ImageDocument#
- pydantic model llama_index.schema.ImageDocument#
Data document containing an image.
Show JSON schema
{ "title": "ImageDocument", "description": "Data document containing an image.", "type": "object", "properties": { "doc_id": { "title": "Doc Id", "description": "Unique ID of the node.", "type": "string" }, "embedding": { "title": "Embedding", "description": "Embedding of the node.", "type": "array", "items": { "type": "number" } }, "extra_info": { "title": "Extra Info", "description": "A flat dictionary of metadata fields", "type": "object" }, "excluded_embed_metadata_keys": { "title": "Excluded Embed Metadata Keys", "description": "Metadata keys that are excluded from text for the embed model.", "type": "array", "items": { "type": "string" } }, "excluded_llm_metadata_keys": { "title": "Excluded Llm Metadata Keys", "description": "Metadata keys that are excluded from text for the LLM.", "type": "array", "items": { "type": "string" } }, "relationships": { "title": "Relationships", "description": "A mapping of relationships to other node information.", "type": "object", "additionalProperties": { "anyOf": [ { "$ref": "#/definitions/RelatedNodeInfo" }, { "type": "array", "items": { "$ref": "#/definitions/RelatedNodeInfo" } } ] } }, "text": { "title": "Text", "description": "Text content of the node.", "default": "", "type": "string" }, "start_char_idx": { "title": "Start Char Idx", "description": "Start char index of the node.", "type": "integer" }, "end_char_idx": { "title": "End Char Idx", "description": "End char index of the node.", "type": "integer" }, "text_template": { "title": "Text Template", "description": "Template for how text is formatted, with {content} and {metadata_str} placeholders.", "default": "{metadata_str}\n\n{content}", "type": "string" }, "metadata_template": { "title": "Metadata Template", "description": "Template for how metadata is formatted, with {key} and {value} placeholders.", "default": "{key}: {value}", "type": "string" }, "metadata_seperator": { "title": "Metadata Seperator", "description": "Separator between metadata fields when converting to string.", "default": "\n", "type": "string" }, "image": { "title": "Image", "type": "string" }, "image_path": { "title": "Image Path", "type": "string" }, "image_url": { "title": "Image Url", "type": "string" }, "image_mimetype": { "title": "Image Mimetype", "type": "string" }, "text_embedding": { "title": "Text Embedding", "description": "Text embedding of image node, if text field is filled out", "type": "array", "items": { "type": "number" } }, "class_name": { "title": "Class Name", "type": "string", "default": "ImageDocument" } }, "definitions": { "ObjectType": { "title": "ObjectType", "description": "An enumeration.", "enum": [ "1", "2", "3", "4" ], "type": "string" }, "RelatedNodeInfo": { "title": "RelatedNodeInfo", "description": "Base component object to capture class names.", "type": "object", "properties": { "node_id": { "title": "Node Id", "type": "string" }, "node_type": { "$ref": "#/definitions/ObjectType" }, "metadata": { "title": "Metadata", "type": "object" }, "hash": { "title": "Hash", "type": "string" }, "class_name": { "title": "Class Name", "type": "string", "default": "RelatedNodeInfo" } }, "required": [ "node_id" ] } } }
- Config
allow_population_by_field_name: bool = True
validate_assignment: bool = True
- Fields
- classmethod class_name() str #
Get the class name, used as a unique ID in serialization.
This provides a key that makes serialization robust against actual class name changes.