Turning text, images, and audio into vectors — the substrate for search, RAG, and classification.
Sign in to track your progress across sections.
14 articles
Listed inEmbedding Models on Hugging FaceEmbeddingson
Benchmark scores across retrieval, clustering, and reranking tasks. Useful for a shortlist, dangerous as a final answer.
Listed inSentence TransformersEmbeddingson
The library most self-hosted embedding pipelines are built on: pooling, training, and inference.
Listed inOpenAI Embeddings APIEmbeddingson
Shortening a vector is supported and cheap, and slicing it yourself without normalizing degrades search with nothing failing.
Listed inAnomaly DetectionEmbeddingson
An anomaly score is a distance read backwards. Plus the unnormalized-vector bug that makes a detector flag your longest documents.
Listed inEmbedding Models on Hugging FaceEmbeddingson
Changing embedding models means re-embedding the whole corpus, so the choice is harder to reverse than a generation model. What to check on a model card: vector dimensions, maximum sequence length, licensing, and whether the model expects a prompt prefix that fails silently when omitted.
Listed inRecommendation SystemsEmbeddingson
Nearest neighbours of an item are a recommender you already have. It measures whether two things are about the same subject, which is not the same as predicting what a person will engage with.
Listed inJina EmbeddingsEmbeddingson
A 32,768-token context means the encoder stops dictating your chunk size. Task types move the query-versus-passage distinction into a parameter a reviewer can see, and truncatable vectors have one way to cut them safely.
Listed inWhat are Embeddings?Embeddingson
Dense vectors that put semantically similar things near each other.
Listed inCohere EmbedEmbeddingson
Multilingual embeddings plus a reranker that often beats a bigger index.
Listed inEmbedding ModelsEmbeddingson
Dimensions, context limits, and why you can never mix models in one index.
Listed inData ClassificationEmbeddingson
Labelling at scale by embedding once and comparing against class centroids.
Listed inSentence TransformersEmbeddingson
The open library behind most self-hosted embedding pipelines.
Listed inSemantic SearchEmbeddingson
Retrieving by meaning instead of keywords, and where it still loses to BM25.
Listed inGemini EmbeddingEmbeddingson
Google's embedding models and the task-type hints that tune them.