oracle-ads 2.13.9rc0__py3-none-any.whl → 2.13.10__py3-none-any.whl

ads/templates/schemas/openapi.json

@@ -0,0 +1,1740 @@
+{
+  "components": {
+    "schemas": {
+      "ClassifierModel": {
+        "properties": {
+          "id2label": {
+            "additionalProperties": {
+              "type": "string"
+            },
+            "example": {
+              "0": "LABEL"
+            },
+            "type": "object"
+          },
+          "label2id": {
+            "additionalProperties": {
+              "minimum": 0,
+              "type": "integer"
+            },
+            "example": {
+              "LABEL": 0
+            },
+            "type": "object"
+          }
+        },
+        "required": [
+          "id2label",
+          "label2id"
+        ],
+        "type": "object"
+      },
+      "DecodeRequest": {
+        "properties": {
+          "ids": {
+            "$ref": "#/components/schemas/InputIds"
+          },
+          "skip_special_tokens": {
+            "default": "true",
+            "example": "true",
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "ids"
+        ],
+        "type": "object"
+      },
+      "DecodeResponse": {
+        "example": [
+          "test"
+        ],
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "EmbedAllRequest": {
+        "properties": {
+          "inputs": {
+            "$ref": "#/components/schemas/Input"
+          },
+          "prompt_name": {
+            "default": "null",
+            "description": "The name of the prompt that should be used by for encoding. If not set, no prompt\nwill be applied.\n\nMust be a key in the `sentence-transformers` configuration `prompts` dictionary.\n\nFor example if ``prompt_name`` is \"query\" and the ``prompts`` is {\"query\": \"query: \", ...},\nthen the sentence \"What is the capital of France?\" will be encoded as\n\"query: What is the capital of France?\" because the prompt text will be prepended before\nany text to encode.",
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          },
+          "truncate": {
+            "default": "false",
+            "example": "false",
+            "nullable": true,
+            "type": "boolean"
+          },
+          "truncation_direction": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationDirection"
+              }
+            ],
+            "default": "right"
+          }
+        },
+        "required": [
+          "inputs"
+        ],
+        "type": "object"
+      },
+      "EmbedAllResponse": {
+        "example": [
+          [
+            [
+              0.0,
+              1.0,
+              2.0
+            ]
+          ]
+        ],
+        "items": {
+          "items": {
+            "items": {
+              "format": "float",
+              "type": "number"
+            },
+            "type": "array"
+          },
+          "type": "array"
+        },
+        "type": "array"
+      },
+      "EmbedRequest": {
+        "properties": {
+          "inputs": {
+            "$ref": "#/components/schemas/Input"
+          },
+          "normalize": {
+            "default": "true",
+            "example": "true",
+            "type": "boolean"
+          },
+          "prompt_name": {
+            "default": "null",
+            "description": "The name of the prompt that should be used by for encoding. If not set, no prompt\nwill be applied.\n\nMust be a key in the `sentence-transformers` configuration `prompts` dictionary.\n\nFor example if ``prompt_name`` is \"query\" and the ``prompts`` is {\"query\": \"query: \", ...},\nthen the sentence \"What is the capital of France?\" will be encoded as\n\"query: What is the capital of France?\" because the prompt text will be prepended before\nany text to encode.",
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          },
+          "truncate": {
+            "default": "false",
+            "example": "false",
+            "nullable": true,
+            "type": "boolean"
+          },
+          "truncation_direction": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationDirection"
+              }
+            ],
+            "default": "right"
+          }
+        },
+        "required": [
+          "inputs"
+        ],
+        "type": "object"
+      },
+      "EmbedResponse": {
+        "example": [
+          [
+            0.0,
+            1.0,
+            2.0
+          ]
+        ],
+        "items": {
+          "items": {
+            "format": "float",
+            "type": "number"
+          },
+          "type": "array"
+        },
+        "type": "array"
+      },
+      "EmbedSparseRequest": {
+        "properties": {
+          "inputs": {
+            "$ref": "#/components/schemas/Input"
+          },
+          "prompt_name": {
+            "default": "null",
+            "description": "The name of the prompt that should be used by for encoding. If not set, no prompt\nwill be applied.\n\nMust be a key in the `sentence-transformers` configuration `prompts` dictionary.\n\nFor example if ``prompt_name`` is \"query\" and the ``prompts`` is {\"query\": \"query: \", ...},\nthen the sentence \"What is the capital of France?\" will be encoded as\n\"query: What is the capital of France?\" because the prompt text will be prepended before\nany text to encode.",
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          },
+          "truncate": {
+            "default": "false",
+            "example": "false",
+            "nullable": true,
+            "type": "boolean"
+          },
+          "truncation_direction": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationDirection"
+              }
+            ],
+            "default": "right"
+          }
+        },
+        "required": [
+          "inputs"
+        ],
+        "type": "object"
+      },
+      "EmbedSparseResponse": {
+        "items": {
+          "items": {
+            "$ref": "#/components/schemas/SparseValue"
+          },
+          "type": "array"
+        },
+        "type": "array"
+      },
+      "Embedding": {
+        "oneOf": [
+          {
+            "items": {
+              "format": "float",
+              "type": "number"
+            },
+            "type": "array"
+          },
+          {
+            "type": "string"
+          }
+        ]
+      },
+      "EmbeddingModel": {
+        "properties": {
+          "pooling": {
+            "example": "cls",
+            "type": "string"
+          }
+        },
+        "required": [
+          "pooling"
+        ],
+        "type": "object"
+      },
+      "EncodingFormat": {
+        "enum": [
+          "float",
+          "base64"
+        ],
+        "type": "string"
+      },
+      "ErrorResponse": {
+        "properties": {
+          "error": {
+            "type": "string"
+          },
+          "error_type": {
+            "$ref": "#/components/schemas/ErrorType"
+          }
+        },
+        "required": [
+          "error",
+          "error_type"
+        ],
+        "type": "object"
+      },
+      "ErrorType": {
+        "enum": [
+          "Unhealthy",
+          "Backend",
+          "Overloaded",
+          "Validation",
+          "Tokenizer"
+        ],
+        "type": "string"
+      },
+      "Info": {
+        "properties": {
+          "auto_truncate": {
+            "type": "boolean"
+          },
+          "docker_label": {
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          },
+          "max_batch_requests": {
+            "default": "null",
+            "example": "null",
+            "minimum": 0,
+            "nullable": true,
+            "type": "integer"
+          },
+          "max_batch_tokens": {
+            "example": "2048",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "max_client_batch_size": {
+            "example": "32",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "max_concurrent_requests": {
+            "description": "Router Parameters",
+            "example": "128",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "max_input_length": {
+            "example": "512",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "model_dtype": {
+            "example": "float16",
+            "type": "string"
+          },
+          "model_id": {
+            "description": "Model info",
+            "example": "thenlper/gte-base",
+            "type": "string"
+          },
+          "model_sha": {
+            "example": "fca14538aa9956a46526bd1d0d11d69e19b5a101",
+            "nullable": true,
+            "type": "string"
+          },
+          "model_type": {
+            "$ref": "#/components/schemas/ModelType"
+          },
+          "sha": {
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          },
+          "tokenization_workers": {
+            "example": "4",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "version": {
+            "description": "Router Info",
+            "example": "0.5.0",
+            "type": "string"
+          }
+        },
+        "required": [
+          "model_id",
+          "model_dtype",
+          "model_type",
+          "max_concurrent_requests",
+          "max_input_length",
+          "max_batch_tokens",
+          "max_client_batch_size",
+          "auto_truncate",
+          "tokenization_workers",
+          "version"
+        ],
+        "type": "object"
+      },
+      "Input": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputType"
+          },
+          {
+            "items": {
+              "$ref": "#/components/schemas/InputType"
+            },
+            "type": "array"
+          }
+        ]
+      },
+      "InputIds": {
+        "oneOf": [
+          {
+            "items": {
+              "format": "int32",
+              "minimum": 0,
+              "type": "integer"
+            },
+            "type": "array"
+          },
+          {
+            "items": {
+              "items": {
+                "format": "int32",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "type": "array"
+            },
+            "type": "array"
+          }
+        ]
+      },
+      "InputType": {
+        "oneOf": [
+          {
+            "type": "string"
+          },
+          {
+            "items": {
+              "format": "int32",
+              "minimum": 0,
+              "type": "integer"
+            },
+            "type": "array"
+          }
+        ]
+      },
+      "ModelType": {
+        "oneOf": [
+          {
+            "properties": {
+              "classifier": {
+                "$ref": "#/components/schemas/ClassifierModel"
+              }
+            },
+            "required": [
+              "classifier"
+            ],
+            "type": "object"
+          },
+          {
+            "properties": {
+              "embedding": {
+                "$ref": "#/components/schemas/EmbeddingModel"
+              }
+            },
+            "required": [
+              "embedding"
+            ],
+            "type": "object"
+          },
+          {
+            "properties": {
+              "reranker": {
+                "$ref": "#/components/schemas/ClassifierModel"
+              }
+            },
+            "required": [
+              "reranker"
+            ],
+            "type": "object"
+          }
+        ]
+      },
+      "OpenAICompatEmbedding": {
+        "properties": {
+          "embedding": {
+            "$ref": "#/components/schemas/Embedding"
+          },
+          "index": {
+            "example": "0",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "object": {
+            "example": "embedding",
+            "type": "string"
+          }
+        },
+        "required": [
+          "object",
+          "embedding",
+          "index"
+        ],
+        "type": "object"
+      },
+      "OpenAICompatErrorResponse": {
+        "properties": {
+          "code": {
+            "format": "int32",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "error_type": {
+            "$ref": "#/components/schemas/ErrorType"
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "message",
+          "code",
+          "error_type"
+        ],
+        "type": "object"
+      },
+      "OpenAICompatRequest": {
+        "properties": {
+          "encoding_format": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/EncodingFormat"
+              }
+            ],
+            "default": "float"
+          },
+          "input": {
+            "$ref": "#/components/schemas/Input"
+          },
+          "model": {
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          },
+          "user": {
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          }
+        },
+        "required": [
+          "input"
+        ],
+        "type": "object"
+      },
+      "OpenAICompatResponse": {
+        "properties": {
+          "data": {
+            "items": {
+              "$ref": "#/components/schemas/OpenAICompatEmbedding"
+            },
+            "type": "array"
+          },
+          "model": {
+            "example": "thenlper/gte-base",
+            "type": "string"
+          },
+          "object": {
+            "example": "list",
+            "type": "string"
+          },
+          "usage": {
+            "$ref": "#/components/schemas/OpenAICompatUsage"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "model",
+          "usage"
+        ],
+        "type": "object"
+      },
+      "OpenAICompatUsage": {
+        "properties": {
+          "prompt_tokens": {
+            "example": "512",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "total_tokens": {
+            "example": "512",
+            "minimum": 0,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "prompt_tokens",
+          "total_tokens"
+        ],
+        "type": "object"
+      },
+      "PredictInput": {
+        "description": "Model input. Can be either a single string, a pair of strings or a batch of mixed single and pairs of strings.",
+        "example": "What is Deep Learning?",
+        "oneOf": [
+          {
+            "description": "A single string",
+            "type": "string"
+          },
+          {
+            "description": "A pair of strings",
+            "items": {
+              "type": "string"
+            },
+            "maxItems": 2,
+            "minItems": 2,
+            "type": "array"
+          },
+          {
+            "description": "A batch",
+            "items": {
+              "oneOf": [
+                {
+                  "description": "A single string",
+                  "items": {
+                    "type": "string"
+                  },
+                  "maxItems": 1,
+                  "minItems": 1,
+                  "type": "array"
+                },
+                {
+                  "description": "A pair of strings",
+                  "items": {
+                    "type": "string"
+                  },
+                  "maxItems": 2,
+                  "minItems": 2,
+                  "type": "array"
+                }
+              ]
+            },
+            "type": "array"
+          }
+        ]
+      },
+      "PredictRequest": {
+        "properties": {
+          "inputs": {
+            "$ref": "#/components/schemas/PredictInput"
+          },
+          "raw_scores": {
+            "default": "false",
+            "example": "false",
+            "type": "boolean"
+          },
+          "truncate": {
+            "default": "false",
+            "example": "false",
+            "nullable": true,
+            "type": "boolean"
+          },
+          "truncation_direction": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationDirection"
+              }
+            ],
+            "default": "right"
+          }
+        },
+        "required": [
+          "inputs"
+        ],
+        "type": "object"
+      },
+      "PredictResponse": {
+        "oneOf": [
+          {
+            "items": {
+              "$ref": "#/components/schemas/Prediction"
+            },
+            "type": "array"
+          },
+          {
+            "items": {
+              "items": {
+                "$ref": "#/components/schemas/Prediction"
+              },
+              "type": "array"
+            },
+            "type": "array"
+          }
+        ]
+      },
+      "Prediction": {
+        "properties": {
+          "label": {
+            "example": "admiration",
+            "type": "string"
+          },
+          "score": {
+            "example": "0.5",
+            "format": "float",
+            "type": "number"
+          }
+        },
+        "required": [
+          "score",
+          "label"
+        ],
+        "type": "object"
+      },
+      "Rank": {
+        "properties": {
+          "index": {
+            "example": "0",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "score": {
+            "example": "1.0",
+            "format": "float",
+            "type": "number"
+          },
+          "text": {
+            "default": "null",
+            "example": "Deep Learning is ...",
+            "nullable": true,
+            "type": "string"
+          }
+        },
+        "required": [
+          "index",
+          "score"
+        ],
+        "type": "object"
+      },
+      "RerankRequest": {
+        "properties": {
+          "query": {
+            "example": "What is Deep Learning?",
+            "type": "string"
+          },
+          "raw_scores": {
+            "default": "false",
+            "example": "false",
+            "type": "boolean"
+          },
+          "return_text": {
+            "default": "false",
+            "example": "false",
+            "type": "boolean"
+          },
+          "texts": {
+            "example": [
+              "Deep Learning is ..."
+            ],
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "truncate": {
+            "default": "false",
+            "example": "false",
+            "nullable": true,
+            "type": "boolean"
+          },
+          "truncation_direction": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationDirection"
+              }
+            ],
+            "default": "right"
+          }
+        },
+        "required": [
+          "query",
+          "texts"
+        ],
+        "type": "object"
+      },
+      "RerankResponse": {
+        "items": {
+          "$ref": "#/components/schemas/Rank"
+        },
+        "type": "array"
+      },
+      "SimilarityInput": {
+        "properties": {
+          "sentences": {
+            "description": "A list of strings which will be compared against the source_sentence.",
+            "example": [
+              "What is Machine Learning?"
+            ],
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "source_sentence": {
+            "description": "The string that you wish to compare the other strings with. This can be a phrase, sentence,\nor longer passage, depending on the model being used.",
+            "example": "What is Deep Learning?",
+            "type": "string"
+          }
+        },
+        "required": [
+          "source_sentence",
+          "sentences"
+        ],
+        "type": "object"
+      },
+      "SimilarityParameters": {
+        "properties": {
+          "prompt_name": {
+            "default": "null",
+            "description": "The name of the prompt that should be used by for encoding. If not set, no prompt\nwill be applied.\n\nMust be a key in the `sentence-transformers` configuration `prompts` dictionary.\n\nFor example if ``prompt_name`` is \"query\" and the ``prompts`` is {\"query\": \"query: \", ...},\nthen the sentence \"What is the capital of France?\" will be encoded as\n\"query: What is the capital of France?\" because the prompt text will be prepended before\nany text to encode.",
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          },
+          "truncate": {
+            "default": "false",
+            "example": "false",
+            "nullable": true,
+            "type": "boolean"
+          },
+          "truncation_direction": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationDirection"
+              }
+            ],
+            "default": "right"
+          }
+        },
+        "required": [
+          "truncation_direction"
+        ],
+        "type": "object"
+      },
+      "SimilarityRequest": {
+        "properties": {
+          "inputs": {
+            "$ref": "#/components/schemas/SimilarityInput"
+          },
+          "parameters": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/SimilarityParameters"
+              }
+            ],
+            "default": "null",
+            "nullable": true
+          }
+        },
+        "required": [
+          "inputs"
+        ],
+        "type": "object"
+      },
+      "SimilarityResponse": {
+        "example": [
+          0.0,
+          1.0,
+          0.5
+        ],
+        "items": {
+          "format": "float",
+          "type": "number"
+        },
+        "type": "array"
+      },
+      "SimpleToken": {
+        "properties": {
+          "id": {
+            "example": 0,
+            "format": "int32",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "special": {
+            "example": "false",
+            "type": "boolean"
+          },
+          "start": {
+            "example": 0,
+            "minimum": 0,
+            "nullable": true,
+            "type": "integer"
+          },
+          "stop": {
+            "example": 2,
+            "minimum": 0,
+            "nullable": true,
+            "type": "integer"
+          },
+          "text": {
+            "example": "test",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "text",
+          "special"
+        ],
+        "type": "object"
+      },
+      "SparseValue": {
+        "properties": {
+          "index": {
+            "minimum": 0,
+            "type": "integer"
+          },
+          "value": {
+            "format": "float",
+            "type": "number"
+          }
+        },
+        "required": [
+          "index",
+          "value"
+        ],
+        "type": "object"
+      },
+      "TokenizeInput": {
+        "oneOf": [
+          {
+            "type": "string"
+          },
+          {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          }
+        ]
+      },
+      "TokenizeRequest": {
+        "properties": {
+          "add_special_tokens": {
+            "default": "true",
+            "example": "true",
+            "type": "boolean"
+          },
+          "inputs": {
+            "$ref": "#/components/schemas/TokenizeInput"
+          },
+          "prompt_name": {
+            "default": "null",
+            "description": "The name of the prompt that should be used by for encoding. If not set, no prompt\nwill be applied.\n\nMust be a key in the `sentence-transformers` configuration `prompts` dictionary.\n\nFor example if ``prompt_name`` is \"query\" and the ``prompts`` is {\"query\": \"query: \", ...},\nthen the sentence \"What is the capital of France?\" will be encoded as\n\"query: What is the capital of France?\" because the prompt text will be prepended before\nany text to encode.",
+            "example": "null",
+            "nullable": true,
+            "type": "string"
+          }
+        },
+        "required": [
+          "inputs"
+        ],
+        "type": "object"
+      },
+      "TokenizeResponse": {
+        "example": [
+          [
+            {
+              "id": 0,
+              "special": false,
+              "start": 0,
+              "stop": 2,
+              "text": "test"
+            }
+          ]
+        ],
+        "items": {
+          "items": {
+            "$ref": "#/components/schemas/SimpleToken"
+          },
+          "type": "array"
+        },
+        "type": "array"
+      },
+      "TruncationDirection": {
+        "enum": [
+          "Left",
+          "Right"
+        ],
+        "type": "string"
+      }
+    }
+  },
+  "info": {
+    "contact": {
+      "name": "Olivier Dehaene"
+    },
+    "description": "Text Embedding Webserver",
+    "license": {
+      "name": "Apache 2.0",
+      "url": "https://www.apache.org/licenses/LICENSE-2.0"
+    },
+    "title": "Text Embeddings Inference",
+    "version": "1.6.0"
+  },
+  "openapi": "3.0.3",
+  "paths": {
+    "/decode": {
+      "post": {
+        "operationId": "decode",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/DecodeRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DecodeResponse"
+                }
+              }
+            },
+            "description": "Decoded ids"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "message": "Tokenization error",
+                  "type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          }
+        },
+        "summary": "Decode input ids",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/embed": {
+      "post": {
+        "operationId": "embed",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/EmbedRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EmbedResponse"
+                }
+              }
+            },
+            "description": "Embeddings"
+          },
+          "413": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Batch size error",
+                  "error_type": "validation"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Batch size error"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Tokenization error",
+                  "error_type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          },
+          "424": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Inference failed",
+                  "error_type": "backend"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Embedding Error"
+          },
+          "429": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Model is overloaded",
+                  "error_type": "overloaded"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Model is overloaded"
+          }
+        },
+        "summary": "Get Embeddings. Returns a 424 status code if the model is not an embedding model.",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/embed_all": {
+      "post": {
+        "description": "Returns a 424 status code if the model is not an embedding model.",
+        "operationId": "embed_all",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/EmbedAllRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EmbedAllResponse"
+                }
+              }
+            },
+            "description": "Embeddings"
+          },
+          "413": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Batch size error",
+                  "error_type": "validation"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Batch size error"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Tokenization error",
+                  "error_type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          },
+          "424": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Inference failed",
+                  "error_type": "backend"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Embedding Error"
+          },
+          "429": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Model is overloaded",
+                  "error_type": "overloaded"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Model is overloaded"
+          }
+        },
+        "summary": "Get all Embeddings without Pooling.",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/embed_sparse": {
+      "post": {
+        "operationId": "embed_sparse",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/EmbedSparseRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EmbedSparseResponse"
+                }
+              }
+            },
+            "description": "Embeddings"
+          },
+          "413": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Batch size error",
+                  "error_type": "validation"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Batch size error"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Tokenization error",
+                  "error_type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          },
+          "424": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Inference failed",
+                  "error_type": "backend"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Embedding Error"
+          },
+          "429": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Model is overloaded",
+                  "error_type": "overloaded"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Model is overloaded"
+          }
+        },
+        "summary": "Get Sparse Embeddings. Returns a 424 status code if the model is not an embedding model with SPLADE pooling.",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/health": {
+      "get": {
+        "operationId": "health",
+        "responses": {
+          "200": {
+            "description": "Everything is working fine"
+          },
+          "503": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "unhealthy",
+                  "error_type": "unhealthy"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Text embeddings Inference is down"
+          }
+        },
+        "summary": "Health check method",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/info": {
+      "get": {
+        "operationId": "get_model_info",
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Info"
+                }
+              }
+            },
+            "description": "Served model info"
+          }
+        },
+        "summary": "Text Embeddings Inference endpoint info",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/metrics": {
+      "get": {
+        "operationId": "metrics",
+        "responses": {
+          "200": {
+            "content": {
+              "text/plain": {
+                "schema": {
+                  "type": "string"
+                }
+              }
+            },
+            "description": "Prometheus Metrics"
+          }
+        },
+        "summary": "Prometheus metrics scrape endpoint",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/predict": {
+      "post": {
+        "operationId": "predict",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PredictRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/PredictResponse"
+                }
+              }
+            },
+            "description": "Predictions"
+          },
+          "413": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Batch size error",
+                  "error_type": "validation"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Batch size error"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Tokenization error",
+                  "error_type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          },
+          "424": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Inference failed",
+                  "error_type": "backend"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Prediction Error"
+          },
+          "429": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Model is overloaded",
+                  "error_type": "overloaded"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Model is overloaded"
+          }
+        },
+        "summary": "Get Predictions. Returns a 424 status code if the model is not a Sequence Classification model",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/rerank": {
+      "post": {
+        "description": "a single class.",
+        "operationId": "rerank",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RerankRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RerankResponse"
+                }
+              }
+            },
+            "description": "Ranks"
+          },
+          "413": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Batch size error",
+                  "error_type": "validation"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Batch size error"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Tokenization error",
+                  "error_type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          },
+          "424": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Inference failed",
+                  "error_type": "backend"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Rerank Error"
+          },
+          "429": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Model is overloaded",
+                  "error_type": "overloaded"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Model is overloaded"
+          }
+        },
+        "summary": "Get Ranks. Returns a 424 status code if the model is not a Sequence Classification model with",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/similarity": {
+      "post": {
+        "operationId": "similarity",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/SimilarityRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SimilarityResponse"
+                }
+              }
+            },
+            "description": "Sentence Similarity"
+          },
+          "413": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Batch size error",
+                  "error_type": "validation"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Batch size error"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Tokenization error",
+                  "error_type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          },
+          "424": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Inference failed",
+                  "error_type": "backend"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Embedding Error"
+          },
+          "429": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "error": "Model is overloaded",
+                  "error_type": "overloaded"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Model is overloaded"
+          }
+        },
+        "summary": "Get Sentence Similarity. Returns a 424 status code if the model is not an embedding model.",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/tokenize": {
+      "post": {
+        "operationId": "tokenize",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/TokenizeRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/TokenizeResponse"
+                }
+              }
+            },
+            "description": "Tokenized ids"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "message": "Tokenization error",
+                  "type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          }
+        },
+        "summary": "Tokenize inputs",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    },
+    "/v1/embeddings": {
+      "post": {
+        "operationId": "openai_embed",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/OpenAICompatRequest"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAICompatResponse"
+                }
+              }
+            },
+            "description": "Embeddings"
+          },
+          "413": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "message": "Batch size error",
+                  "type": "validation"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAICompatErrorResponse"
+                }
+              }
+            },
+            "description": "Batch size error"
+          },
+          "422": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "message": "Tokenization error",
+                  "type": "tokenizer"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAICompatErrorResponse"
+                }
+              }
+            },
+            "description": "Tokenization error"
+          },
+          "424": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "message": "Inference failed",
+                  "type": "backend"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAICompatErrorResponse"
+                }
+              }
+            },
+            "description": "Embedding Error"
+          },
+          "429": {
+            "content": {
+              "application/json": {
+                "example": {
+                  "message": "Model is overloaded",
+                  "type": "overloaded"
+                },
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAICompatErrorResponse"
+                }
+              }
+            },
+            "description": "Model is overloaded"
+          }
+        },
+        "summary": "OpenAI compatible route. Returns a 424 status code if the model is not an embedding model.",
+        "tags": [
+          "Text Embeddings Inference"
+        ]
+      }
+    }
+  },
+  "tags": [
+    {
+      "description": "Hugging Face Text Embeddings Inference API",
+      "name": "Text Embeddings Inference"
+    }
+  ]
+}