193 lines
4.0 KiB
Python
193 lines
4.0 KiB
Python
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
from rich import print
|
|
|
|
|
|
PROJECT_ROOT = Path(__file__).resolve().parents[2]
|
|
|
|
if str(PROJECT_ROOT) not in sys.path:
|
|
sys.path.insert(0, str(PROJECT_ROOT))
|
|
|
|
|
|
from tools.rag.common import DB_FILE
|
|
from tools.rag.search_utils import search_database
|
|
from tools.retrieval.retrieval_contract import error_result
|
|
|
|
|
|
def print_results(
|
|
query: str,
|
|
response: dict,
|
|
) -> None:
|
|
results = response["results"]
|
|
|
|
print(
|
|
f"[bold]Dopyt:[/bold] "
|
|
f"{query}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Vyhľadávač:[/bold] "
|
|
f"{response['engine']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Stratégie:[/bold] "
|
|
f"{', '.join(response['strategies']) or 'žiadna'}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Počet výsledkov:[/bold] "
|
|
f"{len(results)}"
|
|
)
|
|
|
|
print(
|
|
"\n[bold]Top výsledky:[/bold]\n"
|
|
)
|
|
|
|
for rank, item in enumerate(
|
|
results,
|
|
start=1,
|
|
):
|
|
print(
|
|
f"[cyan]{rank}. "
|
|
f"Skóre: {item['score']} "
|
|
f"(BM25: {item['bm25_score']})"
|
|
f"[/cyan]"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Názov:[/bold] "
|
|
f"{item['title']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Cesta:[/bold] "
|
|
f"{item['document_path']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]URL:[/bold] "
|
|
f"{item['source_url']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Chunk:[/bold] "
|
|
f"{item['chunk_index']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Zhoda:[/bold] "
|
|
f"{item['match_strategy']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Kategórie:[/bold] "
|
|
f"{item['categories']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Tagy:[/bold] "
|
|
f"{item['tags']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Autor:[/bold] "
|
|
f"{item['author']}"
|
|
)
|
|
|
|
print(
|
|
f"[bold]Ukážka:[/bold] "
|
|
f"{item['snippet']}"
|
|
)
|
|
|
|
print("[bold]Text:[/bold]")
|
|
|
|
print(
|
|
(item["text"] or "")[:700]
|
|
)
|
|
|
|
print("-" * 80)
|
|
|
|
|
|
def main() -> None:
|
|
parser = argparse.ArgumentParser(
|
|
description=(
|
|
"FTS5 vyhľadávanie "
|
|
"v SQLite indexe zpwiki."
|
|
)
|
|
)
|
|
|
|
parser.add_argument(
|
|
"query",
|
|
nargs="+",
|
|
help="Text, ktorý sa má vyhľadať.",
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--limit",
|
|
type=int,
|
|
default=10,
|
|
help="Počet výsledkov.",
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--published-only",
|
|
action="store_true",
|
|
default=True,
|
|
help=(
|
|
"Vylúči explicitné published=false (predvolené)."
|
|
),
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--max-per-document",
|
|
type=int,
|
|
default=3,
|
|
help=(
|
|
"Maximálny počet chunkov "
|
|
"z jedného dokumentu. "
|
|
"Hodnota 0 vypne limit."
|
|
),
|
|
)
|
|
|
|
parser.add_argument("--include-unpublished", action="store_false", dest="published_only",
|
|
help="Výslovne zahrnie aj nepublikované dokumenty.")
|
|
parser.add_argument('--json', action='store_true', help='Strojový výstup so spoločným kontraktom.')
|
|
args = parser.parse_args()
|
|
query = " ".join(args.query)
|
|
|
|
try:
|
|
response = search_database(
|
|
DB_FILE,
|
|
query,
|
|
args.limit,
|
|
published_only=args.published_only,
|
|
max_per_document=args.max_per_document,
|
|
)
|
|
|
|
except Exception as error:
|
|
if args.json:
|
|
sys.stdout.write(json.dumps(error_result(error), ensure_ascii=False, indent=2)+'\n')
|
|
raise SystemExit(1) from error
|
|
raise SystemExit(
|
|
str(error)
|
|
) from error
|
|
|
|
if args.json:
|
|
sys.stdout.write(json.dumps(response, ensure_ascii=False, indent=2)+'\n')
|
|
return
|
|
|
|
print_results(
|
|
query,
|
|
response,
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|