Tema: search
-
A filtragem predefinida do ripgrep encurta as pesquisas de código feitas por agentes, em comparação com grep -r
Hipótese: agentes de programação que pesquisam repositórios com as regras de exclusão predefinidas do ripgrep (ficheiros ignorados pelo git, ocultos e binários são saltados) precisam de menos chamadas de pesquisa e leem menos resultados irrelevantes por tarefa do que agentes que usam grep -r sem exclusões, porque não há ocorrências em output de build nem em dependências; não é reportada nenhuma medição.
-
Pesquisa de texto integral no PostgreSQL com tsvector
O PostgreSQL transforma texto num tsvector de lexemas normalizados usando uma configuração de idioma, compara-o com um tsquery, classifica com ts_rank e indexa com GIN; trata stemming e stop words, mas não erros de digitação nem sinónimos, sem configuração adicional.
-
grep and ripgrep for code search: recursion, filters and exit codes
GNU grep searches recursively with -r, narrows with --include and --exclude-dir and exits 0, 1 or 2 for match, no match or error; ripgrep does the same by default while skipping git-ignored, hidden and binary files. Know what each tool skips before trusting an empty result.
-
Document search over a corpus walk-through: indexing pipeline, permissions and reindexing
A design walk-through for search over documents held in a system of record: a derived, rebuildable index fed by change events, ACL keys indexed as fields so filtering happens before ranking, versioned indexes switched by alias, a reconciler that finds drift, and a list of what to defer.
-
Tries for prefix lookups: autocomplete and longest-prefix matching
A trie stores strings with one node per common prefix, so lookup costs the key length regardless of how many keys exist, all keys with a prefix form one subtree, and the longest stored prefix of a query is found in one walk; use it for autocomplete and routing, and compare against a sorted array first.
-
Embeddings as a data type: fixed-length vectors, a distance function and what a column of them needs
An embedding is a fixed-length float vector produced by a specific model, meaningful only under the distance that model was trained for and only next to vectors from the same model version; storing it requires the dimension, the model identifier and the distance to be recorded, and querying it means nearest-neighbour search, exact or approximate.
-
Retrieval basics for LLM applications: chunking, passage identifiers and citing what was retrieved
Retrieval-augmented generation feeds retrieved passages to the model; the decisions that matter are how documents are split, what context each chunk carries, and how the answer points back to a specific passage so that a reader can check it.
Legível por máquina: JSON