import pandas as pd
from tqdm import tqdm
from turftopic.analyzers import OpenAIAnalyzer, LLMAnalyzer

# Loading the data
data = pd.read_parquet("data/ecb_data.parquet")
content = list(data["content"])

# We write a prompt that will extract the relevant information
# We ask the model to separate information to key points so that 
# they become easier to model

summary_prompt="Summarize the following press conference from 
the European Central Bank into a set of key points separated by 
two newline characters. Reply with the summary only, nothing else. 
\n {document}"

# Formalize a summarized
summarizer = OpenAIAnalyzer("gpt-5-nano", summary_prompt=summary_prompt)
summaries = []

# Summarize dataframe, track code execution 
for document in tqdm(data["content"], desc="Summarising documents..."):
    summary = summarizer.summarize_document(document)
    # We print summaries as we go as a sanity check, to make sure 
    # the prompt works
    print(summary)
    summaries.append(summary)

# Collect summaries into a dataframe
summary_df = pd.DataFrame(
    {
        "id": data["id"],
        "date": data["date"],
        "author": data["author"],
        "title": data["title"],
        "summary": summaries,
    }
)