\n", - " | filename | \n", - "contents | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "document_id | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "{\"_name\":\"\",\"type\":\"pdf-document\",\"description... | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "|
1 | \n", - "earth.pdf | \n", - "{\"_name\":\"\",\"type\":\"pdf-document\",\"description... | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.84518433, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Solar System\\nFor more details about the Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.18510437, 570.83258057, 374.99838257, 581... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "|
3 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.87112427, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "|
6 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "|
7 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "
\n", - " | filename | \n", - "contents | \n", - "
---|---|---|
0 | \n", - "mars.pdf | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "
1 | \n", - "mars.pdf | \n", - "Solar System\\nFor more details about the Solar... | \n", - "
2 | \n", - "mars.pdf | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "
3 | \n", - "mars.pdf | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "
4 | \n", - "earth.pdf | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "
5 | \n", - "earth.pdf | \n", - "Solar System\\nFor more details about our Solar... | \n", - "
6 | \n", - "earth.pdf | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "
7 | \n", - "earth.pdf | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "chunk_hash | \n", - "chunk_id | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.84518433, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "4 | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Solar System\\nFor more details about the Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.18510437, 570.83258057, 374.99838257, 581... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "5 | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "6 | \n", - "|
3 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7 | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.87112427, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "0 | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "1 | \n", - "|
6 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "2 | \n", - "|
7 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "3 | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "chunk_hash | \n", - "chunk_id | \n", - "removed | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Solar System\\nFor more details about the Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.18510437, 570.83258057, 374.99838257, 581... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "5 | \n", - "[44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf567... | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "6 | \n", - "[] | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7 | \n", - "[] | \n", - "|
3 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.87112427, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "0 | \n", - "[] | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "1 | \n", - "[] | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "2 | \n", - "[] | \n", - "|
6 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "3 | \n", - "[] | \n", - "
\n", - " | filename | \n", - "contents | \n", - "
---|---|---|
0 | \n", - "mars.pdf | \n", - "Solar System\\nFor more details about the Solar... | \n", - "
1 | \n", - "mars.pdf | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "
2 | \n", - "mars.pdf | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "
3 | \n", - "earth.pdf | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "
4 | \n", - "earth.pdf | \n", - "Solar System\\nFor more details about our Solar... | \n", - "
5 | \n", - "earth.pdf | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "
6 | \n", - "earth.pdf | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "chunk_hash | \n", - "chunk_id | \n", - "removed | \n", - "embeddings | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Solar System\\nFor more details about the Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.18510437, 570.83258057, 374.99838257, 581... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "5 | \n", - "[44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf567... | \n", - "[-0.051861435, 0.0035226212, 0.030617002, 0.04... | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "6 | \n", - "[] | \n", - "[0.07728295, 0.024970993, -0.043180738, 0.0580... | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:34:44.259545 | \n", - "0.845978 | \n", - "mars.pdf | \n", - "6e9fd08a-a4e2-47da-b5a9-bb1e1a3ab6e2 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7 | \n", - "[] | \n", - "[0.10598018, 0.025460618, 0.023627337, 0.03905... | \n", - "|
3 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.87112427, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "0 | \n", - "[] | \n", - "[0.0077404436, -0.02055944, 0.026426593, 0.011... | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "1 | \n", - "[] | \n", - "[-0.062105548, -0.0053322907, 0.031277698, 0.0... | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "2 | \n", - "[] | \n", - "[0.072435796, -0.058001805, -0.019771898, -0.0... | \n", - "|
6 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:34:43.410297 | \n", - "0.794765 | \n", - "earth.pdf | \n", - "efbdbcb9-f0af-42f0-b191-2f14ce3ddc7c | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "3 | \n", - "[] | \n", - "[0.091821924, 0.015197902, 0.07716932, 0.01711... | \n", - "
\n", - " | filename | \n", - "contents | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "document_id | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "{\"_name\":\"\",\"type\":\"pdf-document\",\"description... | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "|
1 | \n", - "earth.pdf | \n", - "{\"_name\":\"\",\"type\":\"pdf-document\",\"description... | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.84518433, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Solar System\\nFor more details about the Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.18510437, 570.83258057, 374.99838257, 581... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "|
3 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.87112427, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "|
6 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "|
7 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "
\n", - " | filename | \n", - "contents | \n", - "
---|---|---|
0 | \n", - "mars.pdf | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "
1 | \n", - "mars.pdf | \n", - "Solar System\\nFor more details about the Solar... | \n", - "
2 | \n", - "mars.pdf | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "
3 | \n", - "mars.pdf | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "
4 | \n", - "earth.pdf | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "
5 | \n", - "earth.pdf | \n", - "Solar System\\nFor more details about our Solar... | \n", - "
6 | \n", - "earth.pdf | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "
7 | \n", - "earth.pdf | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "chunk_hash | \n", - "chunk_id | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.84518433, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "4 | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Solar System\\nFor more details about the Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.18510437, 570.83258057, 374.99838257, 581... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "5 | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "6 | \n", - "|
3 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7 | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.87112427, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "0 | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "1 | \n", - "|
6 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "2 | \n", - "|
7 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "3 | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "chunk_hash | \n", - "chunk_id | \n", - "removed | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Solar System\\nFor more details about the Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.18510437, 570.83258057, 374.99838257, 581... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "dee4c03474c98efdabbadbcc4ce91138c7820f4ac8ff07... | \n", - "5 | \n", - "[44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf567... | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "6 | \n", - "[] | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7 | \n", - "[] | \n", - "|
3 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.87112427, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "0 | \n", - "[] | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "1 | \n", - "[] | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "2 | \n", - "[] | \n", - "|
6 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "3 | \n", - "[] | \n", - "
\n", - " | filename | \n", - "contents | \n", - "
---|---|---|
0 | \n", - "mars.pdf | \n", - "Solar System\\nFor more details about the Solar... | \n", - "
1 | \n", - "mars.pdf | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "
2 | \n", - "mars.pdf | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "
3 | \n", - "earth.pdf | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "
4 | \n", - "earth.pdf | \n", - "Solar System\\nFor more details about our Solar... | \n", - "
5 | \n", - "earth.pdf | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "
6 | \n", - "earth.pdf | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "chunk_id | \n", - "chunk_hash | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.84518433, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "4 | \n", - "-1 | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "6 | \n", - "-1 | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7 | \n", - "-1 | \n", - "|
3 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "1 | \n", - "5 | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "2 | \n", - "-1 | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "3 | \n", - "-1 | \n", - "
\n", - " | filename | \n", - "contents | \n", - "
---|---|---|
0 | \n", - "mars.pdf | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "
1 | \n", - "mars.pdf | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "
2 | \n", - "mars.pdf | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "
3 | \n", - "earth.pdf | \n", - "Solar System\\nFor more details about our Solar... | \n", - "
4 | \n", - "earth.pdf | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "
5 | \n", - "earth.pdf | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "
\n", - " | filename | \n", - "num_pages | \n", - "num_tables | \n", - "num_doc_elements | \n", - "ext | \n", - "hash | \n", - "size | \n", - "date_acquired | \n", - "pdf_convert_time | \n", - "source_filename | \n", - "source_document_id | \n", - "contents | \n", - "doc_jsonpath | \n", - "page_number | \n", - "bbox | \n", - "document_id | \n", - "chunk_id | \n", - "chunk_hash | \n", - "embeddings | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Solar System\\nOur solar system is a vast and f... | \n", - "$.main-text[2] | \n", - "1 | \n", - "[132.84518433, 588.96014404, 479.40917969, 623... | \n", - "44c6e373258c7cdc03f75a8e96a9b160f9aa4e4baf5674... | \n", - "4 | \n", - "-1 | \n", - "[0.0077404897, -0.020559434, 0.026426662, 0.01... | \n", - "|
1 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Mars\\nMars, the fourth planet from the Sun, is... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.87440491, 500.84011841, 477.48345947, 534... | \n", - "a31663e06fac41470ecc459f5a58658a3f9997d7801053... | \n", - "6 | \n", - "-1 | \n", - "[0.07728298, 0.024971062, -0.04318075, 0.05809... | \n", - "|
2 | \n", - "mars.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "8edd5dfbf888777120b528a5d8998f2757d006df0eaef7... | \n", - "2800 | \n", - "2024-10-18T13:30:59.490007 | \n", - "2.011138 | \n", - "mars.pdf | \n", - "62e5639f-f922-4ccc-a041-3cb02f1cfd83 | \n", - "Basic facts about Mars:\\nยท Distance from the S... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.2026062, 482.90710449, 237.04431152, 493.... | \n", - "7ff317954ec5f3b15607c053c30c2b0db0f6b64cc3295a... | \n", - "7 | \n", - "-1 | \n", - "[0.1059802, 0.025460616, 0.02362733, 0.0390564... | \n", - "|
3 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Solar System\\nFor more details about our Solar... | \n", - "$.main-text[3] | \n", - "1 | \n", - "[133.20942688, 570.81555176, 375.57919312, 581... | \n", - "d7be13d7dee96cf2384072d0eb01981e0e75eec2e7bc6d... | \n", - "1 | \n", - "5 | \n", - "[-0.062105577, -0.0053322953, 0.03127779, 0.04... | \n", - "|
4 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nEarth is the third planet from the Sun.... | \n", - "$.main-text[5] | \n", - "1 | \n", - "[132.91053772, 512.46295166, 477.84887695, 534... | \n", - "7c4a750e2215f231803a6f8078bde1e9699034fb033dd3... | \n", - "2 | \n", - "-1 | \n", - "[0.0724358, -0.058001805, -0.01977186, -0.0243... | \n", - "|
5 | \n", - "earth.pdf | \n", - "1 | \n", - "0 | \n", - "11 | \n", - "18713f970989055625bef22209b6f4b6830b9ca22046bf... | \n", - "2686 | \n", - "2024-10-18T13:30:59.494027 | \n", - "2.015123 | \n", - "earth.pdf | \n", - "f3c0ac2e-1de2-472b-8216-2043f3b3e9d1 | \n", - "Earth\\nBasic facts about Earth:\\nยท Distance fr... | \n", - "$.main-text[6] | \n", - "1 | \n", - "[133.30151367, 494.86206055, 240.17156982, 505... | \n", - "189a221704d17feeb96b1b1ef60a2a2445459848cd8e8f... | \n", - "3 | \n", - "-1 | \n", - "[0.091821924, 0.015197907, 0.07716932, 0.01711... | \n", - "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "date_acquired | \n", + "pdf_convert_time | \n", + "source_filename | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "52b1cdf4-b1ef-4375-8e6b-23f174592c06 | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "2025-02-04T23:06:20.470544 | \n", + "0.693593 | \n", + "lorem-ipsum.pdf | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "854dca5d-9db5-4ea5-b2e5-bddd176bf1b8 | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "2025-02-04T23:06:21.819893 | \n", + "0.676735 | \n", + "spam.pdf | \n", + "|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "875d0907-8dd3-4ef9-b3b0-a0083e7ad438 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "2025-02-04T23:06:19.774915 | \n", + "0.641045 | \n", + "earth2.pdf | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "6264e62a-0121-4cd4-8202-ea6e228e15f1 | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "2025-02-04T23:06:21.141230 | \n", + "0.668992 | \n", + "mars.pdf | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "582bc53b-96e2-4b09-8dd7-6a27a685a53e | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:06:18.199803 | \n", + "1.053618 | \n", + "earth-copy.pdf | \n", + "|
5 | \n", + "earth.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "c6c18475-9365-4325-85dc-8acf6b969d8f | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:06:19.132090 | \n", + "0.929218 | \n", + "earth.pdf | \n", + "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "date_acquired | \n", + "pdf_convert_time | \n", + "source_filename | \n", + "doc_hash | \n", + "int_id_column | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "52b1cdf4-b1ef-4375-8e6b-23f174592c06 | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "2025-02-04T23:06:20.470544 | \n", + "0.693593 | \n", + "lorem-ipsum.pdf | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "3 | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "854dca5d-9db5-4ea5-b2e5-bddd176bf1b8 | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "2025-02-04T23:06:21.819893 | \n", + "0.676735 | \n", + "spam.pdf | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "5 | \n", + "|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "875d0907-8dd3-4ef9-b3b0-a0083e7ad438 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "2025-02-04T23:06:19.774915 | \n", + "0.641045 | \n", + "earth2.pdf | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "2 | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "6264e62a-0121-4cd4-8202-ea6e228e15f1 | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "2025-02-04T23:06:21.141230 | \n", + "0.668992 | \n", + "mars.pdf | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "4 | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "582bc53b-96e2-4b09-8dd7-6a27a685a53e | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:06:18.199803 | \n", + "1.053618 | \n", + "earth-copy.pdf | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "0 | \n", + "|
5 | \n", + "earth.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "c6c18475-9365-4325-85dc-8acf6b969d8f | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:06:19.132090 | \n", + "0.929218 | \n", + "earth.pdf | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "1 | \n", + "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "date_acquired | \n", + "pdf_convert_time | \n", + "source_filename | \n", + "doc_hash | \n", + "int_id_column | \n", + "removed | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "52b1cdf4-b1ef-4375-8e6b-23f174592c06 | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "2025-02-04T23:06:20.470544 | \n", + "0.693593 | \n", + "lorem-ipsum.pdf | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "3 | \n", + "[] | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "854dca5d-9db5-4ea5-b2e5-bddd176bf1b8 | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "2025-02-04T23:06:21.819893 | \n", + "0.676735 | \n", + "spam.pdf | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "5 | \n", + "[] | \n", + "|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "875d0907-8dd3-4ef9-b3b0-a0083e7ad438 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "2025-02-04T23:06:19.774915 | \n", + "0.641045 | \n", + "earth2.pdf | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "2 | \n", + "[] | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "6264e62a-0121-4cd4-8202-ea6e228e15f1 | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "2025-02-04T23:06:21.141230 | \n", + "0.668992 | \n", + "mars.pdf | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "4 | \n", + "[] | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "582bc53b-96e2-4b09-8dd7-6a27a685a53e | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:06:18.199803 | \n", + "1.053618 | \n", + "earth-copy.pdf | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "0 | \n", + "[] | \n", + "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "date_acquired | \n", + "pdf_convert_time | \n", + "source_filename | \n", + "doc_hash | \n", + "int_id_column | \n", + "removed | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "52b1cdf4-b1ef-4375-8e6b-23f174592c06 | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "2025-02-04T23:06:20.470544 | \n", + "0.693593 | \n", + "lorem-ipsum.pdf | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "3 | \n", + "[] | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "854dca5d-9db5-4ea5-b2e5-bddd176bf1b8 | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "2025-02-04T23:06:21.819893 | \n", + "0.676735 | \n", + "spam.pdf | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "5 | \n", + "[] | \n", + "|
2 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "6264e62a-0121-4cd4-8202-ea6e228e15f1 | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "2025-02-04T23:06:21.141230 | \n", + "0.668992 | \n", + "mars.pdf | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "4 | \n", + "[] | \n", + "|
3 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "582bc53b-96e2-4b09-8dd7-6a27a685a53e | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:06:18.199803 | \n", + "1.053618 | \n", + "earth-copy.pdf | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "0 | \n", + "[] | \n", + "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "... | \n", + "docq_mean_word_len | \n", + "docq_symbol_to_word_ratio | \n", + "docq_sentence_count | \n", + "docq_lorem_ipsum_ratio | \n", + "docq_curly_bracket_ratio | \n", + "docq_contain_bad_word | \n", + "docq_bullet_point_ratio | \n", + "docq_ellipsis_line_ratio | \n", + "docq_alphabet_word_ratio | \n", + "docq_contain_common_en_words | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "52b1cdf4-b1ef-4375-8e6b-23f174592c06 | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "... | \n", + "5.000000 | \n", + "0.000000 | \n", + "1 | \n", + "0.085714 | \n", + "0.0 | \n", + "False | \n", + "0.000000 | \n", + "0.0 | \n", + "1.000000 | \n", + "False | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "854dca5d-9db5-4ea5-b2e5-bddd176bf1b8 | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "... | \n", + "3.500000 | \n", + "0.000000 | \n", + "1 | \n", + "0.000000 | \n", + "0.0 | \n", + "True | \n", + "0.000000 | \n", + "0.0 | \n", + "1.000000 | \n", + "False | \n", + "|
2 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "6264e62a-0121-4cd4-8202-ea6e228e15f1 | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "... | \n", + "4.688000 | \n", + "0.032000 | \n", + "8 | \n", + "0.000000 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880000 | \n", + "True | \n", + "|
3 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "582bc53b-96e2-4b09-8dd7-6a27a685a53e | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "... | \n", + "4.541284 | \n", + "0.027523 | \n", + "9 | \n", + "0.000000 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880734 | \n", + "True | \n", + "
4 rows ร 27 columns
\n", + "\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "... | \n", + "docq_mean_word_len | \n", + "docq_symbol_to_word_ratio | \n", + "docq_sentence_count | \n", + "docq_lorem_ipsum_ratio | \n", + "docq_curly_bracket_ratio | \n", + "docq_contain_bad_word | \n", + "docq_bullet_point_ratio | \n", + "docq_ellipsis_line_ratio | \n", + "docq_alphabet_word_ratio | \n", + "docq_contain_common_en_words | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "6264e62a-0121-4cd4-8202-ea6e228e15f1 | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "... | \n", + "4.688000 | \n", + "0.032000 | \n", + "8 | \n", + "0.0 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880000 | \n", + "True | \n", + "|
3 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "582bc53b-96e2-4b09-8dd7-6a27a685a53e | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "... | \n", + "4.541284 | \n", + "0.027523 | \n", + "9 | \n", + "0.0 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880734 | \n", + "True | \n", + "
2 rows ร 27 columns
\n", + "\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "date_acquired | \n", + "pdf_convert_time | \n", + "source_filename | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "3618834f-9dfc-49a1-9066-e2724df95fec | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "2025-02-04T23:08:56.820444 | \n", + "1.846058 | \n", + "lorem-ipsum.pdf | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "27880888-8e1a-4b46-a6a9-fecba8eee0eb | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "2025-02-04T23:08:58.414120 | \n", + "1.590731 | \n", + "spam.pdf | \n", + "|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "84f59118-2a64-4d4b-991c-10ca09576a74 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "2025-02-04T23:08:56.713495 | \n", + "1.827202 | \n", + "earth2.pdf | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "71ef93eb-66d3-4a21-bb47-cf4b85d4f8ff | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "2025-02-04T23:08:58.272496 | \n", + "1.547326 | \n", + "mars.pdf | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "7ce227b2-66cb-4e2e-b76b-3a0a8c9d2f44 | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:08:54.872145 | \n", + "1.864833 | \n", + "earth-copy.pdf | \n", + "|
5 | \n", + "earth.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "5b12b0e8-946f-4538-8812-9ee74204c2d7 | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:08:54.969828 | \n", + "1.962273 | \n", + "earth.pdf | \n", + "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "date_acquired | \n", + "pdf_convert_time | \n", + "source_filename | \n", + "doc_hash | \n", + "int_id_column | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "3618834f-9dfc-49a1-9066-e2724df95fec | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "2025-02-04T23:08:56.820444 | \n", + "1.846058 | \n", + "lorem-ipsum.pdf | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "3 | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "27880888-8e1a-4b46-a6a9-fecba8eee0eb | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "2025-02-04T23:08:58.414120 | \n", + "1.590731 | \n", + "spam.pdf | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "5 | \n", + "|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "84f59118-2a64-4d4b-991c-10ca09576a74 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "2025-02-04T23:08:56.713495 | \n", + "1.827202 | \n", + "earth2.pdf | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "2 | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "71ef93eb-66d3-4a21-bb47-cf4b85d4f8ff | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "2025-02-04T23:08:58.272496 | \n", + "1.547326 | \n", + "mars.pdf | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "4 | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "7ce227b2-66cb-4e2e-b76b-3a0a8c9d2f44 | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:08:54.872145 | \n", + "1.864833 | \n", + "earth-copy.pdf | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "1 | \n", + "|
5 | \n", + "earth.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "5b12b0e8-946f-4538-8812-9ee74204c2d7 | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:08:54.969828 | \n", + "1.962273 | \n", + "earth.pdf | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "0 | \n", + "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "date_acquired | \n", + "pdf_convert_time | \n", + "source_filename | \n", + "doc_hash | \n", + "int_id_column | \n", + "removed | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "3618834f-9dfc-49a1-9066-e2724df95fec | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "2025-02-04T23:08:56.820444 | \n", + "1.846058 | \n", + "lorem-ipsum.pdf | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "3 | \n", + "[] | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "27880888-8e1a-4b46-a6a9-fecba8eee0eb | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "2025-02-04T23:08:58.414120 | \n", + "1.590731 | \n", + "spam.pdf | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "5 | \n", + "[] | \n", + "|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "84f59118-2a64-4d4b-991c-10ca09576a74 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "2025-02-04T23:08:56.713495 | \n", + "1.827202 | \n", + "earth2.pdf | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "2 | \n", + "[] | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "71ef93eb-66d3-4a21-bb47-cf4b85d4f8ff | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "2025-02-04T23:08:58.272496 | \n", + "1.547326 | \n", + "mars.pdf | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "4 | \n", + "[] | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "7ce227b2-66cb-4e2e-b76b-3a0a8c9d2f44 | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:08:54.872145 | \n", + "1.864833 | \n", + "earth-copy.pdf | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "1 | \n", + "[] | \n", + "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "date_acquired | \n", + "pdf_convert_time | \n", + "source_filename | \n", + "doc_hash | \n", + "int_id_column | \n", + "removed | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "3618834f-9dfc-49a1-9066-e2724df95fec | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "2025-02-04T23:08:56.820444 | \n", + "1.846058 | \n", + "lorem-ipsum.pdf | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "3 | \n", + "[] | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "27880888-8e1a-4b46-a6a9-fecba8eee0eb | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "2025-02-04T23:08:58.414120 | \n", + "1.590731 | \n", + "spam.pdf | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "5 | \n", + "[] | \n", + "|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "84f59118-2a64-4d4b-991c-10ca09576a74 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "2025-02-04T23:08:56.713495 | \n", + "1.827202 | \n", + "earth2.pdf | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "2 | \n", + "[] | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "71ef93eb-66d3-4a21-bb47-cf4b85d4f8ff | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "2025-02-04T23:08:58.272496 | \n", + "1.547326 | \n", + "mars.pdf | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "4 | \n", + "[] | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "7ce227b2-66cb-4e2e-b76b-3a0a8c9d2f44 | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "2025-02-04T23:08:54.872145 | \n", + "1.864833 | \n", + "earth-copy.pdf | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "1 | \n", + "[] | \n", + "
\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "... | \n", + "docq_mean_word_len | \n", + "docq_symbol_to_word_ratio | \n", + "docq_sentence_count | \n", + "docq_lorem_ipsum_ratio | \n", + "docq_curly_bracket_ratio | \n", + "docq_contain_bad_word | \n", + "docq_bullet_point_ratio | \n", + "docq_ellipsis_line_ratio | \n", + "docq_alphabet_word_ratio | \n", + "docq_contain_common_en_words | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", + "lorem-ipsum.pdf | \n", + "Lorem ipsum Lorem ipsum Lorem ipsum | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "3618834f-9dfc-49a1-9066-e2724df95fec | \n", + "6571294142213095721 | \n", + "bc012d063005cc02deb6c2592d1f8c3b273625edf9eec5... | \n", + "35 | \n", + "... | \n", + "5.000000 | \n", + "0.000000 | \n", + "1 | \n", + "0.085714 | \n", + "0.0 | \n", + "False | \n", + "0.000000 | \n", + "0.0 | \n", + "1.000000 | \n", + "False | \n", + "|
1 | \n", + "spam.pdf | \n", + "Free xxx | \n", + "1 | \n", + "0 | \n", + "2 | \n", + "27880888-8e1a-4b46-a6a9-fecba8eee0eb | \n", + "10026122586747302274 | \n", + "543ffc97aef373ee009a5f908e0358ef80d329ca7ba964... | \n", + "8 | \n", + "... | \n", + "3.500000 | \n", + "0.000000 | \n", + "1 | \n", + "0.000000 | \n", + "0.0 | \n", + "True | \n", + "0.000000 | \n", + "0.0 | \n", + "1.000000 | \n", + "False | \n", + "|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "84f59118-2a64-4d4b-991c-10ca09576a74 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "... | \n", + "4.541284 | \n", + "0.027523 | \n", + "9 | \n", + "0.000000 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880734 | \n", + "True | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "71ef93eb-66d3-4a21-bb47-cf4b85d4f8ff | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "... | \n", + "4.688000 | \n", + "0.032000 | \n", + "8 | \n", + "0.000000 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880000 | \n", + "True | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "7ce227b2-66cb-4e2e-b76b-3a0a8c9d2f44 | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "... | \n", + "4.541284 | \n", + "0.027523 | \n", + "9 | \n", + "0.000000 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880734 | \n", + "True | \n", + "
5 rows ร 27 columns
\n", + "\n", + " | filename | \n", + "contents | \n", + "num_pages | \n", + "num_tables | \n", + "num_doc_elements | \n", + "document_id | \n", + "document_hash | \n", + "ext | \n", + "hash | \n", + "size | \n", + "... | \n", + "docq_mean_word_len | \n", + "docq_symbol_to_word_ratio | \n", + "docq_sentence_count | \n", + "docq_lorem_ipsum_ratio | \n", + "docq_curly_bracket_ratio | \n", + "docq_contain_bad_word | \n", + "docq_bullet_point_ratio | \n", + "docq_ellipsis_line_ratio | \n", + "docq_alphabet_word_ratio | \n", + "docq_contain_common_en_words | \n", + "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2 | \n", + "earth2.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "84f59118-2a64-4d4b-991c-10ca09576a74 | \n", + "10729312978404042321 | \n", + "f039191d59ce8ba25023a844f9b99e7ef2ea4bf75a23f4... | \n", + "610 | \n", + "... | \n", + "4.541284 | \n", + "0.027523 | \n", + "9 | \n", + "0.0 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880734 | \n", + "True | \n", + "|
3 | \n", + "mars.pdf | \n", + "## Mars\\n\\n## Solar System\\n\\nOur solar system... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "71ef93eb-66d3-4a21-bb47-cf4b85d4f8ff | \n", + "7758129997476962679 | \n", + "a3a4bb3b8f4f441d6d669e09f0cd07a9420d06850cf63e... | \n", + "717 | \n", + "... | \n", + "4.688000 | \n", + "0.032000 | \n", + "8 | \n", + "0.0 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880000 | \n", + "True | \n", + "|
4 | \n", + "earth-copy.pdf | \n", + "## Earth\\n\\n## Solar System\\n\\nOur solar syste... | \n", + "1 | \n", + "0 | \n", + "11 | \n", + "7ce227b2-66cb-4e2e-b76b-3a0a8c9d2f44 | \n", + "14711865278795535908 | \n", + "6140cf695f269a3ddca6568536076756105ad3186086b2... | \n", + "610 | \n", + "... | \n", + "4.541284 | \n", + "0.027523 | \n", + "9 | \n", + "0.0 | \n", + "0.0 | \n", + "False | \n", + "0.176471 | \n", + "0.0 | \n", + "0.880734 | \n", + "True | \n", + "
3 rows ร 27 columns
\n", + "