Files
EDSS-calc/total_app.py

119 lines
4.0 KiB
Python

# %% API call1
import time
import json
import os
from datetime import datetime
import pandas as pd
from openai import OpenAI
from dotenv import load_dotenv
# Load environment variables
load_dotenv()
# === CONFIGURATION ===
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
OPENAI_BASE_URL = os.getenv("OPENAI_BASE_URL")
MODEL_NAME = "GPT-OSS-120B"
INPUT_CSV = "/home/shahin/Lab/Doktorarbeit/Barcelona/Data/MS_Briefe_400_with_unique_id_SHA3_explore_cleaned_unique.csv"
EDSS_INSTRUCTIONS_PATH = "/home/shahin/Lab/Doktorarbeit/Barcelona/attach/Komplett.txt"
client = OpenAI(
api_key=OPENAI_API_KEY,
base_url=OPENAI_BASE_URL
)
with open(EDSS_INSTRUCTIONS_PATH, 'r') as f:
EDSS_INSTRUCTIONS = f.read().strip()
# === UPDATED RUN INFERENCE WITH RETRY LOGIC ===
def run_inference(patient_text, max_retries=3):
prompt = f'''Du bist ein medizinischer Assistent... (rest of your prompt)''' # Kept same as your original
# Instructions omitted for brevity, but keep your full prompt here
attempts = 0
while attempts < max_retries:
start_time = time.time()
attempts += 1
try:
response = client.chat.completions.create(
messages=[
{"role": "system", "content": "You extract EDSS scores..."},
{"role": "user", "content": prompt}
],
model=MODEL_NAME,
max_tokens=2048,
temperature=0.0,
response_format={"type": "json_object"}
)
content = response.choices[0].message.content
# Check if content is empty or None
if not content or content.strip() == "" or content.strip() == "{}":
print(f" [Attempt {attempts}] Warning: Received empty response. Retrying...")
time.sleep(1) # Short pause before retrying
continue
# Parse the JSON response
parsed = json.loads(content)
inference_time = time.time() - start_time
return {
"success": True,
"result": parsed,
"inference_time_sec": inference_time,
"attempts": attempts
}
except Exception as e:
print(f" [Attempt {attempts}] Error: {e}")
if attempts < max_retries:
time.sleep(2) # Wait longer on actual connection errors
else:
return {
"success": False,
"error": f"Failed after {max_retries} attempts: {str(e)}",
"inference_time_sec": -1,
"attempts": attempts
}
return {"success": False, "error": "Unknown failure", "attempts": attempts}
# === BUILD PATIENT TEXT ===
def build_patient_text(row):
summary = str(row.get("T_Zusammenfassung", "")) if pd.notna(row.get("T_Zusammenfassung")) else ""
diagnoses = str(row.get("Diagnosen", "")) if pd.notna(row.get("Diagnosen")) else ""
clinical = str(row.get("T_KlinBef", "")) if pd.notna(row.get("T_KlinBef")) else ""
findings = str(row.get("T_Befunde", "")) if pd.notna(row.get("T_Befunde")) else ""
return "\n".join([summary, diagnoses, clinical, findings]).strip()
if __name__ == "__main__":
df = pd.read_csv(INPUT_CSV, sep=';')
results = []
for idx, row in df.iterrows():
print(f"Processing row {idx + 1}/{len(df)}")
patient_text = build_patient_text(row)
# Calling the updated inference function
result = run_inference(patient_text, max_retries=3)
result["unique_id"] = row.get("unique_id", f"row_{idx}")
result["MedDatum"] = row.get("MedDatum", None)
results.append(result)
# Optional: only print success to keep console clean
if result["success"]:
print(f" Success on attempt {result.get('attempts')}")
output_json = INPUT_CSV.replace(".csv", "_results_total.json")
with open(output_json, 'w', encoding='utf-8') as f:
json.dump(results, f, indent=2, ensure_ascii=False)
print(f"Results saved to {output_json}")