import openai
import pandas as pd
df = pd.read_csv('olympics-data/olympics_qa.csv')
olympics_search_fileid = "file-c3shd8wqF3vSCKaukW4Jr1TT"
df.head()

from sklearn.model_selection import train_test_split
train_df, test_df = train_test_split(df, test_size=0.2, random_state=42)
len(train_df), len(test_df)

df.context.str.contains('->').sum()

for name, is_disc in [('discriminator', True), ('qa', False)]:
    for train_test, dt in [('train', train_df), ('test', test_df)]:
        ft = create_fine_tuning_dataset(dt, discriminator=is_disc, n_negative=1, add_related=True)
        ft.to_json(f'{name}_{train_test}.jsonl', orient='records', lines=True)

!openai api fine_tunes.create -t "olympics-data/discriminator_train.jsonl" -v "olympics-data/discriminator_test.jsonl" --batch_size 16  --compute_classification_metrics --classification_positive_class " yes" --model ada

!openai api fine_tunes.create -t "olympics-data/qa_train.jsonl" -v "olympics-data/qa_test.jsonl" --batch_size 16

ft_discriminator = "curie:ft-openai-internal-2021-08-23-23-58-57"
ft_qa = "curie:ft-openai-internal-2021-08-23-17-54-10"

def apply_ft_discriminator(context, question, discriminator_model):
    """
    Apply the fine tuned discriminator to a question, to assess whether it can be answered from the context.
    """
    prompt = f"{context}\nQuestion: {question}\n Related:"
    result = openai.chat.completions.create(model=discriminator_model, prompt=prompt, max_tokens=1, temperature=0, top_p=1, n=1, logprobs=2)
    return result['choices'][0]['logprobs']['top_logprobs']

apply_ft_discriminator('The first human-made object in space was the Soviet Union satellite Sputnik 1 on 4 October 1957.', 
                        'What was the first human-made object in space?', ft_discriminator)

def apply_ft_qa_answer(context, question, answering_model):
    """
    Apply the fine tuned discriminator to a question
    """
    prompt = f"{context}\nQuestion: {question}\nAnswer:"
    result = openai.chat.completions.create(model=answering_model, prompt=prompt, max_tokens=30, temperature=0, top_p=1, n=1, stop=['.','\n'])
    return result['choices'][0]['text']

apply_ft_qa_answer('The first human-made object in space was the Soviet Union satellite Sputnik 1 on 4 October 1957.', 
                    'What was the first human-made object in space?', ft_qa)

apply_ft_qa_answer('The first human-made object in space was the Soviet Union satellite Sputnik 1 on 4 October 1957.',
                    'What is impressive about the Soviet Union?', ft_qa)

apply_ft_qa_answer('The first human-made object in space was the Soviet Union satellite Sputnik 1 on 4 October 1957.',
                    'How many cars were produced in the Soviet Union in 1970?', ft_qa)

def answer_question_conditionally(answering_model, discriminator_model, context, question, discriminator_logprob_yes_modifier=0):
    logprobs = apply_ft_discriminator(context, question, discriminator_model)
    yes_logprob = logprobs[' yes'] if ' yes' in logprobs else -100
    no_logprob = logprobs[' no'] if ' no' in logprobs else -100
    if yes_logprob + discriminator_logprob_yes_modifier < no_logprob:
        return " No appropriate context found to answer the question based on the discriminator."
    return apply_ft_qa_answer(context, question, answering_model)
answer_question_conditionally(ft_qa, ft_discriminator, 
                                "Crowdless games are a rare although not unheard-of occurrence in sports. \
                                 When they do occur, it is usually the result of events beyond the control \
                                 of the teams or fans, such as weather-related concerns, public health concerns, \
                                 or wider civil disturbances unrelated to the game. For instance, \
                                 the COVID-19 pandemic caused many sports leagues around the world \
                                 to be played behind closed doors.",
                                "Could weather cause a sport event to have no crowd?")

from answers_with_ft import answer_question
answer_question(olympics_search_fileid, ft_qa, "Which country won the Women's football tournament at the 2020 Olympic games?")