readctrl / code /validation /data_gen_subclaims_support_valid_ch_gpt5.py
shahidul034's picture
Add files using upload-large-folder tool
1db7196 verified
from openai import OpenAI
import json, os
with open("/home/mshahidul/readctrl/prompts/subclaim_result_generate_gpt5.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
with open("/home/mshahidul/readctrl/data/extracting_subclaim/extracted_subclaims_full_data.json", "r") as f:
data = json.load(f)
save_path="/home/mshahidul/readctrl/data/model_validity_check/subclaims_support_validity_check_gt_gpt5(1-5).json"
res=[]
if os.path.exists(save_path):
with open(save_path, "r") as f:
res = json.load(f)
import tqdm
for i in tqdm.tqdm(range(5)):
for label in ["easy", "intermediate", "hard"]:
new_prompt = prompt_template.replace("<<<DOCUMENT>>>",data[i]['fulltext']).replace("<<<SUBCLAIMS>>>", json.dumps(data[i][f'{label}_subclaims'], indent=2, ensure_ascii=False))
# import ipdb; ipdb.set_trace()
sample = openai_return(new_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)