marek/MtoRagSystem
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

patch 15

Browse Source
This commit is contained in:
team 1
2026-05-01 17:40:48 +02:00
parent 17cb098235
commit ad7cac72be
19 changed files with 1084 additions and 157 deletions
Download Patch File Download Diff File Expand all files Collapse all files

134
src/Knowledge/Retrieval/NdjsonHybridRetriever.php
View File

@@ -474,25 +474,7 @@ final readonly class NdjsonHybridRetriever implements RetrieverInterface
return false;
}
$patterns = [
'/\balle\b/u',
'/\bliste\b/u',
'/\bauflistung\b/u',
'/\buebersicht\b/u',
'/\bübersicht\b/u',
'/\bsortiment\b/u',
'/\bwelche\b.*\b(gibt|verfügbar|verfuegbar|existieren)\b/u',
'/\bzeige\b.*\b(produkte|geraete|geräte|modelle|artikel)\b/u',
'/\bwas\b.*\b(gibt es|verfügbar|verfuegbar)\b/u',
];
foreach ($patterns as $pattern) {
if (preg_match($pattern, $normalized) === 1) {
return true;
}
}
return false;
return $this->matchesAnyPattern($normalized, $this->retrieverConfig->catalogListShortcutPatterns());
}
/**
@@ -872,21 +854,14 @@ final readonly class NdjsonHybridRetriever implements RetrieverInterface
}
}
if (str_starts_with($token, 'indikator')) {
$variants[] = 'indikator';
$variants[] = 'indikatortyp';
}
foreach ($this->retrieverConfig->exactSelectionTokenVariantPrefixes() as $prefix => $configuredVariants) {
if (!str_starts_with($token, $prefix)) {
continue;
}
if (str_starts_with($token, 'grenzwert')) {
$variants[] = 'grenzwert';
}
if (str_starts_with($token, 'messbereich')) {
$variants[] = 'messbereich';
}
if (str_starts_with($token, 'testomat')) {
$variants[] = 'testomat';
foreach ($configuredVariants as $variant) {
$variants[] = $variant;
}
}
return array_values(array_unique($variants));
@@ -903,12 +878,13 @@ final readonly class NdjsonHybridRetriever implements RetrieverInterface
true
);
$asksIndicator = isset($tokens['indikator'])
|| isset($tokens['indikatortyp'])
|| isset($tokens['reagenz'])
|| isset($tokens['reagens'])
|| str_contains($normalized, 'mit welchem')
|| str_contains($normalized, 'womit');
$asksIndicator = $this->containsAnyConfiguredToken(
$tokens,
$this->retrieverConfig->exactSelectionIndicatorQuestionTokens()
) || $this->containsAnyConfiguredPhrase(
$normalized,
$this->retrieverConfig->exactSelectionIndicatorQuestionPhrases()
);
return [
'asks_indicator' => $asksIndicator,
@@ -931,24 +907,26 @@ final readonly class NdjsonHybridRetriever implements RetrieverInterface
return $score;
}
if (preg_match('/verf(?:ü|ue)gbare\s+indikatortypen|indikatortypen|indikatorvarianten/iu', $rawText) === 1) {
if ($this->matchesAnyPattern($rawText, $this->retrieverConfig->exactSelectionIndicatorTableHeadingPatterns())) {
$score += 14.0;
}
if (preg_match('/\|\s*(?:typ|indikator)\s*\|\s*(?:grenzwert|messbereich|bereich)/iu', $rawText) === 1) {
if ($this->matchesAnyPattern($rawText, $this->retrieverConfig->exactSelectionIndicatorTableHeaderPatterns())) {
$score += 10.0;
}
if (preg_match('/\|\s*[A-Z]{0,4}\s*\d{2,4}\s*[A-Z]?\s*\|\s*\d/iu', $rawText) === 1) {
if ($this->matchesAnyPattern($rawText, $this->retrieverConfig->exactSelectionIndicatorTableRowPatterns())) {
$score += 8.0;
}
if (
str_contains($normalizedHaystack, 'indikator')
&& (
str_contains($normalizedHaystack, 'grenzwert')
|| str_contains($normalizedHaystack, 'messbereich')
|| str_contains($normalizedHaystack, 'bereich')
$this->containsAnyConfiguredPhrase(
$normalizedHaystack,
$this->retrieverConfig->exactSelectionIndicatorTableRequiredPrimaryTerms()
)
&& $this->containsAnyConfiguredPhrase(
$normalizedHaystack,
$this->retrieverConfig->exactSelectionIndicatorTableRequiredContextTerms()
)
) {
$score += 5.0;
@@ -959,27 +937,55 @@ final readonly class NdjsonHybridRetriever implements RetrieverInterface
private function isExactDetailToken(string $token): bool
{
return in_array($token, [
'indikator', 'indikatoren', 'indikatortyp', 'indikatortypen', 'reagenz', 'reagens', 'grenzwert',
'messbereich', 'bereich', 'wasserhaerte', 'wasserhärte',
'resthaerte', 'resthärte', 'haerte', 'härte', 'aufloesung',
'auflösung', 'schnittstelle', 'relais', 'fehlercode', 'code',
'wert', 'werte',
], true);
return in_array($token, $this->retrieverConfig->exactDetailTokens(), true);
}
private function isGenericExactSelectionToken(string $token): bool
{
return in_array($token, [
'vorherige', 'vorheriger', 'nutzerfrage', 'aktuelle',
'folgefrage', 'frage', 'antwort', 'technische', 'referenzanker',
'referenzaufloesung', 'referenzauflösung', 'faktenquelle', 'keine',
'welche', 'welcher', 'welches',
'welchem', 'welchen', 'wird', 'werden', 'wurde', 'kann', 'koennen',
'können', 'mit', 'der', 'die', 'das', 'den', 'dem', 'ein', 'eine',
'einer', 'eines', 'ist', 'sind', 'was', 'wie', 'wo', 'zum', 'zur',
'fuer', 'für', 'durch', 'von', 'vom', 'und', 'oder', 'auch',
], true);
return in_array($token, $this->retrieverConfig->genericExactSelectionTokens(), true);
}
/**
* @param string[] $patterns
*/
private function matchesAnyPattern(string $value, array $patterns): bool
{
foreach ($patterns as $pattern) {
if (preg_match($pattern, $value) === 1) {
return true;
}
}
return false;
}
/**
* @param array<string, bool> $tokens
* @param string[] $needles
*/
private function containsAnyConfiguredToken(array $tokens, array $needles): bool
{
foreach ($needles as $needle) {
if (isset($tokens[$needle])) {
return true;
}
}
return false;
}
/**
* @param string[] $phrases
*/
private function containsAnyConfiguredPhrase(string $haystack, array $phrases): bool
{
foreach ($phrases as $phrase) {
if ($phrase !== '' && str_contains($haystack, $phrase)) {
return true;
}
}
return false;
}
/**