From 8b9336466f711626fb2c27e2a880d559102f3f88 Mon Sep 17 00:00:00 2001 From: Dayuan Jiang <34411969+DayuanJiang@users.noreply.github.com> Date: Thu, 11 Dec 2025 14:14:31 +0900 Subject: [PATCH] feat: make PDF/text extraction char limit configurable via env (#214) Add NEXT_PUBLIC_MAX_EXTRACTED_CHARS environment variable to allow configuring the maximum characters extracted from PDF and text files. Defaults to 150000 (150k chars) if not set. --- env.example | 1 + lib/pdf-utils.ts | 7 +++++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/env.example b/env.example index 616243e..65dd428 100644 --- a/env.example +++ b/env.example @@ -90,3 +90,4 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0 # Enable PDF file upload to extract text and generate diagrams # Enabled by default. Set to "false" to disable. # ENABLE_PDF_INPUT=true +# NEXT_PUBLIC_MAX_EXTRACTED_CHARS=150000 # Max characters for PDF/text extraction (default: 150000) diff --git a/lib/pdf-utils.ts b/lib/pdf-utils.ts index b069cc4..2e5c4ad 100644 --- a/lib/pdf-utils.ts +++ b/lib/pdf-utils.ts @@ -1,7 +1,10 @@ import { extractText, getDocumentProxy } from "unpdf" -// Maximum characters allowed for extracted text -export const MAX_EXTRACTED_CHARS = 150000 // 150k chars +// Maximum characters allowed for extracted text (configurable via env) +const DEFAULT_MAX_EXTRACTED_CHARS = 150000 // 150k chars +export const MAX_EXTRACTED_CHARS = + Number(process.env.NEXT_PUBLIC_MAX_EXTRACTED_CHARS) || + DEFAULT_MAX_EXTRACTED_CHARS // Text file extensions we support const TEXT_EXTENSIONS = [