Sentence-transformers
Sentence Transformers is a Python library for computing dense embeddings of text and other inputs and training embedding models using transformer-based architectures.
Domain-Specific Small Language Models
A library for producing dense text vectors with transformer encoders for embedding and similarity search.
- How it is used
- Builds dense text representations for semantic search, RAG retrieval, and similarity-based classification.
- How deep it goes
- Explains encoding, vector-space similarity, model selection, and retrieval integration, but defers detailed model architecture and training procedures.
- Examples
- Demonstrates document-chunk retrieval for RAG and superhero-text classification with a normalized FAISS index.
- What you can do after
- Apply it via Python APIs to encode text, compare query and document vectors, and feed retrieved passages into a RAG pipeline.
Read how Domain-Specific Small Language Models explains sentence-transformers →
AI-Powered Search
Sentence Transformers is a software library and collection of models for computing semantically meaningful vector representations of sentences and other text.
- How it is used
- Supports semantic search by representing sentences as dense vectors that can be compared and ranked by similarity.
- How deep it goes
- Explains pooling, training, embeddings, normalization, similarity calculation, and ranking, but defers detailed model architecture.
- Examples
- Uses weather and vehicle phrases, 768-dimensional embeddings, normalized vectors, pairwise scores, and a sorted similarity table.
- What you can do after
- Build it with Python by loading a pretrained model, encoding phrases, computing similarities, and ranking related text.
Related concepts
- embeddingproduces · A numerical vector representation of an item or input that encodes features or relationships useful for computational tasks.
- tokenizationuses · Tokenization is the process of dividing text or other sequential input into discrete units called tokens for computational processing.
- all-mpnet-base-v2uses · all-mpnet-base-v2 is a pretrained sentence-embedding model that maps sentences and short passages to 768-dimensional vector representations.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.