From c3a67e6cb57782e3f5eaead493be594e3895bf63 Mon Sep 17 00:00:00 2001 From: Dan Lew Date: Mon, 26 Jan 2026 11:04:56 -0600 Subject: [PATCH] Added docs for OCR document parser strategy I was not sure if we should callout that it's technically not OCR, can update if we want to do that. --- content/docs/features/ocr.mdx | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/content/docs/features/ocr.mdx b/content/docs/features/ocr.mdx index be2aac233..e16c54683 100644 --- a/content/docs/features/ocr.mdx +++ b/content/docs/features/ocr.mdx @@ -163,11 +163,23 @@ ocr: 3. Download the service account JSON key file 4. Set the `GOOGLE_SERVICE_KEY_FILE` environment variable using one of the supported methods -### 4. Custom OCR (Planned) +### 4. Document Parser + +The built-in document parser OCR strategy supports native parsing of some +document file formats (like PDF, DOCX, and XLSX) as text. + +**Configuration:** +```yaml +# `librechat.yaml` +ocr: + strategy: "document_parser" +``` + +### 5. Custom OCR (Planned) Support for custom OCR providers and user-defined strategies is planned for future releases. -### 5. Upload Files to Provider (Direct) +### 6. Upload Files to Provider (Direct) For supported LLM Providers (**OpenAI, AzureOpenAI, Anthropic, Google, and AWS Bedrock**) and their respective models, files can now be sent directly to the provider APIs as message attachments, allowing the provider to use their own native OCR implementations to parse files using the `Upload to Provider` option in the file attachment dropdown menu.