Presentando Citai: el motor RAG que construí en 6 artículos — y que ahora podés probar gratis
Martin Palopoli presentó Citai, un motor RAG de conocimiento con citación verificable que permite a los usuarios consultar documentos y verificar las fuentes de las respuestas. El sistema, desarrollado y documentado en una serie de seis artículos, incluye funciones avanzadas como búsqueda híbrida, reranking, streaming SSE y cache semántico. Citai ya está disponible para probar gratis en citai.ai.
- ▪Citai es un motor RAG que proporciona respuestas con citas exactas a fuentes como páginas o párrafos en documentos.
- ▪El sistema utiliza un pipeline de búsqueda híbrida con pgvector, BM25, cross-encoder reranking y MMR para mejorar la relevancia de los resultados.
- ▪Citai incluye un widget embebible, configuración sin código, cache semántico y detección de idioma, y está disponible gratuitamente en citai.ai.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DEV Community |
| Canonical URL | https://dev.to/martin_palopoli/presentando-citai-el-motor-rag-que-construi-en-6-articulos-y-que-ahora-podes-probar-gratis-4dl0 |
| Publication time | Tue, 28 Apr 2026 13:10:00 +0000 |
| Retrieval time | 2026-04-28T13:24:31.953Z |
| Last seen | 2026-04-28T13:24:31.953Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 3vab_cWitNc- |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 1593262) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Martin Palopoli Posted on Apr 28 Presentando Citai: el motor RAG que construí en 6 artículos — y que ahora podés probar gratis #rag #ai #showdev #python Durante los últimos 6 artículos compartí cómo construí cada pieza de un motor RAG de producción: búsqueda híbrida, cross-encoder reranking, streaming SSE, multi-tenancy, cache semántico y detección de idioma.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV Community.
Discussion
0 commentsMore from DEV Community
