Glossary

Retrieval pipeline

What is Retrieval pipeline?

A retrieval pipeline is the sequence of processing steps a system uses to find the right information for a question. Typical steps are: ingesting and cleaning documents, splitting them into chunks, building a search index, optionally rewriting the query, retrieving matches, ranking them (reranking) and passing the best ones to the language model. It is the foundation of every RAG application, and its quality largely determines how good the resulting answers are.

How KI.ordo helps

In KI.ordo, stored knowledge is split into overlapping chunks and searched with BM25 keyword search directly on the server – without a vector database.

Learn more →

Topics

RAG
search
data processing

Try KI.ordo

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

Start demo

← All terms

Related terms

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.

Query expansion

Query expansion automatically adds related terms to a search query so that relevant documents using different wording are also found. Typical additions are synonyms, abbreviations, word forms or translations: a search for “cancellation” might then also find texts about “termination of contract”. This is especially useful for keyword search, but it can reduce precision if too many or unsuitable terms are added. Today, language models are often used to generate the expanded queries.

search
synonyms
+1

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.

Search
BM25
+1