Repository navigation
fix(worker): conecta el pipeline completo de ingesta (RF-03) - #21
Merged
Merged
Conversation
El processor de BullMQ solo ejecutaba la extracción de texto del PDF y nunca encadenaba fragmentación, embeddings ni el marcado del documento como "listo": queue.ts recibía únicamente el servicio de extracción, sin chunking ni embed-and-index. Los documentos quedaban en estado "processing" para siempre pese a que cada pieza del pipeline (RF-03) ya tenía su propia PR mergeada. También se conecta ensureChunksVectorIndex en el arranque del worker, que existía y tenía tests pero nunca se invocaba, pese a que el README ya documentaba ese comportamiento. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Resumen
ready: los documentos se quedaban enprocessingpara siempre aunque cada pieza de RF-03 ya tenía su PR mergeada. Ahoraqueue.tsrecibe y ejecuta el pipeline completo (extracción → fragmentación → embeddings e indexación → estado).ensureChunksVectorIndexal arrancar el worker: existía y tenía tests, pero nadie lo llamaba, pese a que el README ya documentaba ese comportamiento.Es un bloqueador del criterio de aceptación "un PDF de 20 páginas pasa a estado listo en menos de 60 s".
Test plan
pnpm --filter @docqa/worker test(18 archivos)pnpm --filter @docqa/worker test:integration(115 passed, Mongo real)readyy que sus chunks aparecen enchunks🤖 Generated with Claude Code