Noms plus clairs : snippets/, scripts de test numérotés, verifier_ollama.py

- base_connaissances/ → snippets/ (corpus/ → textes/, instructions.md → consignes_redaction.md, decoupage.py → fichiers.py, importer.py → envoyer.py) ; python3 -m snippets.envoyer.
- instance-de-test/ : 1_demarrer.sh, 2_creer_boite_et_cle.py, 3_brancher_ia.py, 4_essayer_brouillons.py, voir_empreintes.sh, connexion_admin.py.
- ollama/verifier.py → ollama/verifier_ollama.py ; tests, tâches VS Code et docs alignés.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
maximeandClaude Opus 5.5 committed 2026-11-12 10:27:06 +01:00
1 parent 3e0b5d03a3
commit 10ed887417
142 files changed
+89 -85

No files matched your search

@@ -0,0 +1,17 @@
# What is the error column in exported data?
The error column is a target recognition error, not a displacement uncertainty or accuracy
estimate.
It compares the current appearance of a target with the reference image recorded during
configuration.
The value typically increases when:
• The target is partially or completely obstructed.
• Vegetation, vehicles, people, animals or equipment pass in front of the target.
• The target becomes dirty, wet, covered, or damaged.
• Illumination changes significantly.
• The appearance of the target otherwise differs substantially from its reference image.
Measurements for which the recognition error exceeds the configured Error Threshold can be
rejected as invalid.
The default Error Threshold is 0.7 unless a different value has been configured.
Source : AIMsight FAQ, rév. 1.5