Jina AI

{
  "type": "object",
  "title": "Body_start_bulk_embedding_v1_bulk_embeddings_post",
  "required": [
    "file",
    "model"
  ],
  "properties": {
    "file": {
      "type": "string",
      "title": "File",
      "format": "binary"
    },
    "email": {
      "type": "string",
      "title": "Email",
      "format": "email"
    },
    "model": {
      "type": "string",
      "title": "Model"
    }
  }
}

{
  "type": "object",
  "title": "BulkEmbeddingJobResponse",
  "example": {
    "id": "000000000000000000000000",
    "status": "in-progress",
    "file_name": "input.csv",
    "model_name": "model_1",
    "used_token_count": 1000
  },
  "required": [
    "user_id",
    "model_name",
    "status",
    "file_name",
    "_id"
  ],
  "properties": {
    "_id": {
      "type": "string",
      "title": " Id",
      "description": "The ID of the job"
    },
    "error": {
      "type": "string",
      "title": "Error",
      "description": "The error message of the job"
    },
    "status": {
      "$ref": "#/components/schemas/BulkEmbeddingJobStatus"
    },
    "user_id": {
      "type": "string",
      "title": "User Id",
      "description": "The user ID of the user who created the job"
    },
    "file_name": {
      "type": "string",
      "title": "File Name",
      "description": "The name of the input file"
    },
    "created_at": {
      "type": "string",
      "title": "Created At",
      "format": "date-time",
      "nullable": false,
      "description": "Time of creation of the job."
    },
    "model_name": {
      "type": "string",
      "title": "Model Name",
      "description": "The name of the model to use"
    },
    "user_email": {
      "type": "string",
      "title": "User Email",
      "format": "email",
      "description": "The email of the user who created the job"
    },
    "completed_at": {
      "type": "string",
      "title": "Completed At",
      "format": "date-time",
      "description": "Time of completion of the job."
    },
    "used_token_count": {
      "type": "integer",
      "title": "Used Token Count",
      "description": "The number of tokens used for the job"
    },
    "model_package_arn": {
      "type": "string",
      "title": "Model Package Arn",
      "description": "The model package ARN"
    }
  },
  "x-konfig-properties": {
    "status": {
      "description": "The status of the job"
    }
  }
}

{
  "enum": [
    "waiting",
    "in-progress",
    "failed",
    "completed"
  ],
  "type": "string",
  "title": "BulkEmbeddingJobStatus",
  "description": "An enumeration."
}

{
  "type": "object",
  "title": "ColbertModelEmbeddingsOutput",
  "example": {
    "data": [
      {
        "index": 0,
        "object": "embeddings",
        "embeddings": [
          [
            0.1,
            0.2,
            0.3
          ],
          [
            0.4,
            0.5,
            0.6
          ]
        ]
      },
      {
        "index": 1,
        "object": "embeddings",
        "embeddings": [
          [
            0.6,
            0.5,
            0.4
          ],
          [
            0.3,
            0.2,
            0.1
          ]
        ]
      }
    ],
    "usage": {
      "total_tokens": 15,
      "prompt_tokens": 15
    }
  },
  "required": [
    "model",
    "data",
    "usage"
  ],
  "properties": {
    "data": {
      "type": "array",
      "items": {},
      "title": "Data",
      "description": "A list of Embedding Objects returned by the embedding service"
    },
    "model": {
      "type": "string",
      "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"
    },
    "usage": {
      "$ref": "#/components/schemas/api_schemas__embedding__Usage"
    },
    "object": {
      "type": "string",
      "title": "Object",
      "default": "list"
    }
  },
  "description": "Output of the embedding service",
  "x-konfig-properties": {
    "usage": {
      "title": "Usage",
      "description": "Total usage of the request. Sums up the usage from each individual input"
    }
  }
}

{
  "type": "object",
  "title": "DownloadResultResponse",
  "example": {
    "id": "000000000000000000000000X",
    "download_url": "https://example.com"
  },
  "required": [
    "id",
    "download_url"
  ],
  "properties": {
    "id": {
      "type": "string",
      "title": "Id",
      "description": "The ID of the job"
    },
    "download_url": {
      "type": "string",
      "title": "Download Url",
      "description": "The URL to download the result file"
    }
  }
}

{
  "anyOf": [
    {
      "$ref": "#/components/schemas/api_schemas__embedding__TextEmbeddingInput"
    },
    {
      "$ref": "#/components/schemas/ImageEmbeddingInput"
    }
  ],
  "title": "Body"
}

{
  "type": "object",
  "title": "HTTPValidationError",
  "properties": {
    "detail": {
      "type": "array",
      "items": {
        "$ref": "#/components/schemas/ValidationError"
      },
      "title": "Detail"
    }
  }
}

{
  "type": "object",
  "title": "HealthModel",
  "properties": {},
  "description": "Pydantic BaseModel for Jina health check, used as the response model in REST app."
}

{
  "type": "object",
  "title": "ImageDoc",
  "properties": {
    "id": {
      "type": "string",
      "title": "Id",
      "example": "d25b9372e32971ef9af12b91f524ad52",
      "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"
    },
    "url": {
      "type": "string",
      "title": "Url",
      "format": "uri",
      "maxLength": 65536,
      "minLength": 1,
      "description": "URL of an image file"
    },
    "bytes": {
      "type": "string",
      "title": "Bytes",
      "format": "binary",
      "description": "Bytes representation of the Image."
    }
  },
  "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."
}

{
  "type": "object",
  "title": "ImageEmbeddingInput",
  "example": {
    "input": [
      "bytes or URL"
    ],
    "model": "clip"
  },
  "required": [
    "model",
    "input"
  ],
  "properties": {
    "input": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/ImageDoc"
          }
        },
        {
          "$ref": "#/components/schemas/ImageDoc"
        }
      ],
      "title": "Input",
      "description": "List of images to embed"
    },
    "model": {
      "type": "string",
      "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"
    },
    "encoding_format": {
      "anyOf": [
        {
          "enum": [
            "float",
            "base64",
            "binary",
            "ubinary"
          ],
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "enum": [
              "float",
              "base64",
              "binary",
              "ubinary"
            ],
            "type": "string"
          }
        }
      ],
      "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` "
    }
  },
  "description": "The input to the API for text embedding. OpenAI compatible"
}

{
  "type": "object",
  "title": "ModelEmbeddingOutput",
  "example": {
    "data": [
      {
        "index": 0,
        "object": "embedding",
        "embedding": [
          0.1,
          0.2,
          0.3
        ]
      },
      {
        "index": 1,
        "object": "embedding",
        "embedding": [
          0.3,
          0.2,
          0.1
        ]
      }
    ],
    "usage": {
      "total_tokens": 15,
      "prompt_tokens": 15
    }
  },
  "required": [
    "model",
    "data",
    "usage"
  ],
  "properties": {
    "data": {
      "type": "array",
      "items": {},
      "title": "Data",
      "description": "A list of Embedding Objects returned by the embedding service"
    },
    "model": {
      "type": "string",
      "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"
    },
    "usage": {
      "$ref": "#/components/schemas/api_schemas__embedding__Usage"
    },
    "object": {
      "type": "string",
      "title": "Object",
      "default": "list"
    }
  },
  "description": "Output of the embedding service",
  "x-konfig-properties": {
    "usage": {
      "title": "Usage",
      "description": "Total usage of the request. Sums up the usage from each individual input"
    }
  }
}

{
  "type": "object",
  "title": "RankingOutput",
  "example": {
    "usage": {
      "total_tokens": 15,
      "prompt_tokens": 15
    },
    "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
      }
    ]
  },
  "required": [
    "model",
    "results",
    "usage"
  ],
  "properties": {
    "model": {
      "type": "string",
      "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"
    },
    "usage": {
      "$ref": "#/components/schemas/api_schemas__rank__Usage"
    },
    "results": {
      "type": "array",
      "items": {},
      "title": "Results",
      "description": "An ordered list of ranked documents"
    }
  },
  "description": "Output of the embedding service",
  "x-konfig-properties": {
    "usage": {
      "title": "Usage",
      "description": "Total usage of the request."
    }
  }
}

{
  "type": "object",
  "title": "TextRankInput",
  "example": {
    "model": "jina-reranker-v1-base-en",
    "query": "Search query",
    "documents": [
      "Document to rank 1",
      "Document to rank 2"
    ]
  },
  "required": [
    "model",
    "query",
    "documents"
  ],
  "properties": {
    "model": {
      "type": "string",
      "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"
    },
    "query": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "$ref": "#/components/schemas/api_schemas__rank__TextDoc"
        }
      ],
      "title": "Query",
      "description": "The search query"
    },
    "top_n": {
      "type": "integer",
      "title": "Top N",
      "description": "The number of most relevant documents or indices to return, defaults to the length of `documents`"
    },
    "documents": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/api_schemas__rank__TextDoc"
          }
        }
      ],
      "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."
    },
    "return_documents": {
      "type": "boolean",
      "title": "Return Documents",
      "default": true,
      "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"
    }
  },
  "description": "The input to the API for text embedding. OpenAI compatible"
}

{
  "type": "object",
  "title": "ValidationError",
  "required": [
    "loc",
    "msg",
    "type"
  ],
  "properties": {
    "loc": {
      "type": "array",
      "items": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "integer"
          }
        ]
      },
      "title": "Location"
    },
    "msg": {
      "type": "string",
      "title": "Message"
    },
    "type": {
      "type": "string",
      "title": "Error Type"
    }
  }
}

{
  "type": "object",
  "title": "TextDoc",
  "required": [
    "text"
  ],
  "properties": {
    "id": {
      "type": "string",
      "title": "Id",
      "example": "d25b9372e32971ef9af12b91f524ad52",
      "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"
    },
    "text": {
      "type": "string",
      "title": "Text"
    }
  },
  "description": "Document containing a text field"
}

{
  "type": "object",
  "title": "TextEmbeddingInput",
  "example": {
    "input": [
      "Hello, world!"
    ],
    "model": "jina-embeddings-v2-base-en"
  },
  "required": [
    "model",
    "input"
  ],
  "properties": {
    "input": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/api_schemas__embedding__TextDoc"
          }
        },
        {
          "$ref": "#/components/schemas/api_schemas__embedding__TextDoc"
        }
      ],
      "title": "Input",
      "description": "List of texts to embed"
    },
    "model": {
      "type": "string",
      "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"
    },
    "encoding_format": {
      "anyOf": [
        {
          "enum": [
            "float",
            "base64",
            "binary",
            "ubinary"
          ],
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "enum": [
              "float",
              "base64",
              "binary",
              "ubinary"
            ],
            "type": "string"
          }
        }
      ],
      "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` "
    }
  },
  "description": "The input to the API for text embedding. OpenAI compatible"
}

{
  "type": "object",
  "title": "Usage",
  "required": [
    "total_tokens",
    "prompt_tokens"
  ],
  "properties": {
    "total_tokens": {
      "type": "integer",
      "title": "Total Tokens",
      "description": "The number of tokens used by all the texts in the input"
    },
    "prompt_tokens": {
      "type": "integer",
      "title": "Prompt Tokens",
      "description": "Same as total_tokens"
    }
  }
}

{
  "type": "object",
  "title": "TextEmbeddingInput",
  "example": {
    "input": [
      "Hello, world!"
    ],
    "model": "jina-colbert-v1-en"
  },
  "required": [
    "model",
    "input"
  ],
  "properties": {
    "input": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/api_schemas__embedding__TextDoc"
          }
        },
        {
          "$ref": "#/components/schemas/api_schemas__embedding__TextDoc"
        }
      ],
      "title": "Input",
      "description": "List of texts to embed"
    },
    "model": {
      "type": "string",
      "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"
    },
    "input_type": {
      "enum": [
        "query",
        "document"
      ],
      "type": "string",
      "title": "Input Type",
      "default": "document",
      "description": "Type of the embedding to compute, query or document"
    },
    "encoding_format": {
      "anyOf": [
        {
          "enum": [
            "float",
            "base64",
            "binary",
            "ubinary"
          ],
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "enum": [
              "float",
              "base64",
              "binary",
              "ubinary"
            ],
            "type": "string"
          }
        }
      ],
      "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` "
    }
  },
  "description": "The input to the API for text embedding. OpenAI compatible"
}

{
  "type": "object",
  "title": "TextDoc",
  "required": [
    "text"
  ],
  "properties": {
    "id": {
      "type": "string",
      "title": "Id",
      "example": "d25b9372e32971ef9af12b91f524ad52",
      "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"
    },
    "text": {
      "type": "string",
      "title": "Text"
    }
  },
  "description": "Document containing a text field"
}

{
  "type": "object",
  "title": "Usage",
  "example": {
    "total_tokens": 15,
    "prompt_tokens": 15
  },
  "required": [
    "total_tokens",
    "prompt_tokens"
  ],
  "properties": {
    "total_tokens": {
      "type": "integer",
      "title": "Total Tokens",
      "description": "The number of tokens used by all the texts in the input"
    },
    "prompt_tokens": {
      "type": "integer",
      "title": "Prompt Tokens",
      "description": "Same as total_tokens"
    }
  }
}