Glossary

Information Retrieval

What is Information Retrieval?

Information retrieval covers methods that find the documents or passages in a large body of text that match a query and rank them by relevance. Classic approaches such as BM25 weight search terms by how often and how rarely they occur; newer ones add semantic similarity. It underpins search engines, enterprise search and retrieval-augmented generation, in which a language model uses the retrieved passages as the basis for its answer.

How KI.ordo helps

KI.ordo's knowledge search uses BM25 keyword search directly on the server, without vector search, and agents cite the sources they find.

Learn more →

Topics

Search
BM25
Retrieval

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

Document search with NLP

Document search with NLP uses natural language processing techniques to find information in document collections in response to a freely worded question. Instead of matching exact word sequences only, such systems take into account word forms, the weighting of rare terms or similarity of meaning. For example, someone typing 'How do I request leave?' receives the relevant section of the staff handbook, even if it talks about a 'holiday request'.

Retrieval-augmented generation (RAG)

Retrieval-augmented generation combines search with text generation: before answering, the system searches a knowledge collection – such as manuals, policies or FAQs – for relevant passages and passes them to the language model as context. The answer is therefore based on current, company-specific content rather than only on the model's training knowledge. This reduces invented statements, makes sources traceable and allows updates without retraining.

RAG
knowledge search
+1

Document reranking

Document reranking is a second sorting step in search and RAG systems: a fast initial search returns a set of candidate results, which a more precise but more costly method then reorders by relevance. This is often done by a so-called cross-encoder that assesses the question and a passage together. As a result, the most relevant passages end up at the top before a language model formulates an answer from them.

AI Search

AI search refers to search methods that use AI to grasp the intent behind a query, weight results and often generate a summarised answer with sources rather than a plain list of links. Technically, they use keyword search, vector search over embeddings or a combination, frequently followed by a language model. Examples include answer engines on the web and internal knowledge search that helps staff find what they need in manuals and policies.

Search
Knowledge
+1