Concepts Fondamentaux
Semantic Search
Search that retrieves results based on meaning rather than exact keyword matching.
Semantic search converts both the query and documents into embeddings and retrieves items by vector similarity. Unlike keyword search, it understands synonyms, paraphrases, and conceptual relationships. In LLM applications, semantic search is the retrieval backbone of RAG pipelines and powers contextual lookup in document Q&A systems.
Termes Associés
Vektör Yerleştirme (Embedding)
Kelimelerin veya metinlerin anlamlarını temsil eden çok boyutlu sayısal vektörler.
Vector Database
A database optimized for storing and searching high-dimensional embedding vectors.
RAG (Geri Getirmeyle Güçlendirilmiş Üretim)
Modeli harici bir bilgi bankasından gelen gerçek zamanlı verilerle besleme tekniği.
Tokenizer
The algorithm that converts raw text into a sequence of tokens for a language model.