Zum Inhalt springen
KI-Atlas

Text-Embeddings und semantische Suche

Sätze in Vektoren wandeln und die semantisch nächsten holen

Sprache & WissenFortgeschritten #09
EingabeTextTabelle

Der vollständige Artikel liegt auf Englisch vor; Titel und Zusammenfassung sind lokalisiert.

WAS DIESE FÄHIGKEIT BEDEUTET

Encodes a piece of text into a fixed-length vector so that semantically similar texts sit close together, then retrieves related items by nearest-neighbour lookup. Output is a ranked result list (item ids and scores), not prose. Unlike question answering it only finds possibly relevant material; it does not compose the answer.

Wie sie technisch umgesetzt wird

The mainstream design is a two-tower model: queries and documents are compressed by encoders, and training pushes true pairs above random negatives, typically with contrastive learning and large batches. At query time all document vectors are pre-computed into an index and an approximate nearest-neighbour search returns the top-k in milliseconds. Sparse and dense representations are often mixed to combine keyword hits with semantic recall.

Repräsentative Produkte

6

Beteiligte Organisationen

Typische Verwendungen

  • Search over enterprise documents and code
  • The recall stage of RAG pipelines
  • Deduplication, clustering and topic discovery
  • Recommendation and similar-content entry points

Wie sie bewertet wird

Recall@k
Whether the top-k contain all relevant documents
nDCG
Discounted cumulative gain that accounts for rank position
MRR
Mean reciprocal rank of the first relevant result

Grenzen und schwierige Punkte

  • Semantic similarity is not relevance: near neighbours may merely share wording
  • Cross-domain or cross-lingual use degrades noticeably without adaptation
  • Chunking long documents severs context, and answers at chunk boundaries are easily missed

Konzepte dahinter