Embeddings
Gemini Embedding 2
Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
- Vision
AI model category
Embedding models
The search layer behind knowledge assistants, semantic search and recommendations.
- 6 models
Embedding models turn text into lists of numbers, called vectors, so that similar meanings end up close together. They power the search step in retrieval-augmented generation, where an assistant first finds the right passages and then answers from them. Rerank models take the top results and sort them more precisely.
Embeddings are cheap per request, but switching models later means re-embedding every document, so the choice deserves a proper test.
Embeddings
All embedding models
Embeddings
text-embedding-3-large
OpenAI
OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
- OpenAI
Embeddings
text-embedding-3-small
OpenAI
OpenAI's efficient, lowest-cost embedding model, with 1,536-dimension vectors for search, retrieval and similarity at scale.
- OpenAI
Embeddings
Cohere Embed v4
Cohere
Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
- Cohere
- Vision
Embeddings
Cohere Rerank 4
Cohere
Cohere's multilingual rerank models, which sort search results by relevance, in a best-quality Pro version and a low-latency Fast version.
- Cohere
Embeddings
Voyage 4
Voyage AI by MongoDB
Voyage AI's current embedding series, now part of MongoDB, with large, standard and lite models that share one embedding space.
- Voyage AI by MongoDB
How to choose
How to choose in this category
Build a small test set of real questions with the passages that should answer them, and measure how often each model finds them. Check language support if your documents are not all in English, and the maximum input length per chunk. Adding a rerank step is often the cheapest way to improve results.
Other categories
Browse other categories
Keep exploring
Related on ExecMedia
Related services
View all related services- RAG knowledge assistants Assistants that answer questions from your own documents and show where each answer came from.
- Database design Data models that stay fast and correct as your business grows, with backups and access rules in place.
- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
Solutions
View all solutionsIndustries
View all industriesGuides and articles
View all guides and articlesMCP servers
View all mcp servers- Knowledge and memory Servers that give AI long-term memory or access to knowledge bases, wikis and personal notes.
- Confluence Atlassian's official Rovo MCP server lets AI search and read Confluence spaces and pages, create and edit content and add comments and labels.
- Memory The MCP project's Memory reference server gives AI a local knowledge graph to store people, things and facts and recall them later.
- Obsidian A community MCP server that lets AI list, read, search, edit, append to and delete notes in an Obsidian vault through the Local REST API plugin.
- Readwise Readwise's official hosted MCP server lets AI search and manage your reading highlights and Reader documents.
- Databases Servers that let AI query and, where allowed, change data in SQL, NoSQL, analytics and vector databases.
Glossary terms
View all glossary terms- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
- Hallucination A hallucination is when an AI model states something false or invented as if it were true, such as a made-up fact, figure or source.