# Embeddings > An embedding is a list of numbers an embedding model gives a piece of text, so texts with related meaning get lists that sit close together. Find text that means the same thing, even in different words, and know when a close score still isn't the answer. Track: Foundations Card: https://buildsparkai.com/embeddings Plain text: https://buildsparkai.com/embeddings.md Last checked: 2026-10-25 ## What it is OpenAI's embeddings guide says an embedding is a list of floating point numbers, and that the distance between two lists measures relatedness: small distances mean related, large ones mean not. You don't read the numbers. You compare them. The usual score is cosine similarity: near 1 means the two lists point the same way. Sentence Transformers lets you choose the similarity function, such as cosine or dot product. Use the one your model's docs name. The same idea powers search, grouping similar texts, and classification, which OpenAI's guide lists. Searching your documents is its own card: Embeddings for retrieval . ## Why it matters **Cost.** [OpenAI's guide](https://developers.openai.com/api/docs/guides/embeddings) says embedding requests are billed by input tokens. You pay once to embed what you store, and again for each new text you compare. This card does not copy a rate. **Quality.** Settings must match. [Cohere](https://docs.cohere.com/docs/embeddings) and [Voyage AI](https://docs.voyageai.com/docs/embeddings) ask you to mark text as a query or a document for search. [Gemini's guide](https://ai.google.dev/gemini-api/docs/embeddings) sets a task type or a task instruction, depending on the model. Gemini also lets you pick a smaller size with output_dimensionality , which saves storage for a small loss in quality. **Risk.** [Gemini's guide](https://ai.google.dev/gemini-api/docs/embeddings) says the spaces of gemini-embedding-001 and gemini-embedding-2 are incompatible. You can't compare across them, and an upgrade means re-embedding all your data. A score from mismatched models looks normal and means nothing. ## Try today Take one question and three sentences from your own docs. Embed all four with the same model and settings. Rank the sentences by cosine score. Is the top one the sentence you'd pick by reading? If not, note which setting differs before you change anything else. ## Common mistake Comparing a new model's embeddings with ones you stored from an older model. The scores still come out as numbers. Re-embed what you stored first. ## Self-check Two texts score 0.98 cosine similarity. What does that tell you? Their meanings are closely related ## Understand it: what has to match before a score means anything 5 min, optional A high cosine says the lists point the same way. It does not say the text is the answer. ### Cosine, dot product, and distance [Sentence Transformers](https://sbert.net/docs/sentence_transformer/usage/semantic_textual_similarity.html) lets you score pairs with cosine, dot product, or a distance. On vectors that are already normalised, dot product ranks the same as cosine. On vectors that aren't, cosine and dot product can rank differently. [OpenAI's guide](https://developers.openai.com/api/docs/guides/embeddings) says its embeddings are normalised to length 1, so those two measures rank the same way there, and it recommends cosine. Use the measure your model's docs name. ### Dimensions and shorter vectors [Gemini's guide](https://ai.google.dev/gemini-api/docs/embeddings) lets you set `output_dimensionality` so the list is shorter. A shorter list saves storage for a small loss in quality. [Cohere](https://docs.cohere.com/docs/embeddings) and [Voyage AI](https://docs.voyageai.com/docs/embeddings) also offer smaller sizes. Lists of different lengths can't be compared. See each maker's docs for the sizes that model allows. ### Query and document forms [Cohere](https://docs.cohere.com/docs/embeddings) asks for `input_type` `search_query` on a question and `search_document` on the text you store. [Voyage AI](https://docs.voyageai.com/docs/embeddings) asks for `input_type` `query` or `document` for retrieval. [Gemini's guide](https://ai.google.dev/gemini-api/docs/embeddings) sets a task type on `gemini-embedding-001`, and a task instruction in the text on `gemini-embedding-2`. Use the query form on questions and the document form on what you store. ### Not every maker sells an embedding model [Anthropic's embeddings page](https://platform.claude.com/docs/en/build-with-claude/embeddings) says Anthropic does not offer its own embedding model, and points to Voyage AI. Pick one model for both sides of a comparison, whichever maker you use. ### Uses beyond search [OpenAI's guide](https://developers.openai.com/api/docs/guides/embeddings) lists search, clustering (grouping similar texts), recommendations, and classification. [Mistral's embeddings page](https://docs.mistral.ai/studio/knowledge-rag/embeddings) calls embeddings vector representations that capture meaning, and lists duplicate detection among the uses. Search against stored chunks is [Embeddings for retrieval](/embeddings-retrieval). ### Upgrading the model [Gemini's guide](https://ai.google.dev/gemini-api/docs/embeddings) says the spaces of `gemini-embedding-001` and `gemini-embedding-2` are incompatible, so an upgrade means re-embedding all your data. After you re-embed, run your retrieval checks again. [Production evaluation](/production-evaluation) shows how to keep a saved set of checks you can re-run. ### Check yourself **Name two settings that must match before you compare two embeddings.** Answer: The model and version, and the size (dimensions). The task or input type, and the similarity measure your model's docs name, have to match too. ## Practice and deep Example: made up to show the idea. Work out one score by hand, rank the texts for a new question, then find what broke a search. Question: "Can I get my money back?" → [0.8, 0.1, 0.3] Text (Northline Desk sample docs) Numbers Cosine with the question "The refund window is 14 days from the charge." [0.9, 0.1, 0.2] 0.99 "After 14 days, you get account credit only." [0.7, 0.2, 0.4] 0.98 "Weekday support is open 09:00 to 17:00." [0.1, 0.9, 0.2] 0.29 Refund row: multiply the matching numbers and add them up: 0.8 times 0.9, plus 0.1 times 0.1, plus 0.3 times 0.2, is 0.79. Divide by the two lists' lengths multiplied together (about 0.80), and you get 0.99. New question Question: "When can I email support?" → [0.2, 0.8, 0.1] Text Numbers Cosine with the question "The refund window is 14 days from the charge." [0.9, 0.1, 0.2] 0.36 "After 14 days, you get account credit only." [0.7, 0.2, 0.4] 0.49 "Weekday support is open 09:00 to 17:00." [0.1, 0.9, 0.2] ? Which row comes first? Work out the last row, or look at which way its numbers point. A · Refund window B · The credit-only row C · Weekday support ## Sources - [Anthropic, Embeddings](https://platform.claude.com/docs/en/build-with-claude/embeddings) - [Cohere, Introduction to Embeddings at Cohere](https://docs.cohere.com/docs/embeddings) - [Gemini, Embeddings](https://ai.google.dev/gemini-api/docs/embeddings) - [Mistral, Embeddings](https://docs.mistral.ai/studio/knowledge-rag/embeddings) - [OpenAI, Vector embeddings](https://developers.openai.com/api/docs/guides/embeddings) - [Sentence Transformers, Semantic Textual Similarity](https://sbert.net/docs/sentence_transformer/usage/semantic_textual_similarity.html) - [Voyage AI, Text Embeddings](https://docs.voyageai.com/docs/embeddings) Vendor and library docs.