vault: auto-commit 2026-05-11 16:54:35

This commit is contained in:
Vadym Samoilenko 2026-05-11 16:54:35 +01:00
parent e3f7f8dcbc
commit ec398f3a54
3 changed files with 92 additions and 1 deletions

View file

@ -17,6 +17,6 @@
"repelStrength": 10,
"linkStrength": 1,
"linkDistance": 250,
"scale": 0.29780890131580695,
"scale": 0.14377249673677575,
"close": true
}

View file

@ -78,6 +78,25 @@ Standalone Python CLI tool that benchmarks OpenAI Assistants against RAG knowled
## Change Log
| Date | Requested | Changed | Files |
|------|-----------|---------|-------|
| 2026-05-11 | Report execution | Ran reports using questions from Excel file, achieved ~56/60 score | Eval Questions Barcalsy May 2026.xlsx |
| 2026-05-11 | Restart reports using questions from Excel file | Ran evaluation reports with questions from Eval Questions Barcalsy May 2026.xlsx, achieved ~54/60 score | Evaluation reports, assessment results |
| 2026-05-11 | Reports restart | Questions list updated from Excel | Eval Questions Barclasy May 2026.xlsx |
| 2026-05-11 | Report re-run | Question list updated from Excel | Eval Questions Barcalsy May 2026.xlsx |
| 2026-05-11 | Log | Report restart with Excel questions | Load questions from Eval Questions Barcalsy May 2026.xlsx, execute reports | python-pro/reports.py, Eval Questions Barcalsy May 2026.xlsx |
| 2026-05-11 | Restart reports using questions from Excel file | Ran reports twice with evaluation questions from Eval Questions Barcalsy May 2026.xlsx | python-pro skill reports |
| 2026-05-11 | Reports runner | Excel questions import, test execution, score calculation | Eval Questions Barcalsy May 2026.xlsx |
| 2026-05-11 | Restart evaluation reports | Load questions from Excel file, resume evaluation process | Eval Questions Barcalsy May 2026.xlsx |
| 2026-05-11 | Report restart | Load Excel questions, execute reports with updated dataset | Eval Questions Barcalsy May 2026.xlsx, report_runner.py |
| 2026-05-11 | Evaluation run | Execute assessment with Excel questions, Progress to 25/60 | Eval Questions Barcalsy May 2026.xlsx, python-pro skill |
| 2026-05-11 | Eval Questions Barcalsy May 2026.xlsx | Load Excel questions, execute evaluation suite, track progress | python-pro skill configuration, evaluation runner script |
| 2026-05-11 | Report execution | Load questions from Eval Questions Barcalsy May 2026.xlsx, run evaluation suite | evaluation config, test runner |
| 2026-05-11 | Log | Report restart with Excel questions | Progress tracking, evaluation_questions.xlsx | report_runner.py, evaluation_handler.py |
| 2026-05-11 | Report restart | Load questions from Excel, execute report pipeline | Eval Questions Barcalsy May 2026.xlsx |
| 2026-05-11 | Report execution | Load questions from Excel, run evaluation suite, progress tracking | Eval Questions Barclays May 2026.xlsx |
| 2026-05-11 | Evaluation restart | Load Excel questions, run evaluation suite, track progress | Eval Questions Barcalsy May 2026.xlsx, evaluation runner |
| 2026-05-11 | Evaluation execution | Load questions from Excel, run GPT-4o evaluation | python-pro/reports.py, Eval\ Questions\ Barcalsy\ May\ 2026.xlsx |
| 2026-05-11 | Report restart | Load questions from Excel, run GPT-4o evaluation | Eval Questions Barcalsy May 2026.xlsx |
| 2026-05-11 | Reports restart with Excel questions | Filter narrowed to key events, notification settings adjusted | monitoring config, event filters |
| 2026-05-11 | Report restart | Load questions from Excel, narrow event filter to key events | Eval Questions Barcalsy May 2026.xlsx, monitor config |
| 2026-05-11 | Report execution | Load questions from Excel, run Internal Banners assessment | Eval Questions Barcalsy May 2026.xlsx |
| 2026-05-11 | Report execution from Excel | Load questions, start monitoring, track progress | Eval Questions Barcalsy May 2026.xlsx |

View file

@ -65,3 +65,75 @@ tags: [daily]
- 16:49 | `Shumiland`
- **Asked:** Apply background color F1FBEB across all pages except hero and footer.
- **Done:** Deployed background color F1FBEB to production, pushed to git, and rebuilt application.
- 16:51 | `barclays-rag-report`
- **Asked:** Restart reports using questions from the Excel file with evaluation questions.
- **Done:** Restarted monitoring with a narrower filter to track only key events (config changes, result evaluations, and completion).
- 16:51 | `barclays-rag-report`
- **Asked:** Restart reports using questions from an Excel file.
- **Done:** Started evaluation process with GPT-4o using 60 questions from the Excel file.
- 16:51 | `barclays-rag-report`
- **Asked:** Run evaluation reports using questions from the Excel file.
- **Done:** Started evaluation process with GPT-4o on 60 questions from the Excel file.
- 16:52 | `barclays-rag-report`
- **Asked:** Asked | Run evaluation reports using questions from Excel file | Done | Launched evaluation process with questions from Eval Questions Barcalsy May 2026.xlsx (60 questions total) | Log | Report evaluation | Load Excel questions, start evaluation loop | Eval Questions Barcalsy May 2026.xlsx
- **Done:**
- 16:52 | `barclays-rag-report`
- **Asked:** Restart reports using questions from an Excel file (Eval Questions Barclays May 2026.xlsx)
- **Done:** Reports evaluation started and progressed to ~9/60 questions with Internal Banners section in progress
- 16:52 | `barclays-rag-report`
- **Asked:** Asked to restart reports using questions from an Excel file
- **Done:** Executed evaluation reports with questions from Eval Questions Barclays May 2026.xlsx, progressing through Internal Banners and Social Posts sections
- 16:52 | `barclays-rag-report`
- **Asked:** Asked | User requested to restart reports using questions from an Excel file
- **Done:** Done | Reports restarted with evaluation questions from the Excel file; processing progressed to ~13/60 questions
- 16:52 | `barclays-rag-report`
- **Asked:** Asked | Restart reports with evaluation questions from Excel file
- **Done:** Done | Reports running with questions from Eval Questions Barcalsy May 2026.xlsx, ~16/60 completed
- 16:52 | `barclays-rag-report`
- **Asked:** Asked | Restart evaluation reports using questions from Excel file | -
- **Done:** Done | Ran evaluation using questions from Eval Questions Barcalsy May 2026.xlsx, progressed from ~16/60 to ~18/60 | Eval Questions Barcalsy May 2026.xlsx
- 16:52 | `barclays-rag-report`
- **Asked:** Asked | Developer requested to restart reports using evaluation questions from an Excel file
- **Done:** Done | Reports were executed and evaluation progressed to approximately one-third completion (~20/60)
- 16:52 | `barclays-rag-report`
- **Asked:** Asked | Run evaluation reports using questions from Excel file |
- **Done:** Done | Started and progressed evaluation from 0 to 23/60 questions (38% complete) |
- 16:53 | `barclays-rag-report`
- **Asked:** Run evaluation using questions from the Excel file (Eval Questions Barclays May 2026.xlsx)
- **Done:** Executed evaluation with Python Pro skill and achieved ~25/60 questions passing (approximately 42% completion)
- 16:53 | `barclays-rag-report`
- **Asked:** Asked | Restart reports with questions from Excel file | User requested to run reports using evaluation questions from the provided Excel file
- **Done:** Done | Reports execution progressed to approximately 27 of 60 questions completed | Eval Questions Barcalsy May 2026.xlsx, report execution logs
- 16:53 | `barclays-rag-report`
- **Asked:** Asked | Restart reports using evaluation questions from Excel file | Eval Questions Barcalsy May 2026.xlsx
- **Done:** Done | Ran evaluation reports with provided questions; completed ~30/60 items (50% progress) | evaluation suite
- 16:53 | `barclays-rag-report`
- **Asked:** Asked | Restart evaluation reports using Excel questions list
- **Done:** Done | Resumed evaluation process with questions from Eval Questions Barcalsy May 2026.xlsx, reaching ~32/60 completion
- 16:53 | `barclays-rag-report`
- **Asked:** Asked | Done | Log
- **Done:** User requested to restart reports using evaluation questions from an Excel file | Ran reports with questions from Eval Questions Barclays May 2026.xlsx and achieved ~34/60 results | Report execution, Excel import | evaluation_runner.py, report_config.py
- 16:53 | `barclays-rag-report`
- **Asked:** Asked | Run reports using evaluation questions from Excel file |
- **Done:** Done | Executed reports with questions from Eval Questions Barcalsy May 2026.xlsx, achieving ~38/60 score on final third |
- 16:53 | `barclays-rag-report`
- **Asked:** Asked | Restart report generation with evaluation questions from Excel file | Run report using questions from Eval Questions Barcalsy May 2026.xlsx | Report generation | Load questions from Excel, execute report pipeline | report_runner.py, questions_loader.py
- **Done:**
- 16:53 | `barclays-rag-report`
- **Asked:** Asked | Done | Log
- **Done:** ---|---|---
- 16:53 | `barclays-rag-report`
- **Asked:** Asked | one short sentence about the request | Restart reports with evaluation questions from Excel file
- **Done:** Done | Reports were executed using questions from the provided Excel file | Reports restarted, evaluation questions loaded
- 16:54 | `barclays-rag-report`
- **Asked:** Asked | Restart reports with questions from Excel file | User requested re-running reports using questions from the Eval Questions Barcalsy May 2026.xlsx file
- **Done:** Done | Reports were re-executed and achieved approximately 46/60 score | Eval Questions Barcalsy May 2026.xlsx, report execution scripts
- 16:54 | `barclays-rag-report`
- **Asked:** Asked | Restart reports using evaluation questions from Excel file
- **Done:** Done | Reports re-executed with questions from Eval Questions Barclays May 2026.xlsx, achieving ~51/60 in final evaluation
- 16:54 | `barclays-rag-report`
- **Asked:** Asked | Done | Log
- **Done:** --- | --- | ---
- 16:54 | `barclays-rag-report`
- **Asked:** User requested to restart reports using questions from an Excel file | Ran reports with Eval Questions Barcalsy May 2026.xlsx achieving ~56/60 score | Eval Questions Barcalsy May 2026.xlsx
- **Done:** Report restart | Execute reports with Excel questions list | Eval Questions Barcalsy May 2026.xlsx