Files
siemens_ragas/webapp/services/text_utils.py

48 lines
1.6 KiB
Python
Raw Normal View History

"""Self-contained text helpers for the web layer.
These intentionally avoid importing from rag_eval so the web server has no
import-time dependency on the evaluation engine (and therefore boots even when
ragas is unavailable). The contexts parser mirrors rag_eval.shared.utils so the
console interprets serialized CSV context columns the same way the engine does.
"""
from __future__ import annotations
import ast
import json
import math
from typing import Any
def parse_contexts(value: Any) -> list[str]:
"""Normalize a context payload into a list of non-empty strings.
Accepts native lists, JSON/Python-literal serialized lists (as written into
scores.csv), and plain text, mirroring the engine's own parsing rules.
"""
if isinstance(value, list):
return [str(item).strip() for item in value if str(item).strip()]
if value is None or (isinstance(value, float) and math.isnan(value)):
return []
text = str(value).strip()
if not text:
return []
# Accept serialized lists from CSV exports before falling back to plain text.
for parser in (json.loads, ast.literal_eval):
try:
parsed = parser(text)
except (ValueError, SyntaxError, json.JSONDecodeError):
continue
if isinstance(parsed, list):
return [str(item).strip() for item in parsed if str(item).strip()]
# Preserve paragraph-style context dumps by splitting on blank lines first.
if "\n\n" in text:
chunks = [chunk.strip() for chunk in text.split("\n\n") if chunk.strip()]
if chunks:
return chunks
return [text]