code/translation/translation_using_gpt5.py

from openai import OpenAI
import json, os

source_language = "English"
target_language = "Hindi"
print(f"Translating from {source_language} to {target_language}")
with open("/home/mshahidul/readctrl/prompts/translation_prompt.txt", "r") as f:
    prompt_template = f.read()


api_file = "/home/mshahidul/api_new.json"
with open(api_file, "r") as f:
    api_keys = json.load(f)
openai_api_key = api_keys["openai"]

client = OpenAI(api_key=openai_api_key)


def openai_return(prompt, model="gpt-5"):
    """Send a prompt to GPT and parse JSON."""
    response = client.chat.completions.create(
        model=model,
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": prompt}
        ]
    )
    content = response.choices[0].message.content.strip()
    cleaned = content.replace("```json", "").replace("```", "").strip()
    try:
        return json.loads(cleaned)
    except json.JSONDecodeError:
        print("⚠️ JSON parse failed — storing raw text.")
        return cleaned

save_path=f"/home/mshahidul/readctrl/data/translated_data/translation_{source_language[:2].lower()}2{target_language[:2].lower()}_v1.json"
res=[]
if os.path.exists(save_path):
    with open(save_path, "r") as f:
        res = json.load(f)
import tqdm
with open("/home/mshahidul/readctrl/data/testing_data_gs/multiclinsum_gs_train_en.json", "r") as f:
    data = json.load(f)
for item in tqdm.tqdm(data[:15]):
    prompt=prompt_template.replace("<MEDICAL_TEXT>", item["fulltext"]).replace("<SOURCE_LANGUAGE>", source_language).replace("<TARGET_LANGUAGE>", target_language)
    # import ipdb; ipdb.set_trace()
    sample = openai_return(prompt, model="gpt-5")

    res.append(sample)

    if len(res) % 2 == 0:
        with open(save_path, "w") as f:
            json.dump(res, f, indent=2, ensure_ascii=False)
        print(f"Saved {len(res)} samples so far.")

with open(save_path, "w") as f:
    json.dump(res, f, indent=2, ensure_ascii=False)