{
  "openapi": "3.0.3",
  "info": {
    "title": "The Jina Embedding Serving API",
    "description": "This is the UniversalAPI to access all the Jina embedding models",
    "version": "0.0.89",
    "x-konfig-ignore": {
      "object-with-no-properties": true
    }
  },
  "servers": [
    {
      "url": "https://api.jina.ai"
    }
  ],
  "tags": [
    {
      "name": "bulk-embeddings"
    },
    {
      "name": "multi-vector"
    },
    {
      "name": "embeddings"
    },
    {
      "name": "rerank"
    },
    {
      "name": "health"
    }
  ],
  "paths": {
    "/v1/embeddings": {
      "post": {
        "tags": [
          "embeddings"
        ],
        "summary": "Create Embedding",
        "operationId": "Embeddings_createRepresentation",
        "security": [
          {
            "HTTPBearer": []
          }
        ],
        "description": "Create embedding representations of the given input texts.",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/EmbeddingsCreateRepresentationRequest"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "description": "Create embeddings",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ModelEmbeddingOutput"
                }
              }
            }
          },
          "422": {
            "description": "Validation Error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HTTPValidationError"
                }
              }
            }
          }
        }
      }
    },
    "/v1/bulk-embeddings": {
      "post": {
        "tags": [
          "bulk-embeddings"
        ],
        "summary": "Start Bulk Embedding",
        "operationId": "Bulkembeddings_uploadFileAndGetEmbeddings",
        "security": [
          {
            "HTTPBearer": []
          }
        ],
        "description": "Upload a file and get embeddings for each row",
        "requestBody": {
          "content": {
            "multipart/form-data": {
              "schema": {
                "$ref": "#/components/schemas/Body_start_bulk_embedding_v1_bulk_embeddings_post"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "description": "Start a bulk embedding job",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/BulkEmbeddingJobResponse"
                }
              }
            }
          },
          "422": {
            "description": "Validation Error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HTTPValidationError"
                }
              }
            }
          }
        }
      }
    },
    "/v1/bulk-embeddings/{job_id}": {
      "get": {
        "tags": [
          "bulk-embeddings"
        ],
        "summary": "Retrieve Job",
        "operationId": "Bulkembeddings_getJob",
        "parameters": [
          {
            "required": true,
            "schema": {
              "title": "Job Id",
              "type": "string"
            },
            "name": "job_id",
            "in": "path"
          }
        ],
        "responses": {
          "200": {
            "description": "Get information about a bulk embedding job",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/BulkEmbeddingJobResponse"
                }
              }
            }
          },
          "422": {
            "description": "Validation Error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HTTPValidationError"
                }
              }
            }
          }
        }
      }
    },
    "/v1/bulk-embeddings/{job_id}/download-result": {
      "post": {
        "tags": [
          "bulk-embeddings"
        ],
        "summary": "Download Result",
        "operationId": "Bulkembeddings_downloadResultPost",
        "parameters": [
          {
            "required": true,
            "schema": {
              "title": "Job Id",
              "type": "string"
            },
            "name": "job_id",
            "in": "path"
          }
        ],
        "responses": {
          "200": {
            "description": "Download the result of a bulk embedding job",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/DownloadResultResponse"
                }
              }
            }
          },
          "422": {
            "description": "Validation Error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HTTPValidationError"
                }
              }
            }
          }
        }
      }
    },
    "/v1/rerank": {
      "post": {
        "tags": [
          "rerank"
        ],
        "summary": "Rank",
        "operationId": "Rerank_pairRanking",
        "security": [
          {
            "HTTPBearer": []
          }
        ],
        "description": "Rank pairs.",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/TextRankInput"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "description": "Rank output",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/RankingOutput"
                }
              }
            }
          },
          "422": {
            "description": "Validation Error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HTTPValidationError"
                }
              }
            }
          }
        }
      }
    },
    "/v1/multi-vector": {
      "post": {
        "tags": [
          "multi-vector"
        ],
        "summary": "Create Multi Vector",
        "operationId": "Multivector_generateVectorRepresentations",
        "security": [
          {
            "HTTPBearer": []
          }
        ],
        "description": "Create multiple vector representations of the given input texts. One vector representation for each token in the input text.",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/api_schemas__multi_embeddings__TextEmbeddingInput"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "description": "Create multi vector embeddings",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ColbertModelEmbeddingsOutput"
                }
              }
            }
          },
          "422": {
            "description": "Validation Error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HTTPValidationError"
                }
              }
            }
          }
        }
      }
    },
    "/v1/multi-embeddings": {
      "post": {
        "tags": [
          "multi-vector"
        ],
        "summary": "Create Multi Vector",
        "operationId": "Multiembeddings_generateEmbeddings",
        "security": [
          {
            "HTTPBearer": []
          }
        ],
        "description": "Create multiple vector representations of the given input texts. One vector representation for each token in the input text.",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/api_schemas__multi_embeddings__TextEmbeddingInput"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "description": "Create multi vector embeddings",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ColbertModelEmbeddingsOutput"
                }
              }
            }
          },
          "422": {
            "description": "Validation Error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HTTPValidationError"
                }
              }
            }
          }
        },
        "deprecated": true
      }
    },
    "/": {
      "get": {
        "tags": [
          "health"
        ],
        "summary": "Get the health of Universal API service",
        "operationId": "Health_checkStatus",
        "description": "Get the health of this Gateway service.\n.. # noqa: DAR201",
        "responses": {
          "200": {
            "description": "Successful Response",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HealthModel"
                }
              }
            }
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "Body_start_bulk_embedding_v1_bulk_embeddings_post": {
        "title": "Body_start_bulk_embedding_v1_bulk_embeddings_post",
        "properties": {
          "file": {
            "title": "File",
            "type": "string",
            "format": "binary"
          },
          "email": {
            "title": "Email",
            "type": "string",
            "format": "email"
          },
          "model": {
            "title": "Model",
            "type": "string"
          }
        },
        "type": "object",
        "required": [
          "file",
          "model"
        ]
      },
      "BulkEmbeddingJobResponse": {
        "title": "BulkEmbeddingJobResponse",
        "properties": {
          "user_id": {
            "title": "User Id",
            "description": "The user ID of the user who created the job",
            "type": "string"
          },
          "model_name": {
            "title": "Model Name",
            "description": "The name of the model to use",
            "type": "string"
          },
          "model_package_arn": {
            "title": "Model Package Arn",
            "description": "The model package ARN",
            "type": "string"
          },
          "status": {
            "$ref": "#/components/schemas/BulkEmbeddingJobStatus"
          },
          "file_name": {
            "title": "File Name",
            "description": "The name of the input file",
            "type": "string"
          },
          "user_email": {
            "title": "User Email",
            "description": "The email of the user who created the job",
            "type": "string",
            "format": "email"
          },
          "created_at": {
            "title": "Created At",
            "description": "Time of creation of the job.",
            "type": "string",
            "format": "date-time",
            "nullable": false
          },
          "completed_at": {
            "title": "Completed At",
            "description": "Time of completion of the job.",
            "type": "string",
            "format": "date-time"
          },
          "error": {
            "title": "Error",
            "description": "The error message of the job",
            "type": "string"
          },
          "_id": {
            "title": " Id",
            "description": "The ID of the job",
            "type": "string"
          },
          "used_token_count": {
            "title": "Used Token Count",
            "description": "The number of tokens used for the job",
            "type": "integer"
          }
        },
        "type": "object",
        "required": [
          "user_id",
          "model_name",
          "status",
          "file_name",
          "_id"
        ],
        "example": {
          "id": "000000000000000000000000",
          "model_name": "model_1",
          "status": "in-progress",
          "file_name": "input.csv",
          "used_token_count": 1000
        },
        "x-konfig-properties": {
          "status": {
            "description": "The status of the job"
          }
        }
      },
      "BulkEmbeddingJobStatus": {
        "title": "BulkEmbeddingJobStatus",
        "description": "An enumeration.",
        "type": "string",
        "enum": [
          "waiting",
          "in-progress",
          "failed",
          "completed"
        ]
      },
      "ColbertModelEmbeddingsOutput": {
        "title": "ColbertModelEmbeddingsOutput",
        "description": "Output of the embedding service",
        "properties": {
          "model": {
            "title": "Model",
            "description": "The identifier of the model.\n\nAvailable models and corresponding param size and dimension:\n- `jina-embedding-t-en-v1`,\t14m,\t312\n- `jina-embedding-s-en-v1`,\t35m,\t512 (default)\n- `jina-embedding-b-en-v1`,\t110m,\t768\n- `jina-embedding-l-en-v1`,\t330,\t1024\n\nFor more information, please checkout our [technical blog](https://arxiv.org/abs/2307.11224).\n",
            "type": "string"
          },
          "object": {
            "title": "Object",
            "type": "string",
            "default": "list"
          },
          "data": {
            "title": "Data",
            "description": "A list of Embedding Objects returned by the embedding service",
            "items": {},
            "type": "array"
          },
          "usage": {
            "$ref": "#/components/schemas/api_schemas__embedding__Usage"
          }
        },
        "type": "object",
        "required": [
          "model",
          "data",
          "usage"
        ],
        "example": {
          "data": [
            {
              "index": 0,
              "embeddings": [
                [
                  0.1,
                  0.2,
                  0.3
                ],
                [
                  0.4,
                  0.5,
                  0.6
                ]
              ],
              "object": "embeddings"
            },
            {
              "index": 1,
              "embeddings": [
                [
                  0.6,
                  0.5,
                  0.4
                ],
                [
                  0.3,
                  0.2,
                  0.1
                ]
              ],
              "object": "embeddings"
            }
          ],
          "usage": {
            "total_tokens": 15,
            "prompt_tokens": 15
          }
        },
        "x-konfig-properties": {
          "usage": {
            "title": "Usage",
            "description": "Total usage of the request. Sums up the usage from each individual input"
          }
        }
      },
      "DownloadResultResponse": {
        "title": "DownloadResultResponse",
        "properties": {
          "id": {
            "title": "Id",
            "description": "The ID of the job",
            "type": "string"
          },
          "download_url": {
            "title": "Download Url",
            "description": "The URL to download the result file",
            "type": "string"
          }
        },
        "type": "object",
        "required": [
          "id",
          "download_url"
        ],
        "example": {
          "id": "000000000000000000000000X",
          "download_url": "https://example.com"
        }
      },
      "HTTPValidationError": {
        "title": "HTTPValidationError",
        "properties": {
          "detail": {
            "title": "Detail",
            "items": {
              "$ref": "#/components/schemas/ValidationError"
            },
            "type": "array"
          }
        },
        "type": "object"
      },
      "HealthModel": {
        "title": "HealthModel",
        "description": "Pydantic BaseModel for Jina health check, used as the response model in REST app.",
        "properties": {},
        "type": "object"
      },
      "ImageDoc": {
        "title": "ImageDoc",
        "description": "BaseDoc is the base class for all Documents. This class should be subclassed\nto create new Document types with a specific schema.\n\nThe schema of a Document is defined by the fields of the class.\n\nExample:\n```python\nfrom docarray import BaseDoc\nfrom docarray.typing import NdArray, ImageUrl\nimport numpy as np\n\n\nclass MyDoc(BaseDoc):\n    embedding: NdArray[512]\n    image: ImageUrl\n\n\ndoc = MyDoc(embedding=np.zeros(512), image='https://example.com/image.jpg')\n```\n\n\nBaseDoc is a subclass of [pydantic.BaseModel](https://docs.pydantic.dev/usage/models/) and can be used in a similar way.",
        "properties": {
          "id": {
            "title": "Id",
            "description": "The ID of the BaseDoc. This is useful for indexing in vector stores. If not set by user, it will automatically be assigned a random value",
            "type": "string",
            "example": "d25b9372e32971ef9af12b91f524ad52"
          },
          "url": {
            "title": "Url",
            "description": "URL of an image file",
            "type": "string",
            "maxLength": 65536,
            "minLength": 1,
            "format": "uri"
          },
          "bytes": {
            "title": "Bytes",
            "description": "Bytes representation of the Image.",
            "type": "string",
            "format": "binary"
          }
        },
        "type": "object"
      },
      "ImageEmbeddingInput": {
        "title": "ImageEmbeddingInput",
        "description": "The input to the API for text embedding. OpenAI compatible",
        "properties": {
          "model": {
            "title": "Model",
            "description": "The identifier of the model.\n\nAvailable models and corresponding param size and dimension:\n- `jina-embedding-t-en-v1`,\t14m,\t312\n- `jina-embedding-s-en-v1`,\t35m,\t512 (default)\n- `jina-embedding-b-en-v1`,\t110m,\t768\n- `jina-embedding-l-en-v1`,\t330,\t1024\n\nFor more information, please checkout our [technical blog](https://arxiv.org/abs/2307.11224).\n",
            "type": "string"
          },
          "input": {
            "title": "Input",
            "description": "List of images to embed",
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ImageDoc"
                },
                "type": "array"
              },
              {
                "$ref": "#/components/schemas/ImageDoc"
              }
            ]
          },
          "encoding_format": {
            "title": "Encoding Format",
            "description": "The format in which you want the embeddings to be returned.Possible value are `float`, `base64`, `binary`, `ubinary` or a list containing any of them. Defaults to `float` ",
            "anyOf": [
              {
                "type": "string",
                "enum": [
                  "float",
                  "base64",
                  "binary",
                  "ubinary"
                ]
              },
              {
                "items": {
                  "type": "string",
                  "enum": [
                    "float",
                    "base64",
                    "binary",
                    "ubinary"
                  ]
                },
                "type": "array"
              }
            ]
          }
        },
        "type": "object",
        "required": [
          "model",
          "input"
        ],
        "example": {
          "model": "clip",
          "input": [
            "bytes or URL"
          ]
        }
      },
      "ModelEmbeddingOutput": {
        "title": "ModelEmbeddingOutput",
        "description": "Output of the embedding service",
        "properties": {
          "model": {
            "title": "Model",
            "description": "The identifier of the model.\n\nAvailable models and corresponding param size and dimension:\n- `jina-embedding-t-en-v1`,\t14m,\t312\n- `jina-embedding-s-en-v1`,\t35m,\t512 (default)\n- `jina-embedding-b-en-v1`,\t110m,\t768\n- `jina-embedding-l-en-v1`,\t330,\t1024\n\nFor more information, please checkout our [technical blog](https://arxiv.org/abs/2307.11224).\n",
            "type": "string"
          },
          "object": {
            "title": "Object",
            "type": "string",
            "default": "list"
          },
          "data": {
            "title": "Data",
            "description": "A list of Embedding Objects returned by the embedding service",
            "items": {},
            "type": "array"
          },
          "usage": {
            "$ref": "#/components/schemas/api_schemas__embedding__Usage"
          }
        },
        "type": "object",
        "required": [
          "model",
          "data",
          "usage"
        ],
        "example": {
          "data": [
            {
              "index": 0,
              "embedding": [
                0.1,
                0.2,
                0.3
              ],
              "object": "embedding"
            },
            {
              "index": 1,
              "embedding": [
                0.3,
                0.2,
                0.1
              ],
              "object": "embedding"
            }
          ],
          "usage": {
            "total_tokens": 15,
            "prompt_tokens": 15
          }
        },
        "x-konfig-properties": {
          "usage": {
            "title": "Usage",
            "description": "Total usage of the request. Sums up the usage from each individual input"
          }
        }
      },
      "RankingOutput": {
        "title": "RankingOutput",
        "description": "Output of the embedding service",
        "properties": {
          "model": {
            "title": "Model",
            "description": "The identifier of the model.\n\nAvailable models and corresponding param size and dimension:\n- `jina-embedding-t-en-v1`,\t14m,\t312\n- `jina-embedding-s-en-v1`,\t35m,\t512 (default)\n- `jina-embedding-b-en-v1`,\t110m,\t768\n- `jina-embedding-l-en-v1`,\t330,\t1024\n\nFor more information, please checkout our [technical blog](https://arxiv.org/abs/2307.11224).\n",
            "type": "string"
          },
          "results": {
            "title": "Results",
            "description": "An ordered list of ranked documents",
            "items": {},
            "type": "array"
          },
          "usage": {
            "$ref": "#/components/schemas/api_schemas__rank__Usage"
          }
        },
        "type": "object",
        "required": [
          "model",
          "results",
          "usage"
        ],
        "example": {
          "results": [
            {
              "index": 0,
              "document": {
                "text": "Document to rank 1"
              },
              "relevance_score": 0.9
            },
            {
              "index": 1,
              "document": {
                "text": "Document to rank 2"
              },
              "relevance_score": 0.8
            }
          ],
          "usage": {
            "total_tokens": 15,
            "prompt_tokens": 15
          }
        },
        "x-konfig-properties": {
          "usage": {
            "title": "Usage",
            "description": "Total usage of the request."
          }
        }
      },
      "TextRankInput": {
        "title": "TextRankInput",
        "description": "The input to the API for text embedding. OpenAI compatible",
        "properties": {
          "model": {
            "title": "Model",
            "description": "The identifier of the model.\n\nAvailable models and corresponding param size and dimension:\n- `jina-embedding-t-en-v1`,\t14m,\t312\n- `jina-embedding-s-en-v1`,\t35m,\t512 (default)\n- `jina-embedding-b-en-v1`,\t110m,\t768\n- `jina-embedding-l-en-v1`,\t330,\t1024\n\nFor more information, please checkout our [technical blog](https://arxiv.org/abs/2307.11224).\n",
            "type": "string"
          },
          "query": {
            "title": "Query",
            "description": "The search query",
            "anyOf": [
              {
                "type": "string"
              },
              {
                "$ref": "#/components/schemas/api_schemas__rank__TextDoc"
              }
            ]
          },
          "documents": {
            "title": "Documents",
            "description": "A list of text documents or strings to rerank. If a document is provided the text fields is required and all other fields will be preserved in the response.",
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "items": {
                  "$ref": "#/components/schemas/api_schemas__rank__TextDoc"
                },
                "type": "array"
              }
            ]
          },
          "top_n": {
            "title": "Top N",
            "description": "The number of most relevant documents or indices to return, defaults to the length of `documents`",
            "type": "integer"
          },
          "return_documents": {
            "title": "Return Documents",
            "description": "If false, returns results without the doc text - the api will return a list of {index, relevance score} where index is inferred from the list passed into the request. If true, returns results with the doc text passed in - the api will return an ordered list of {index, text, relevance score} where index + text refers to the list passed into the request. Defaults to true",
            "type": "boolean",
            "default": true
          }
        },
        "type": "object",
        "required": [
          "model",
          "query",
          "documents"
        ],
        "example": {
          "model": "jina-reranker-v1-base-en",
          "query": "Search query",
          "documents": [
            "Document to rank 1",
            "Document to rank 2"
          ]
        }
      },
      "ValidationError": {
        "title": "ValidationError",
        "properties": {
          "loc": {
            "title": "Location",
            "items": {
              "anyOf": [
                {
                  "type": "string"
                },
                {
                  "type": "integer"
                }
              ]
            },
            "type": "array"
          },
          "msg": {
            "title": "Message",
            "type": "string"
          },
          "type": {
            "title": "Error Type",
            "type": "string"
          }
        },
        "type": "object",
        "required": [
          "loc",
          "msg",
          "type"
        ]
      },
      "api_schemas__embedding__TextDoc": {
        "title": "TextDoc",
        "description": "Document containing a text field",
        "properties": {
          "id": {
            "title": "Id",
            "description": "The ID of the BaseDoc. This is useful for indexing in vector stores. If not set by user, it will automatically be assigned a random value",
            "type": "string",
            "example": "d25b9372e32971ef9af12b91f524ad52"
          },
          "text": {
            "title": "Text",
            "type": "string"
          }
        },
        "type": "object",
        "required": [
          "text"
        ]
      },
      "api_schemas__embedding__TextEmbeddingInput": {
        "title": "TextEmbeddingInput",
        "description": "The input to the API for text embedding. OpenAI compatible",
        "properties": {
          "model": {
            "title": "Model",
            "description": "The identifier of the model.\n\nAvailable models and corresponding param size and dimension:\n- `jina-embedding-t-en-v1`,\t14m,\t312\n- `jina-embedding-s-en-v1`,\t35m,\t512 (default)\n- `jina-embedding-b-en-v1`,\t110m,\t768\n- `jina-embedding-l-en-v1`,\t330,\t1024\n\nFor more information, please checkout our [technical blog](https://arxiv.org/abs/2307.11224).\n",
            "type": "string"
          },
          "input": {
            "title": "Input",
            "description": "List of texts to embed",
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "string"
              },
              {
                "items": {
                  "$ref": "#/components/schemas/api_schemas__embedding__TextDoc"
                },
                "type": "array"
              },
              {
                "$ref": "#/components/schemas/api_schemas__embedding__TextDoc"
              }
            ]
          },
          "encoding_format": {
            "title": "Encoding Format",
            "description": "The format in which you want the embeddings to be returned.Possible value are `float`, `base64`, `binary`, `ubinary` or a list containing any of them. Defaults to `float` ",
            "anyOf": [
              {
                "type": "string",
                "enum": [
                  "float",
                  "base64",
                  "binary",
                  "ubinary"
                ]
              },
              {
                "items": {
                  "type": "string",
                  "enum": [
                    "float",
                    "base64",
                    "binary",
                    "ubinary"
                  ]
                },
                "type": "array"
              }
            ]
          }
        },
        "type": "object",
        "required": [
          "model",
          "input"
        ],
        "example": {
          "model": "jina-embeddings-v2-base-en",
          "input": [
            "Hello, world!"
          ]
        }
      },
      "api_schemas__embedding__Usage": {
        "title": "Usage",
        "properties": {
          "total_tokens": {
            "title": "Total Tokens",
            "description": "The number of tokens used by all the texts in the input",
            "type": "integer"
          },
          "prompt_tokens": {
            "title": "Prompt Tokens",
            "description": "Same as total_tokens",
            "type": "integer"
          }
        },
        "type": "object",
        "required": [
          "total_tokens",
          "prompt_tokens"
        ]
      },
      "api_schemas__multi_embeddings__TextEmbeddingInput": {
        "title": "TextEmbeddingInput",
        "description": "The input to the API for text embedding. OpenAI compatible",
        "properties": {
          "model": {
            "title": "Model",
            "description": "The identifier of the model.\n\nAvailable models and corresponding param size and dimension:\n- `jina-embedding-t-en-v1`,\t14m,\t312\n- `jina-embedding-s-en-v1`,\t35m,\t512 (default)\n- `jina-embedding-b-en-v1`,\t110m,\t768\n- `jina-embedding-l-en-v1`,\t330,\t1024\n\nFor more information, please checkout our [technical blog](https://arxiv.org/abs/2307.11224).\n",
            "type": "string"
          },
          "input": {
            "title": "Input",
            "description": "List of texts to embed",
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "string"
              },
              {
                "items": {
                  "$ref": "#/components/schemas/api_schemas__embedding__TextDoc"
                },
                "type": "array"
              },
              {
                "$ref": "#/components/schemas/api_schemas__embedding__TextDoc"
              }
            ]
          },
          "input_type": {
            "title": "Input Type",
            "description": "Type of the embedding to compute, query or document",
            "type": "string",
            "enum": [
              "query",
              "document"
            ],
            "default": "document"
          },
          "encoding_format": {
            "title": "Encoding Format",
            "description": "The format in which you want the embeddings to be returned.Possible value are `float`, `base64`, `binary`, `ubinary` or a list containing any of them. Defaults to `float` ",
            "anyOf": [
              {
                "type": "string",
                "enum": [
                  "float",
                  "base64",
                  "binary",
                  "ubinary"
                ]
              },
              {
                "items": {
                  "type": "string",
                  "enum": [
                    "float",
                    "base64",
                    "binary",
                    "ubinary"
                  ]
                },
                "type": "array"
              }
            ]
          }
        },
        "type": "object",
        "required": [
          "model",
          "input"
        ],
        "example": {
          "model": "jina-colbert-v1-en",
          "input": [
            "Hello, world!"
          ]
        }
      },
      "api_schemas__rank__TextDoc": {
        "title": "TextDoc",
        "description": "Document containing a text field",
        "properties": {
          "id": {
            "title": "Id",
            "description": "The ID of the BaseDoc. This is useful for indexing in vector stores. If not set by user, it will automatically be assigned a random value",
            "type": "string",
            "example": "d25b9372e32971ef9af12b91f524ad52"
          },
          "text": {
            "title": "Text",
            "type": "string"
          }
        },
        "type": "object",
        "required": [
          "text"
        ]
      },
      "api_schemas__rank__Usage": {
        "title": "Usage",
        "properties": {
          "total_tokens": {
            "title": "Total Tokens",
            "description": "The number of tokens used by all the texts in the input",
            "type": "integer"
          },
          "prompt_tokens": {
            "title": "Prompt Tokens",
            "description": "Same as total_tokens",
            "type": "integer"
          }
        },
        "type": "object",
        "required": [
          "total_tokens",
          "prompt_tokens"
        ],
        "example": {
          "total_tokens": 15,
          "prompt_tokens": 15
        }
      },
      "EmbeddingsCreateRepresentationRequest": {
        "title": "Body",
        "anyOf": [
          {
            "$ref": "#/components/schemas/api_schemas__embedding__TextEmbeddingInput"
          },
          {
            "$ref": "#/components/schemas/ImageEmbeddingInput"
          }
        ]
      }
    },
    "securitySchemes": {
      "HTTPBearer": {
        "type": "http",
        "scheme": "bearer"
      }
    }
  }
}