feat: PDF ingestion via unpdf with page chunking#33
feat: PDF ingestion via unpdf with page chunking#33RaviTharuma wants to merge 1 commit intoAVIDS2:mainfrom
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b0e39c413c
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| */ | ||
| export async function extractPdfText(input: PdfInput): Promise<PdfExtractionResult> { | ||
| // Dynamic import — unpdf is optional | ||
| const unpdf = await import('unpdf').catch(() => null) as { |
There was a problem hiding this comment.
This new loader hard-depends on resolving import('unpdf'), but the package is not declared in Memorix’s dependency metadata, so default installs won’t provide it. In the documented global-install flow (npm install -g memorix), telling users to run local npm install unpdf still won’t make this import resolvable from the global package tree, so memorix_ingest_pdf will consistently fail for those users.
Useful? React with 👍 / 👎.
| const limit = Math.min(rawPages.length, maxPages); | ||
|
|
||
| for (let i = 0; i < limit; i++) { |
There was a problem hiding this comment.
maxPages is treated as an arbitrary number and used directly in i < limit, which causes fractional values to round up in practice (e.g., maxPages=1.1 processes pages 1 and 2). Negative values also silently result in zero ingestion. Because this tool parameter represents a page count, it should be validated/coerced to a positive integer before computing the loop bound.
Useful? React with 👍 / 👎.
| @@ -0,0 +1,32 @@ | |||
| import { describe, it, expect } from 'bun:test'; | |||
There was a problem hiding this comment.
The repository’s test runner is Vitest (npm test runs vitest run), but this file imports from bun:test. In the Node/Vitest environment this module is not available, so the new test suite cannot execute as part of normal CI/test runs.
Useful? React with 👍 / 👎.
|
Thanks for working on PDF ingestion — page-level storage is a good direction, but this branch still has a few hard blockers.
So at the moment this is not just a dependency-install issue — it needs one more pass to make the optional dependency story and the repo's type/test expectations line up. |
2 participants
Summary
Adds an
memorix_ingest_pdfMCP tool that extracts text from PDF files usingunpdfand stores each page (or chunk) as a memorix observation.What's included
src/multimodal/pdf-loader.ts— PDF text extractor with:unpdfdependency (clear error if not installed)src/server.ts— MCP tool registration (memorix_ingest_pdf)tests/multimodal/pdf-loader.test.ts— 4 tests covering:Design decisions
unpdfis an optional peer dependency — tool returns clear error if not installed (npm install unpdf).how-it-worksobservation type with PDF metadata (page number, total pages, filename) in facts.unpdfis pure JS/WASM.Tests