One search. Connected ideas.

An embedding is a list of numbers representing useful features of content, often its meaning. That list is a vector; its number of entries is its dimension. Semantic similarity means closeness in meaning, such as “car accident” and “vehicle collision,” even…

Quantization represents model values with fewer bits to reduce memory and sometimes improve speed. GGUF is a model file format used by compatible local inference runtimes; it is not itself a model or a guarantee of quantization level. Local embeddings run an…

Beginner — Explain an embedding.

An embedding model creates vectors; an embedding pipeline manages generation, versions, and storage. An embedding is a derived index representation, not a replacement for the original text. Different models, dimensions, or preprocessing choices can produce…

Atlas is MongoDB's managed database environment; MongoDB Vector Search indexes supported vector fields for similarity retrieval. Source metadata and application records can live alongside chunk documents. A vector/search index is distinct from ordinary…

Similarity measures how close two vectors are according to a selected metric. Cosine similarity compares their direction, effectively asking whether they point in a similar direction regardless of magnitude. Dot product and Euclidean distance are other common…

Reranking is a second ranking stage that examines a short candidate list more carefully. A reranker often reads the query and each candidate together, allowing richer comparison than separate embeddings. It changes candidate order; it cannot recover a…

RAG stands for retrieval-augmented generation. It retrieves relevant external information and provides that information to a model before asking for an answer. It connects language generation to a changing knowledge source without retraining the model.

AI and LLM fundamentals

A vector database stores vectors and supports similarity queries with metadata. Vector search is the numerical operation; semantic search is the application goal of finding meaningfully related content. Existing databases can also add vector indexes, so you…

Chunking divides documents into retrieval-sized pieces. Chunk size controls how much content each piece contains; overlap repeats a small amount at boundaries. Metadata identifies the piece's source, permissions, version, and other useful attributes.

Batch processing groups noninteractive tasks; bounded concurrency controls simultaneous requests; rate limits constrain traffic over time. Streaming exposes progress earlier. Fallback uses an approved alternative after eligible failures.

An embedding model creates vectors; an embedding pipeline manages generation, versions, and storage. An embedding is a derived index representation, not a replacement for the original text. Different models, dimensions, or preprocessing choices can produce…

An embedding is a list of numbers representing useful features of content, often its meaning. That list is a vector; its number of entries is its dimension. Semantic similarity means closeness in meaning, such as “car accident” and “vehicle collision,” even…

Quantization represents model values with fewer bits to reduce memory and sometimes improve speed. GGUF is a model file format used by compatible local inference runtimes; it is not itself a model or a guarantee of quantization level. Local embeddings run an…

Beginner — Explain an embedding.

Similarity measures how close two vectors are according to a selected metric. Cosine similarity compares their direction, effectively asking whether they point in a similar direction regardless of magnitude. Dot product and Euclidean distance are other common…

Atlas is MongoDB's managed database environment; MongoDB Vector Search indexes supported vector fields for similarity retrieval. Source metadata and application records can live alongside chunk documents. A vector/search index is distinct from ordinary…

I add exact identifier fields and lexical/hybrid retrieval. Embeddings may not preserve rare codes or precise numbers well. I test actual identifiers and keep them intact during query rewriting and text preprocessing.

Reranking is a second ranking stage that examines a short candidate list more carefully. A reranker often reads the query and each candidate together, allowing richer comparison than separate embeddings. It changes candidate order; it cannot recover a…

RAG stands for retrieval-augmented generation. It retrieves relevant external information and provides that information to a model before asking for an answer. It connects language generation to a changing knowledge source without retraining the model.

It is a numerical vector that represents useful features of content, often meaning. Similar wording or meaning tends to produce nearby vectors, enabling retrieval of “vehicle collision” for a query about “car accident.”

I version models and index data, re-embed the intended corpus into a separate compatible space, evaluate filtered retrieval, and switch query/index routing together. I preserve source data and support rollback instead of mixing arbitrary old and new vectors.

AI and LLM fundamentals

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module