← Back
Home › Systems › AI applications

rag

retrieval-augmented generation

enterprise search assistant

SystemTechniques · 16Primitives · 57 rag Citation groundingagentic-ai · medium: Attaching answer spans to retrieved source passages and verifying each claim is supportedSemantic cacheagentic-ai · medium: Caching LLM responses keyed by embedding similarity of prompts, with thresholds and invalidationContrastive learningmachine-learning · medium: Train an encoder so two views of the same thing score higher than every other pair in the batch; InfoNCE with a temperature, no labels needed.›HTML main-text extractionmachine-learning · medium: Decode bytes, tolerate broken markup, drop non-content nodes and score text blocks by length and link density to keep the main run, with headings, metadata and offsets for citation.›LLM-as-judgemachine-learning · medium: Grade open-ended outputs with a language model under a rubric, then correct its known biases by order swapping, voting and calibration against human labels.›Cross-encoder rerankingsearch-sort · medium: Re-score the top-k candidates of a cheap first stage with a model that reads query and candidate together; more accurate than separate embeddings, but one model call per pair.›Nearest-neighbour search with filte…search-sort · medium: Combine approximate nearest-neighbour search with attribute predicates by pre-filtering, post-filtering or filter-aware graph traversal, chosen by how many items pass.›Text chunkingmachine-learning · low: Cut documents into token-bounded pieces along structure boundaries, keeping offsets and section paths, so each piece embeds well and can be cited.›Embeddingsmachine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.›Top-k selectionsearch-sort · low: Keep the k best of n items without sorting all n - bounded min-heap for streams, quickselect for arrays, threshold pruning to skip most items.›BM25 rankingsearch-sort · low: The standard lexical relevance score: IDF-weighted term frequency with saturation (k1) and length normalization (b); default in Lucene, Elasticsearch and SQLite FTS5.›Context window managementagentic-ai · low: Keep an agent's growing history inside the model's window by truncating, clearing and summarizing old turns in a cheap-to-lossy ladder, at turn boundaries.›Prompt cachingagentic-ai · low: Reuse the attention keys/values of a repeated prompt prefix, so an agent's growing context is prefilled once and later turns pay only for the new tokens.›Evaluation metricsmachine-learning · low: Precision, recall, ROC AUC, average precision, log loss, NDCG and pass@k computed correctly, plus paired confidence intervals for comparing models.›PDF text extractionmachine-learning · low: Rebuild words, lines, columns and reading order from the glyph positions a born-digital PDF stores, and route pages without usable text to OCR.›Hybrid search and rank fusionsearch-sort · low: Merge a keyword (BM25) result list and a vector (ANN) list into one ranking, by ranks (RRF) or by normalized scores (convex combination).›Query expansionsearch-sort · low: Rewriting queries with synonyms, pseudo-relevance feedback or LLM-generated variants (multi-query, HyDE)Fuzzy string matchingsearch-sort · low: Edit distance, Jaro-Winkler and trigram indexes for approximate name and address matchingLRU and CLOCKsystems · low: LRU evicts the least recently used entry via hash map plus linked list; CLOCK approximates it with a reference bit, so hits take no lock.›Data augmentationmachine-learning · low: Generate label-preserving variants of each training example on the fly to enlarge the effective dataset and bake in invariances.›Loss functionsmachine-learning · low: The scalar a model minimizes: cross-entropy for classes and tokens, MSE or Huber for values, each with a stable form and simple gradient.›Negative samplingmachine-learning · low: Train by contrasting each observed positive with a few sampled negatives instead of normalising over every candidate; the choice of sampler decides bias and quality.›Text normalizationmachine-learning · low: Rewrite messy text into one canonical form for matchers and models, or into spoken words for speech output (and back), keeping a map to the original offsets.›+ 9 more techniques+ 41 more primitives

Similar systems

Share the most building blocks with this one.

deep-research 43 %agent-memory 31 %product-search 25 %support-agent 25 %vector-db 23 %

In-house systems

Named systems of this kind at large companies, with their paper or write-up.

AI @ Morgan Stanley AssistantMorgan Stanley