mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-09-09 08:39:57 +00:00
086b8d6f8a
**Summary** Step 2 in prep for pluggable auto-partitioners, remove `regex_metadata` field from `ElementMetadata`. **Additional Context** - "regex-metadata" was an experimental feature that didn't pan out. - It's implemented by one of the post-partitioning metadata decorators, so get rid of it as part of the cleanup before consolidating those decorators.
145 lines
3.7 KiB
JSON
145 lines
3.7 KiB
JSON
{
|
|
"properties": {
|
|
"element_id": {
|
|
"type": "keyword"
|
|
},
|
|
"text": {
|
|
"type": "text",
|
|
"analyzer": "english"
|
|
},
|
|
"type": {
|
|
"type": "text"
|
|
},
|
|
"embeddings": {
|
|
"type": "dense_vector",
|
|
"dims": 384,
|
|
"index": "true",
|
|
"similarity": "cosine"
|
|
},
|
|
"metadata": {
|
|
"type": "object",
|
|
"properties": {
|
|
"category_depth": {
|
|
"type": "integer"
|
|
},
|
|
"parent_id": {
|
|
"type": "keyword"
|
|
},
|
|
"attached_to_filename": {
|
|
"type": "keyword"
|
|
},
|
|
"filetype": {
|
|
"type": "keyword"
|
|
},
|
|
"last_modified": {
|
|
"type": "date"
|
|
},
|
|
"file_directory": {
|
|
"type": "keyword"
|
|
},
|
|
"filename": {
|
|
"type": "keyword"
|
|
},
|
|
"data_source": {
|
|
"type": "object",
|
|
"properties": {
|
|
"url": {
|
|
"type": "text",
|
|
"analyzer": "standard"
|
|
},
|
|
"version": {
|
|
"type": "keyword"
|
|
},
|
|
"date_created": {
|
|
"type": "date"
|
|
},
|
|
"date_modified": {
|
|
"type": "date"
|
|
},
|
|
"date_processed": {
|
|
"type": "date"
|
|
},
|
|
"record_locator": {
|
|
"type": "keyword"
|
|
},
|
|
"permissions_data": {
|
|
"type": "object"
|
|
}
|
|
}
|
|
},
|
|
"coordinates": {
|
|
"type": "object",
|
|
"properties": {
|
|
"system": {
|
|
"type": "keyword"
|
|
},
|
|
"layout_width": {
|
|
"type": "float"
|
|
},
|
|
"layout_height": {
|
|
"type": "float"
|
|
},
|
|
"points": {
|
|
"type": "float"
|
|
}
|
|
}
|
|
},
|
|
"languages": {
|
|
"type": "keyword"
|
|
},
|
|
"page_number": {
|
|
"type": "integer"
|
|
},
|
|
"page_name": {
|
|
"type": "keyword"
|
|
},
|
|
"url": {
|
|
"type": "text",
|
|
"analyzer": "standard"
|
|
},
|
|
"links": {
|
|
"type": "object"
|
|
},
|
|
"link_urls": {
|
|
"type": "text"
|
|
},
|
|
"link_texts": {
|
|
"type": "text"
|
|
},
|
|
"sent_from": {
|
|
"type": "text",
|
|
"analyzer": "standard"
|
|
},
|
|
"sent_to": {
|
|
"type": "text",
|
|
"analyzer": "standard"
|
|
},
|
|
"subject": {
|
|
"type": "text",
|
|
"analyzer": "standard"
|
|
},
|
|
"section": {
|
|
"type": "text",
|
|
"analyzer": "standard"
|
|
},
|
|
"header_footer_type": {
|
|
"type": "keyword"
|
|
},
|
|
"emphasized_text_contents": {
|
|
"type": "text"
|
|
},
|
|
"emphasized_text_tags": {
|
|
"type": "keyword"
|
|
},
|
|
"text_as_html": {
|
|
"type": "text",
|
|
"analyzer": "standard"
|
|
},
|
|
"detection_class_prob": {
|
|
"type": "float"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|