09a251185e
Le 27b-cloud via Ollama Cloud est plus rapide (2m25 vs 4m) et produit des résultats nettement supérieurs au 12b local : - CPAM : plus de confusion Z45.80/Z43.6, preuves non hallucinées - Contre-argumentation : 5334 chars vs 4394, citations du dossier - Fallback local possible via OLLAMA_MODEL=gemma3:12b Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
202 lines
6.8 KiB
Python
202 lines
6.8 KiB
Python
"""Configuration globale et modèles de données pour le pipeline T2A."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from pathlib import Path
|
|
from typing import Optional
|
|
|
|
from dotenv import load_dotenv
|
|
from pydantic import BaseModel, Field
|
|
|
|
load_dotenv()
|
|
|
|
|
|
# --- Chemins ---
|
|
|
|
BASE_DIR = Path(__file__).resolve().parent.parent
|
|
INPUT_DIR = BASE_DIR / "input"
|
|
OUTPUT_DIR = BASE_DIR / "output"
|
|
ANONYMIZED_DIR = OUTPUT_DIR / "anonymized"
|
|
STRUCTURED_DIR = OUTPUT_DIR / "structured"
|
|
REPORTS_DIR = OUTPUT_DIR / "reports"
|
|
|
|
for d in (INPUT_DIR, ANONYMIZED_DIR, STRUCTURED_DIR, REPORTS_DIR):
|
|
d.mkdir(parents=True, exist_ok=True)
|
|
|
|
|
|
# --- Configuration anonymisation ---
|
|
|
|
KEEP_ESTABLISHMENT_NAME = os.environ.get("T2A_KEEP_ESTABLISHMENT", "True").lower() in ("true", "1", "yes")
|
|
NER_MODEL = os.environ.get("T2A_NER_MODEL", "Jean-Baptiste/camembert-ner")
|
|
NER_CONFIDENCE_THRESHOLD = float(os.environ.get("T2A_NER_THRESHOLD", "0.80"))
|
|
|
|
|
|
# --- Configuration Ollama ---
|
|
|
|
OLLAMA_URL = os.environ.get("OLLAMA_URL", "http://localhost:11434")
|
|
OLLAMA_MODEL = os.environ.get("OLLAMA_MODEL", "gemma3:27b-cloud")
|
|
OLLAMA_TIMEOUT = int(os.environ.get("OLLAMA_TIMEOUT", "120"))
|
|
OLLAMA_CACHE_PATH = BASE_DIR / "data" / "ollama_cache.json"
|
|
OLLAMA_MAX_PARALLEL = int(os.environ.get("OLLAMA_MAX_PARALLEL", "2"))
|
|
|
|
|
|
# --- Configuration RUM / établissement ---
|
|
|
|
FINESS = os.environ.get("T2A_FINESS", "000000000")
|
|
NUM_UM = os.environ.get("T2A_NUM_UM", "0000")
|
|
|
|
|
|
# --- Configuration RAG ---
|
|
|
|
RAG_INDEX_DIR = BASE_DIR / "data" / "rag_index"
|
|
REFERENTIELS_DIR = BASE_DIR / "data" / "referentiels"
|
|
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"))
|
|
CCAM_PDF = Path(os.environ.get("T2A_CCAM_PDF", "/home/dom/ai/aivanov_CIM/actualisation_ccam_descriptive_a_usage_pmsi_v4_2025.pdf"))
|
|
|
|
# --- Modèle d'embedding ---
|
|
|
|
EMBEDDING_MODEL = os.environ.get("T2A_EMBEDDING_MODEL", "dangvantuan/sentence-camembert-large")
|
|
|
|
# --- Modèle de re-ranking (cross-encoder, CPU uniquement) ---
|
|
|
|
RERANKER_MODEL = os.environ.get("T2A_RERANKER_MODEL", "cross-encoder/ms-marco-MiniLM-L-6-v2")
|
|
|
|
# --- Modèles de données CIM-10 ---
|
|
|
|
|
|
class RAGSource(BaseModel):
|
|
document: str
|
|
page: Optional[int] = None
|
|
code: Optional[str] = None
|
|
extrait: Optional[str] = None
|
|
|
|
|
|
class Sejour(BaseModel):
|
|
sexe: Optional[str] = None
|
|
age: Optional[int] = None
|
|
date_entree: Optional[str] = None
|
|
date_sortie: Optional[str] = None
|
|
duree_sejour: Optional[int] = None
|
|
mode_entree: Optional[str] = None
|
|
mode_sortie: Optional[str] = None
|
|
imc: Optional[float] = None
|
|
poids: Optional[float] = None
|
|
taille: Optional[float] = None
|
|
|
|
|
|
class PreuveClinique(BaseModel):
|
|
type: str # "biologie" | "imagerie" | "traitement" | "acte" | "clinique"
|
|
element: str # "CRP 180 mg/L"
|
|
interpretation: str # "syndrome inflammatoire majeur"
|
|
|
|
|
|
class Diagnostic(BaseModel):
|
|
texte: str
|
|
cim10_suggestion: Optional[str] = None
|
|
cim10_confidence: Optional[str] = None
|
|
justification: Optional[str] = None
|
|
raisonnement: Optional[str] = None
|
|
sources_rag: list[RAGSource] = Field(default_factory=list)
|
|
preuves_cliniques: list[PreuveClinique] = Field(default_factory=list)
|
|
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):
|
|
texte: str
|
|
code_ccam_suggestion: Optional[str] = None
|
|
ccam_confidence: Optional[str] = None
|
|
justification: Optional[str] = None
|
|
raisonnement: Optional[str] = None
|
|
sources_rag: list[RAGSource] = Field(default_factory=list)
|
|
date: Optional[str] = None
|
|
validite: Optional[str] = None # "valide" | "obsolete" | "non_verifie"
|
|
alertes: list[str] = Field(default_factory=list)
|
|
|
|
|
|
class Traitement(BaseModel):
|
|
medicament: str
|
|
posologie: Optional[str] = None
|
|
code_atc: Optional[str] = None
|
|
|
|
|
|
class BiologieCle(BaseModel):
|
|
test: str
|
|
valeur: Optional[str] = None
|
|
anomalie: Optional[bool] = None
|
|
|
|
|
|
class Imagerie(BaseModel):
|
|
type: str
|
|
conclusion: Optional[str] = None
|
|
score: Optional[str] = None
|
|
|
|
|
|
class DossierMedical(BaseModel):
|
|
source_file: str = ""
|
|
document_type: str = ""
|
|
sejour: Sejour = Field(default_factory=Sejour)
|
|
diagnostic_principal: Optional[Diagnostic] = None
|
|
diagnostics_associes: list[Diagnostic] = Field(default_factory=list)
|
|
actes_ccam: list[ActeCCAM] = Field(default_factory=list)
|
|
antecedents: list[str] = Field(default_factory=list)
|
|
traitements_sortie: list[Traitement] = Field(default_factory=list)
|
|
biologie_cle: list[BiologieCle] = Field(default_factory=list)
|
|
imagerie: list[Imagerie] = Field(default_factory=list)
|
|
complications: list[str] = Field(default_factory=list)
|
|
alertes_codage: list[str] = Field(default_factory=list)
|
|
source_files: list[str] = Field(default_factory=list)
|
|
ghm_estimation: Optional[GHMEstimation] = None
|
|
controles_cpam: list[ControleCPAM] = Field(default_factory=list)
|
|
processing_time_s: float | None = None
|
|
|
|
|
|
# --- Rapport d'anonymisation ---
|
|
|
|
|
|
class GHMEstimation(BaseModel):
|
|
cmd: Optional[str] = None
|
|
cmd_libelle: Optional[str] = None
|
|
type_ghm: Optional[str] = None # "C" / "M" / "K"
|
|
severite: int = 1 # 1-4
|
|
ghm_approx: Optional[str] = None # ex: "07C??2"
|
|
cma_count: int = 0
|
|
cms_count: int = 0
|
|
alertes: list[str] = Field(default_factory=list)
|
|
|
|
|
|
class ControleCPAM(BaseModel):
|
|
numero_ogc: int
|
|
titre: str = ""
|
|
arg_ucr: str = ""
|
|
decision_ucr: str = ""
|
|
dp_ucr: Optional[str] = None
|
|
da_ucr: Optional[str] = None
|
|
dr_ucr: Optional[str] = None
|
|
actes_ucr: Optional[str] = None
|
|
contre_argumentation: Optional[str] = None
|
|
response_data: Optional[dict] = None
|
|
sources_reponse: list[RAGSource] = Field(default_factory=list)
|
|
|
|
|
|
class AnonymizationReport(BaseModel):
|
|
source_file: str
|
|
total_replacements: int = 0
|
|
regex_replacements: int = 0
|
|
ner_replacements: int = 0
|
|
sweep_replacements: int = 0
|
|
entities_found: list[dict] = Field(default_factory=list)
|