MEVZU N° TAG / VOL. 131
#rag
0 blog · 0 news · 16 wiki
Wiki
Grounding
The practice of anchoring an LLM's answer to a verified external source.
- EN
- Grounding
- TR
- Topraklama (Grounding)
RAG — Retrieval-Augmented Generation
A pattern where an LLM retrieves relevant passages from external sources and includes them in context before generating an answer.
- EN
- Retrieval-Augmented Generation (RAG)
- TR
- RAG — Geri Çağırma Destekli Üretim
Semantic Chunking
A smarter chunking method that uses embedding similarity to split documents at topic boundaries.
- EN
- Semantic Chunking
- TR
- Anlamsal Parçalama
Qdrant
A high-performance open-source vector database written in Rust.
- EN
- Qdrant
- TR
- Qdrant
GraphRAG
A RAG variant that extracts a knowledge graph from documents to capture the bigger picture.
- EN
- GraphRAG
- TR
- GraphRAG
Pinecone
A fully managed, scalable vector-database SaaS.
- EN
- Pinecone
- TR
- Pinecone
Recursive Splitter
A practical chunking strategy that splits documents on coarse separators first, then progressively finer ones.
- EN
- Recursive Splitter
- TR
- Özyinelemeli Bölücü
Vector Database
A specialized database that stores high-dimensional vectors and performs similarity search over them.
- EN
- Vector Database
- TR
- Vektör Veritabanı
Citation in RAG
A reference that ties information in an LLM's answer back to its source document.
- EN
- Citation (in RAG)
- TR
- Kaynak Gösterme (RAG'da)
Weaviate
An open-source vector database with built-in hybrid search and modular vectorizers.
- EN
- Weaviate
- TR
- Weaviate
pgvector
An open-source PostgreSQL extension that adds vector data types and similarity search.
- EN
- pgvector
- TR
- pgvector
Reranking
A second stage that re-orders first-stage retrieval results with a stronger model.
- EN
- Reranking
- TR
- Yeniden Sıralama
Agentic RAG
A RAG architecture in which an agent decides retrieval steps instead of a fixed pipeline.
- EN
- Agentic RAG
- TR
- Ajan Davranışlı RAG
Hybrid Search
An approach that combines keyword and semantic search to improve retrieval quality.
- EN
- Hybrid Search
- TR
- Hibrit Arama
Chunking
The process of splitting documents into meaningful, bounded-size pieces for RAG.
- EN
- Chunking
- TR
- Parçalama (Chunking)
Chroma
A developer-friendly, low-friction open-source vector database.
- EN
- Chroma
- TR
- Chroma