Spaces:
Runtime error
Runtime error
File size: 4,757 Bytes
63bcd5a 4552666 63bcd5a 4552666 63bcd5a 4552666 63bcd5a 4552666 63bcd5a 4552666 63bcd5a 4552666 63bcd5a 4552666 63bcd5a 4552666 63bcd5a 4552666 63bcd5a 4552666 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 | import logging
import re
from typing import List
from functools import lru_cache
from src.similarity_model import (
compare_two_ideas,
find_similar_projects
)
from src.recommendation_engine.config import (
IDEA_DUPLICATE_THRESHOLD,
FEATURE_DUPLICATE_THRESHOLD
)
logger = logging.getLogger(__name__)
GENERIC_PATTERNS = [
"dashboard",
"platform",
"system",
"application",
"website",
"ai module",
"analytics module",
"smart system",
"management system"
]
def normalize(text: str) -> str:
text = str(text).lower().strip()
text = re.sub(r"[^a-z0-9\s]", " ", text)
text = re.sub(r"\s+", " ", text).strip()
return text
def is_generic(text: str) -> bool:
low = normalize(text)
for pattern in GENERIC_PATTERNS:
if pattern in low:
return True
return False
def token_overlap_score(a: str, b: str) -> float:
a_tokens = set(normalize(a).split())
b_tokens = set(normalize(b).split())
if not a_tokens or not b_tokens:
return 0.0
overlap = len(a_tokens & b_tokens)
union = len(a_tokens | b_tokens)
return overlap / union
def is_feature_novel(
feature: str,
existing_features: List[str]
) -> bool:
feature = normalize(feature)
if not feature:
return False
if is_generic(feature):
logger.debug(f"[GENERIC FEATURE] {feature}")
return False
existing_norm = [
normalize(f)
for f in existing_features
]
if feature in existing_norm:
logger.debug(f"[EXACT DUP] {feature}")
return False
for old in existing_norm:
if not old:
continue
semantic_score = compare_two_ideas(
feature,
old
)
overlap_score = token_overlap_score(
feature,
old
)
final_score = max(
semantic_score,
overlap_score
)
logger.debug(
f"[COMPARE] {feature} ~ {old} "
f"(semantic={semantic_score:.2f}, "
f"overlap={overlap_score:.2f})"
)
if final_score >= (
FEATURE_DUPLICATE_THRESHOLD + 0.08
):
logger.debug(
f"[FEATURE DUPLICATE] "
f"{feature} ~ {old}"
)
return False
return True
def filter_duplicate_features(
generated_features: List[str],
existing_features: List[str]
) -> List[str]:
final = []
seen = set()
for feat in generated_features:
clean = str(feat).strip()
norm = normalize(clean)
if not clean:
continue
if norm in seen:
continue
if not is_feature_novel(
norm,
existing_features + final
):
continue
seen.add(norm)
final.append(clean)
return final
@lru_cache(maxsize=256)
def _cached_db_check(idea: str) -> float:
try:
results = find_similar_projects(
title=idea,
description=idea,
top_k=3
)
if (
hasattr(results, "iloc")
and len(results) > 0
):
scores = []
for _, row in results.iterrows():
score = float(
row.get("hybrid_score", 0)
)
scores.append(score)
if scores:
return max(scores)
except Exception as e:
logger.warning(f"[DB ERROR] {e}")
return 0.0
def is_idea_novel(idea_title: str) -> bool:
idea_title = normalize(idea_title)
if not idea_title:
return False
if is_generic(idea_title):
logger.info(
f"[GENERIC IDEA REJECTED] "
f"{idea_title}"
)
return False
score = _cached_db_check(idea_title)
logger.info(f"[DB CHECK] {idea_title}")
logger.info(f"[SIMILARITY SCORE] {score:.4f}")
return score < IDEA_DUPLICATE_THRESHOLD
def score_feature_novelty(
feature: str,
existing_features: List[str]
) -> float:
feature = normalize(feature)
if not existing_features:
return 1.0
scores = []
for old in existing_features:
old_norm = normalize(old)
semantic = compare_two_ideas(
feature,
old_norm
)
overlap = token_overlap_score(
feature,
old_norm
)
scores.append(
max(semantic, overlap)
)
if not scores:
return 1.0
return round(
1.0 - max(scores),
4
)
|