        "operationId": "generate_stream",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/GenerateRequest"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "description": "Generated Text",
            "content": {
              "text/event-stream": {
                "schema": {
                  "$ref": "#/components/schemas/StreamResponse"
                }
              }
            }
          },
          "422": {
            "description": "Input validation error",
            "content": {
              "text/event-stream": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "error": "Input validation error"
                }
              }
            }
          },
          "424": {
            "description": "Generation Error",
            "content": {
              "text/event-stream": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "error": "Request failed during generation"
                }
              }
            }
          },
          "429": {
            "description": "Model is overloaded",
            "content": {
              "text/event-stream": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "error": "Model is overloaded"
                }
              }
            }
          },
          "500": {
            "description": "Incomplete generation",
            "content": {
              "text/event-stream": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorResponse"
                },
                "example": {
                  "error": "Incomplete generation"
                }
              }
            }
          }
        },
        "deprecated": false
      }
    },
    "/metrics": {
      "get": {
        "tags": [
          "Text Generation Inference"
        ],
        "summary": "Prometheus metrics scrape endpoint",
        "description": "Prometheus metrics scrape endpoint",
        "operationId": "metrics",
        "responses": {
          "200": {
            "description": "Prometheus Metrics",
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            }
          }
        },
        "deprecated": false
      }
    }
  },
  "components": {
    "schemas": {
      "Details": {
        "type": "object",
        "required": [
          "finish_reason",
          "generated_tokens"
        ],
        "properties": {
          "finish_reason": {
            "$ref": "#/components/schemas/FinishReason"
          },
          "generated_tokens": {
            "type": "integer",
            "format": "int32",
            "example": 1
          },
          "prefill": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/Token"
            }
          },
          "seed": {
            "type": "integer",
            "format": "int64",
            "example": 42
          },
          "tokens": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/Token"
            }
          }
        }
      },
      "ErrorResponse": {
        "type": "object",
        "required": [
          "error"
        ],
        "properties": {
          "error": {
            "type": "string"
          }
        }
      },
      "FinishReason": {
        "type": "string",
        "enum": [
          "length",
          "eos_token",
          "stop_sequence"
        ]
      },
      "GenerateParameters": {
        "type": "object",
        "properties": {
          "details": {
            "type": "boolean",
            "default": "true"
          },
          "do_sample": {
            "type": "boolean",
            "default": "false",
            "example": true
          },
          "max_new_tokens": {
            "type": "integer",
            "format": "int32",
            "default": "20",
            "exclusiveMaximum": 512.0,
            "exclusiveMinimum": 0.0
          },
          "repetition_penalty": {
            "type": "number",
            "format": "float",
            "default": "null",
            "example": 1.03,
            "nullable": true,
            "exclusiveMinimum": 0.0
          },
          "seed": {
            "type": "integer",
            "format": "int64"
          },
          "stop": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "example": [
              "photographer"
            ],
            "maxItems": 4
          },
          "temperature": {
            "type": "number",
            "format": "float",
            "default": "null",
            "example": 0.5,
            "nullable": true,
            "exclusiveMinimum": 0.0
          },
          "top_k": {
            "type": "integer",
            "format": "int32",
            "default": "null",
            "example": 10,
            "nullable": true,
            "exclusiveMinimum": 0.0
          },
          "top_p": {
            "type": "number",
            "format": "float",
            "default": "null",
            "example": 0.95,
            "nullable": true,
            "maximum": 1.0,
            "exclusiveMinimum": 0.0
          }
        }
      },
      "GenerateRequest": {
        "type": "object",
        "required": [
          "inputs"
        ],
        "properties": {
          "inputs": {
            "type": "string",
            "example": "My name is Olivier and I"
          },
          "parameters": {
            "$ref": "#/components/schemas/GenerateParameters"
          }
        }
      },
      "GenerateResponse": {
        "type": "object",
        "required": [
          "generated_text"
        ],
        "properties": {
          "details": {
            "$ref": "#/components/schemas/Details"
          },
          "generated_text": {
            "type": "string",
            "example": "test"
          }
        }
      },
      "StreamDetails": {
        "type": "object",
        "required": [
          "finish_reason",
          "generated_tokens"
        ],
        "properties": {
          "finish_reason": {
            "$ref": "#/components/schemas/FinishReason"
          },
          "generated_tokens": {
            "type": "integer",
            "format": "int32",
            "example": 1
          },
          "seed": {
            "type": "integer",
            "format": "int64",
            "example": 42
          }
        }
      },
      "StreamResponse": {
        "type": "object",
        "required": [
          "token"
        ],
        "properties": {
          "details": {
            "$ref": "#/components/schemas/StreamDetails"
          },
          "generated_text": {
            "type": "string",
            "default": "null",
            "example": "test",
            "nullable": true
          },
          "token": {
            "$ref": "#/components/schemas/Token"
          }
        }
      },
      "Token": {
        "type": "object",
        "required": [
          "id",
          "text",
          "logprob"
        ],
        "properties": {
          "id": {
            "type": "integer",
            "format": "int32",
            "example": 0
          },
          "logprob": {
            "type": "number",
            "format": "float",
            "example": -0.34,
            "nullable": true
          },
          "text": {
            "type": "string",
            "example": "test"
          }
        }
      }
    }
  },
  "tags": [
    {
      "name": "Text Generation Inference",
      "description": "Hugging Face Text Generation Inference API"
    }
  ]
}