Roman Isecke 135aa65906
update ingest pipeline to share ingest docs via multiprocessing.manager.dict (#1814)
### Description
* If the contents of a doc were updated by the process of
reading/downloading it, this was not being persisted. To fix this, the
data being passed around was updated to use a multiprocessing safe dict
rather than the json string. Now that dict is updated after the
`get_file` method is called.
* Wikipedia connector was updated to use a static filename rather than
one requiring a call to fetch data.
* The read config param `re_download` was not being leveraged by the
source node, this was fixed.
* Added fix: chunking and embedding order reversed so chunking runs
before embeddings

---------

Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com>
Co-authored-by: rbiseck3 <rbiseck3@users.noreply.github.com>
2023-10-25 22:04:27 +00:00

775 lines
23 KiB
JSON

[
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "Title",
"element_id": "e7f29a76338c0f4d24e30d18e6f336ee",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2"
},
{
"type": "ListItem",
"element_id": "83cd16582f7c6143822c0954f7f00350",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 List Item 1Testdoc2 List Item 1 Nested Item ATestdoc2 List Item 1 Nested Item B"
},
{
"type": "ListItem",
"element_id": "4e97e8a96031986042c3bec526dd273f",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 List Item 2"
},
{
"type": "ListItem",
"element_id": "629e4dee8b4acc5b39782b4d012ab83c",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 List Item 3"
},
{
"type": "ListItem",
"element_id": "d177691364d515d6eaa385205a64664c",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 List Item 4"
},
{
"type": "ListItem",
"element_id": "f7a3306959cba883aca00f29ca138b6a",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 List Item 5"
},
{
"type": "NarrativeText",
"element_id": "3d15d9222ffb2770ceede5b6532e842a",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1,
"link_urls": [
"https://www.unstructured.io/"
],
"link_texts": [
"This is the link for unstructured . io."
]
},
"text": "This is the link for unstructured . io."
},
{
"type": "ListItem",
"element_id": "fcb6283714c2b7640835964291e59ebd",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1,
"emphasized_text_contents": [
"Testdoc2 Checklist Item 1"
],
"emphasized_text_tags": [
"span"
]
},
"text": "Testdoc2 Checklist Item 1"
},
{
"type": "ListItem",
"element_id": "899f082b917d5e6e380f15705db5923a",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1,
"emphasized_text_contents": [
"Testdoc2 Checklist Item 2 (checked)"
],
"emphasized_text_tags": [
"span"
]
},
"text": "Testdoc2 Checklist Item 2 (checked)"
},
{
"type": "ListItem",
"element_id": "07005b9f1774ceabf978b2cc8afb7183",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1,
"emphasized_text_contents": [
"Testdoc2 Checklist Item 3"
],
"emphasized_text_tags": [
"span"
]
},
"text": "Testdoc2 Checklist Item 3"
},
{
"type": "UncategorizedText",
"element_id": "86e0e9ce51725074a3dc41ed3f10c13c",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "😃 😃 😃 😃 😃 😃 😃 😃 😃 😃 😃 😃"
},
{
"type": "NarrativeText",
"element_id": "72fa9ecafbf0df76a3b307485ce4c98b",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1,
"emphasized_text_contents": [
"Testdoc2 bold text"
],
"emphasized_text_tags": [
"strong"
]
},
"text": "Testdoc2 bold text"
},
{
"type": "Title",
"element_id": "552ed5322965c5e1e8b235b0373f2470",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1,
"emphasized_text_contents": [
"Testdoc2 italic text"
],
"emphasized_text_tags": [
"em"
]
},
"text": "Testdoc2 italic text"
},
{
"type": "Title",
"element_id": "6e11265369ab068c620fc2a2b7b858f5",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 Heading 1 Sized Text"
},
{
"type": "Title",
"element_id": "4da0847af03e9440530539d6da679e85",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 Heading 2 Sized Text"
},
{
"type": "Title",
"element_id": "2003a49a54c45aae0cd7640f47ea3f41",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 Heading 3 Sized Text"
},
{
"type": "Title",
"element_id": "ab09ddfa08278cd006e9ea2201c8989d",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 Heading 4 Sized Text"
},
{
"type": "Title",
"element_id": "4ad754b028bec050fbff5ce2f50c60d1",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1
},
"text": "Testdoc2 Heading 5 Sized Text"
},
{
"type": "Table",
"element_id": "a164cd72991a3856b7bbc6d52d8b04bf",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1802252"
},
"date_created": "2023-07-11T17:01:39.240000",
"date_modified": "2023-07-11T17:01:47.340000"
},
"filetype": "text/html",
"languages": [
"eng",
"fra"
],
"page_number": 1,
"text_as_html": "<table><br><tbody><br><tr><td>Testdoc2 Table: Column 1 Row 0</td><td>Testdoc2 Table: Column 2 Row 0</td><td>Testdoc2 Table: Column 3 Row 0</td></tr><br><tr><td>Testdoc2 Table: Column 1 Row 1</td><td>Testdoc2 Table: Column 2 Row 1</td><td>Testdoc2 Table: Column 3 Row 1</td></tr><br><tr><td>Testdoc2 Table: Column 1 Row 2</td><td>Testdoc2 Table: Column 2 Row 2</td><td>Testdoc2 Table: Column 3 Row 2</td></tr><br></tbody><br></table>"
},
"text": "Testdoc2 Table: Column 1 Row 0 Testdoc2 Table: Column 2 Row 0 Testdoc2 Table: Column 3 Row 0 Testdoc2 Table: Column 1 Row 1 Testdoc2 Table: Column 2 Row 1 Testdoc2 Table: Column 3 Row 1 Testdoc2 Table: Column 1 Row 2 Testdoc2 Table: Column 2 Row 2 Testdoc2 Table: Column 3 Row 2"
}
]