AI search
AI search (also called AI-powered search, generative search, or an answer engine) is a class of search engine and search feature that uses large language models (LLMs) and generative AI to produce a direct
Information Retrieval
Explore Information Retrieval through related topics and the articles other pages reference most.
Most referenced in this topic
Ranked by links from other AI Wiki pages.
Explore articles
Browse subtopics (33)
Articles that also belong to these categories. Counts cover all of Information Retrieval.
All articles (74)Natural Language Processing (29)Machine Learning (14)AI Companies (13)Open Source AI (12)AI Tools & Products (10)AI Agents (8)AI Infrastructure (7)Developer Tools (7)AI Models (4)Artificial Intelligence (4)Large Language Models (4)AI Benchmarks (3)Algorithms (3)Chinese AI (3)Enterprise AI (3)AI Inference (2)Anthropic (2)ChatGPT (2)Mathematics (2)Model Evaluation (2)Neural Networks (2)OpenAI (2)AI History (1)AI Research (1)Computer Science (1)Computer Vision (1)Deep Learning (1)Generative AI (1)Meta AI (1)Microsoft (1)Model Architecture (1)Multimodal AI (1)Research Organizations (1)
Showing 1-60 of 74 articles
Agent memory
Agent memory is the set of systems that let an AI agent retain and recall information beyond a single context window, so it can carry knowledge, preferences, and experience from one interaction or session into…
Agentic RAG
Agentic RAG (agentic retrieval-augmented generation) is a retrieval-augmented generation design pattern in which one or more autonomous large language model AI agents plan, execute, and revise a sequence of…
Atlas (language model)
Atlas is a retrieval-augmented language model developed by researchers at Meta AI (the group then known as Facebook AI Research, or FAIR).
Average Precision
Average precision (AP) is an evaluation metric that summarizes the precision-recall curve of a ranked list into a single number between 0 and 1, equal to the area under that curve.
BGE (BAAI General Embedding)
BGE (BAAI General Embedding) is a family of open-source text embedding and reranking models from the Beijing Academy of Artificial Intelligence (BAAI), first released in August 2023 and distributed through the…
BM25 (Okapi BM25)
BM25, also called Okapi BM25 or Best Match 25, is a probabilistic ranking function used by search engines and information retrieval systems to estimate how relevant a document is to a given query.
Candidate Generation
Candidate generation is the first stage in a multi-stage recommendation system or information retrieval pipeline.
ChatGPT Search
ChatGPT Search is a web search feature built into ChatGPT, the conversational artificial intelligence product from OpenAI.
Chunking (information retrieval)
Chunking is the preprocessing step in document indexing and retrieval-augmented generation (RAG) systems in which a long document or corpus is split into smaller passages, called chunks, that are then embedded…
ColBERT
ColBERT (Contextualized Late Interaction over BERT) is a neural information retrieval model that encodes queries and documents into matrices of token-level vectors and scores them with a late-interaction…
Consensus (academic AI search)
Consensus is an AI-powered academic search engine that uses large language models to find, summarise, and synthesise findings from peer-reviewed scientific literature across a corpus of more than 200 million…
Contextual AI
Contextual AI is an American enterprise artificial intelligence company headquartered in Mountain View, California, that builds production-grade systems based on retrieval-augmented generation.
Contextual retrieval
Contextual retrieval is a document indexing technique for retrieval augmented generation systems, introduced by anthropic on September 19, 2024 in a blog post titled "Introducing Contextual Retrieval".
Cross-encoder
A cross-encoder is a neural network architecture that scores a pair of texts by feeding them jointly into a single transformer (such as BERT) and reading out one scalar score for the pair, for example a…
Dense Passage Retrieval (DPR)
Dense Passage Retrieval (DPR) is a neural information retrieval method that uses a dual-encoder BERT architecture to map questions and passages into dense vectors
Elicit (research tool)
Elicit is an AI research assistant that helps researchers find, screen, summarize, and extract data from academic papers, with a particular focus on automating parts of the systematic review and literature…
EmbeddingGemma
EmbeddingGemma is an open text embedding model from Google, released in September 2025, that turns text into dense numeric vectors for search, retrieval, classification, and clustering.
Embeddings
In machine learning, an embedding is a learned representation that maps an input into a vector, usually so that a downstream model or comparison rule can use relationships encoded in the vector's geometry.
Exa AI
Exa AI (formerly Metaphor) is an artificial intelligence company that builds a search engine designed specifically for AI applications.
FAISS
FAISS (Facebook AI Similarity Search) is an open-source library from Meta for efficient similarity search and clustering of dense vectors
FRAMES (benchmark)
FRAMES is an evaluation dataset for retrieval-augmented generation that tests factual accuracy, retrieval, and reasoning together rather than one at a time.
Genspark
Genspark is an AI agent and productivity product developed by MainFunc, Inc., a startup based in Palo Alto, California, with an office in Singapore.
Glean (company)
Glean is an American enterprise AI software company headquartered in Palo Alto, California, that develops an AI-powered work platform combining enterprise search, an AI assistant, and AI agents.
GraphRAG
GraphRAG is a graph-based approach to retrieval-augmented generation developed by Microsoft Research, first described publicly on February 13, 2024 and formalized in the paper "From Local to Global: A Graph…
HNSW
Hierarchical Navigable Small World (HNSW) is an approximate nearest-neighbor search algorithm that indexes high-dimensional vectors in a multi-layer proximity graph and answers similarity queries in expected…
Hashing
Hashing in machine learning is the use of hash functions to map data of arbitrary size (a word, a URL, a document, a vector) into a fixed-size integer range, trading a small and controllable amount of…
Haystack (framework)
Haystack is an open-source AI orchestration framework developed by deepset, a Berlin-based company, for building production-ready natural language processing (NLP), retrieval-augmented generation (RAG), and AI…
Hebbia
Hebbia is an American enterprise AI company that builds software for knowledge-intensive professional work, primarily in financial services, law, and consulting.
HyDE (Hypothetical Document Embeddings)
HyDE (Hypothetical Document Embeddings) is a zero-shot dense retrieval technique that, instead of searching with the user's query, first prompts an instruction-following large language model to write a…
Hybrid search
Hybrid search is an information retrieval technique that runs a lexical (sparse) keyword retriever, typically BM25, and a semantic (dense) vector retriever in parallel against the same corpus
Information Retrieval
Information retrieval (IR) is the study and engineering of systems that identify material likely to satisfy an information need.
Jina Embeddings v3
Jina Embeddings v3 is a multilingual text embedding model released by Jina AI on September 18, 2024, with 570 million parameters, support for 89 languages, an 8,192 token context window, and a stack of…
Knowledge graph
A knowledge graph is a structured representation of real-world entities and the relationships between them, organized as a network of interconnected nodes and edges.
Knowledge representation and reasoning
Knowledge representation and reasoning (often abbreviated KR&R, or just KR) is the branch of artificial intelligence concerned with encoding facts about the world in a form a machine can manipulate, and with…
LanceDB
LanceDB is an open-source, developer-friendly vector database and multimodal lakehouse built on the Lance columnar storage format, designed to store vector embeddings, images, video, audio, and structured…
Latent semantic analysis (LSA)
Latent semantic analysis (LSA), called latent semantic indexing (LSI) in information retrieval contexts, is an unsupervised technique that maps both terms and documents into a shared low-dimensional vector…
Linkup
Linkup is a Paris-based artificial intelligence company that operates a web search API designed for AI applications, autonomous agents, and retrieval-augmented generation (RAG) systems.
LlamaIndex
LlamaIndex is an open-source data framework for building large language model (LLM) applications, with a particular focus on retrieval-augmented generation (RAG) and document processing.
MMTEB
MMTEB (Massive Multilingual Text Embedding Benchmark) is a large, community-built suite for evaluating text embedding models across more than 500 quality-controlled tasks and over 250 languages
MTEB (Massive Text Embedding Benchmark)
MTEB, short for Massive Text Embedding Benchmark, is the standard public leaderboard for evaluating text embedding models across many task types at once.
Matryoshka representation learning
Matryoshka Representation Learning (MRL) is a representation learning technique that trains a single neural model to produce embedding vectors which remain useful when truncated to many smaller dimensionalities
Multi-hop RAG
Multi-hop RAG is a family of retrieval-augmented generation techniques designed to answer questions that require composing evidence from two or more documents or text chunks.
Phind
Phind was an AI-powered answer engine built for software developers. The product combined a live web index with fine-tuned large language models to return cited, code-aware answers to programming questions…
Product quantization
Product quantization (PQ) is a vector-compression technique for approximate nearest-neighbor (ANN) search that splits each high-dimensional vector into M equal sub-vectors and quantizes each sub-vector with…
Question answering
Question answering (QA) is the task of producing an answer to a question, usually expressed in natural language.
Qwen3 Embedding
Qwen3 Embedding is a family of open text embedding and reranking models released by Alibaba's Qwen team in June 2025.
Ranking
Ranking in machine learning, often called learning to rank (LTR), is the supervised task of ordering a set of items by relevance to a query
Re-ranking
Re-ranking, also written as reranking, is the second stage of a two-stage information retrieval pipeline: a fast first-stage retriever returns a candidate set of roughly 50 to 1000 documents
Recommender System
A recommender system (also called a recommendation system or recommendation engine) is an information filtering system that predicts the preference a user would give to an item and uses those predictions to…
Reranker
A reranker (also called a cross-encoder reranker or rerank model) is a neural model used in retrieval augmented generation and information retrieval pipelines to re-score an initial set of candidate documents…
ResearchRabbit
ResearchRabbit is a free literature-discovery and citation-mapping tool that helps researchers explore academic publications through interactive visual networks rather than keyword search.
SEO
Search engine optimization (SEO) is the practice of preparing websites and other content so that search engines surface them in response to user queries.
SPLADE
SPLADE (Sparse Lexical and Expansion model) is a learned sparse retrieval model that encodes a query or document as a weighted
SciSpace
SciSpace is an AI-powered research platform and literature-review assistant aimed at academics, students, and researchers.
Scite
Scite (stylized lowercase as scite, at scite.ai) is a research-discovery and citation-analysis platform best known for Smart Citations, which use deep learning to classify each citation in the scientific…
Search Engine
A search engine is a software system that retrieves information from a corpus (the web, a private dataset, or a document store) and ranks results by relevance to a user query.
Semantic Scholar
Semantic Scholar is a free, AI-powered academic search engine and open research-data platform built by the Allen Institute for AI (AI2, also styled Ai2)
Semantic chunking
Semantic chunking is a family of document-segmentation strategies for retrieval augmented generation pipelines that places chunk boundaries based on similarity between sentence embeddings rather than fixed…
Similarity Measure
A similarity measure (also called a similarity function or similarity metric) is a real-valued function that quantifies the degree of resemblance between two objects, returning a large value when the objects…