Pipeline
Turn the document drop into verified experiment records — work the steps left to right.
1
Discoversee what's in the drop
2
Extractdocuments → data, checked as you go
3
Linkconnect to experiments
4
Browsethe experiment records
Qwen extract ×14 — Old ELN
Status
done
Started18:25:47 → 18:52:31
Steps16
Log
$ [1/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Exp 19 pdf/9076 Data for Raven POC project/Old ELN/Exp 19.pdf /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh: line 9: /Users/moryasolutions/local-docqa/projects/test-project/.venv/bin/python: No such file or directory direct extraction failed — falling back to Qwen agent Fragment written: - `qwen-extract--exp-19--lbn-19` — aliases: `LBN 19` $ [2/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Exp 49 pdf/9076 Data for Raven POC project/Old ELN/Exp 49.pdf wrote qwen-extract--exp-49--lbn-49 aliases=['LBN 49', 'R225100845'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'procedure_summary', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [3/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/LBN 23 pdf/9076 Data for Raven POC project/Old ELN/LBN 23.pdf wrote qwen-extract--LBN-23--LBN-23 aliases=['LBN 23', 'R226011203'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'procedure_summary', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [4/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/LBN 3 pdf/9076 Data for Raven POC project/Old ELN/LBN 3.pdf wrote qwen-extract--LBN-3--LBN-3 aliases=['LBN 3', 'R226011203'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [5/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/LBN 8 pdf/9076 Data for Raven POC project/Old ELN/LBN 8.pdf wrote qwen-extract--LBN-8--LBN-8 aliases=['LBN 8', 'R226011203'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'field_confidence', 'materials', 'outcome', 'procedure_summary', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [6/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batc 40 pdf/9076 Data for Raven POC project/Old ELN/Lab Batc 40.pdf wrote qwen-extract--lab-batc-40--lbn-40 aliases=['LBN 40', 'R226011203'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [7/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batch 12 pdf/9076 Data for Raven POC project/Old ELN/Lab Batch 12.pdf wrote qwen-extract--lab-batch-12--lbn-12 aliases=['LBN 12'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [8/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batch 16 pdf/9076 Data for Raven POC project/Old ELN/Lab Batch 16.pdf wrote qwen-extract--lab-batch-16--lbn-16 aliases=['LBN 16'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'field_confidence', 'materials', 'outcome', 'procedure_summary', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [9/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batch 24A pdf/9076 Data for Raven POC project/Old ELN/Lab Batch 24A.pdf wrote qwen-extract--lab-batch-24a--lbn-24a aliases=['LBN 24A', 'R225100845'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [10/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batch 26 pdf/9076 Data for Raven POC project/Old ELN/Lab Batch 26.pdf wrote qwen-extract--lab-batch-26--lbn-26 aliases=['LBN 26', 'R225100845'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [11/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batch 30 pdf/9076 Data for Raven POC project/Old ELN/Lab Batch 30.pdf wrote qwen-extract--lab-batch-30--lbn-30 aliases=['LBN 30'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [12/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batch 35 pdf/9076 Data for Raven POC project/Old ELN/Lab Batch 35.pdf wrote qwen-extract--lab-batch-35--lbn-35 aliases=['LBN 35'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [13/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batch 48 pdf/9076 Data for Raven POC project/Old ELN/Lab Batch 48.pdf wrote qwen-extract--lab-batch-48--lbn-48 aliases=['LBN 48', 'R226011203'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [14/16] bash /Users/moryasolutions/local-docqa/scripts/pipeline/extract_doc.sh ocr/Lab Batch 51 pdf/9076 Data for Raven POC project/Old ELN/Lab Batch 51.pdf wrote qwen-extract--lab-batch-51--lbn-51 aliases=['LBN 51', 'R225100845'] payload_fields=['aim', 'conclusion', 'conditions', 'critical_parameters', 'critical_process_parameters', 'date', 'eln_form', 'materials', 'outcome', 'process_steps', 'scientist'] 1 fragment(s) wrote, 0 rejected $ [15/16] /Users/moryasolutions/local-docqa/.venv/bin/python /Users/moryasolutions/local-docqa/scripts/pipeline/merge_records.py # Record pipeline run report — 2026-08-27 - fragments merged: 14 (0 ignored by human review) - records: 14 (0 stubs needing linking review) - records with conflicts: 0 - corrections re-applied: 0 - schema-invalid records: 0 - unlinked fragments: 0 ## Diff vs previous run - records added: 14 — exp-9076-003, exp-9076-008, exp-9076-012, exp-9076-016, exp-9076-019, exp-9076-023, exp-9076-024A, exp-9076-026, exp-9076-030, exp-9076-035, exp-9076-040, exp-9076-048, exp-9076-049, exp-9076-051 - records removed: 0 - records changed: 0 $ [16/16] /Users/moryasolutions/local-docqa/.venv/bin/python /Users/moryasolutions/local-docqa/scripts/pipeline/crawl_sources.py crawl_sources: 49 files in 10 categories; 38 ingested, 14 extracted, 20 with suggestions; crawl diff +0 ~0 -0