Dom/t2a_v2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: mode hybride Ollama — gemma3:27b pour CPAM, 12b pour codage

Browse Source 
Le pipeline utilise désormais gemma3:12b (rapide) pour le codage CIM-10
et gemma3:27b (meilleur raisonnement) pour la contre-argumentation CPAM.
Configurable via OLLAMA_MODEL_CPAM et OLLAMA_TIMEOUT_CPAM.

Inclut aussi : traçabilité source/page DAS, niveaux CMA ATIH, sévérité,
page tracker PDF, améliorations fusion et filtres DAS.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
dom
2026-02-17 17:53:53 +01:00
parent 4ef42dd3d3
commit 01d47f3c4b
20 changed files with 1025 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/config.py
View File

@@ -36,7 +36,9 @@ NER_CONFIDENCE_THRESHOLD = float(os.environ.get("T2A_NER_THRESHOLD", "0.80"))
OLLAMA_URL = os.environ.get("OLLAMA_URL", "http://localhost:11434")
OLLAMA_MODEL = os.environ.get("OLLAMA_MODEL", "gemma3:12b")
OLLAMA_MODEL_CPAM = os.environ.get("OLLAMA_MODEL_CPAM", "gemma3:27b")
OLLAMA_TIMEOUT = int(os.environ.get("OLLAMA_TIMEOUT", "120"))
OLLAMA_TIMEOUT_CPAM = int(os.environ.get("OLLAMA_TIMEOUT_CPAM", "300"))
OLLAMA_CACHE_PATH = BASE_DIR / "data" / "ollama_cache.json"
OLLAMA_MAX_PARALLEL = int(os.environ.get("OLLAMA_MAX_PARALLEL", "2"))
@@ -55,6 +57,7 @@ UPLOAD_MAX_SIZE_MB = 50
ALLOWED_EXTENSIONS = {".pdf", ".csv", ".xlsx", ".xls", ".txt"}
CIM10_DICT_PATH = BASE_DIR / "data" / "cim10_dict.json"
CIM10_SUPPLEMENTS_PATH = BASE_DIR / "data" / "cim10_supplements.json"
CMA_LEVELS_PATH = BASE_DIR / "data" / "cma_levels.json"
CCAM_DICT_PATH = BASE_DIR / "data" / "ccam_dict.json"
CIM10_PDF = Path(os.environ.get("T2A_CIM10_PDF", "/home/dom/ai/aivanov_CIM/cim-10-fr_2026_a_usage_pmsi_version_provisoire_111225.pdf"))
GUIDE_METHODO_PDF = Path(os.environ.get("T2A_GUIDE_METHODO_PDF", "/home/dom/ai/aivanov_CIM/guide_methodo_mco_2026_version_provisoire.pdf"))
@@ -101,7 +104,10 @@ class Diagnostic(BaseModel):
est_cma: Optional[bool] = None
est_cms: Optional[bool] = None
niveau_severite: Optional[str] = None # "leger" | "modere" | "severe" | "non_evalue"
niveau_cma: Optional[int] = None # 1 (pas CMA) | 2 | 3 | 4 (niveau officiel ATIH)
source: Optional[str] = None # "trackare" | "edsnlp" | "regex" | "llm_das"
source_page: Optional[int] = None # numéro de page (1-indexed) dans le PDF source
source_excerpt: Optional[str] = None # extrait du texte source (~200 chars)
class ActeCCAM(BaseModel):