LLM-Model2 / scripts /run_pipeline.py
investmentllm's picture
Upload folder using huggingface_hub
e41fa0b verified
raw
history blame contribute delete
729 Bytes
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
from ingestion.sec_downloader import ingest_ticker
from ingestion.text_extractor import extract_all
from indexes.build_sec_index import build_index
import argparse
p = argparse.ArgumentParser()
p.add_argument("tickers", nargs="+")
p.add_argument("--forms", nargs="+", default=["10-K","10-Q"])
p.add_argument("--max", type=int, default=5)
args = p.parse_args()
for ticker in args.tickers:
print(f"\n{'#'*50}\nRunning pipeline for {ticker.upper()}\n{'#'*50}")
ingest_ticker(ticker, form_types=args.forms, max_filings=args.max)
extract_all(ticker)
build_index(ticker)
print(f"\n✓ {ticker.upper()} complete")