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

307 lines
8.4 KiB
JSON

[
{
"type": "Title",
"element_id": "307afee17dac4c598e361c095338decd",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Copy and paste this section for each week."
},
{
"type": "Title",
"element_id": "b980a145c5e8c9e233a0643366ba520a",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1,
"emphasized_text_contents": [
"Win"
],
"emphasized_text_tags": [
"strong"
]
},
"text": "Win"
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": ""
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": ""
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": ""
},
{
"type": "Title",
"element_id": "aecc044c7725a6555114285dc28fe2d1",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1,
"emphasized_text_contents": [
"Needs input"
],
"emphasized_text_tags": [
"strong"
]
},
"text": "Needs input"
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": ""
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": ""
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": ""
},
{
"type": "Title",
"element_id": "9d3cab2b5efed4eaef42a707dbc813da",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1,
"emphasized_text_contents": [
"Focus"
],
"emphasized_text_tags": [
"strong"
]
},
"text": "Focus"
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": ""
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": ""
},
{
"type": "Table",
"element_id": "a240e43c0ae70731c65ae5430d2dab7f",
"metadata": {
"data_source": {
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605942",
"version": "1",
"record_locator": {
"url": "https://unstructured-ingest-test.atlassian.net",
"page_id": "1605942"
},
"date_created": "2023-07-09T12:54:45.226000",
"date_modified": "2023-07-09T12:54:45.226000"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1,
"text_as_html": "<table><br><tbody><br><tr><td>Notes </td></tr><br><tr><td>Important Links</td></tr><br></tbody><br></table>"
},
"text": "Notes Important Links"
}
]