Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2026-02-26 12:24:10 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

📁 feat: Send Attachments Directly to Provider (OpenAI) (#9098)

Browse source 
* refactor: change references from direct upload to direct attach to better reflect functionality

since we are just using base64 encoding strategy now rather than Files/File API for sending our attachments directly to the provider, the upload nomenclature no longer makes sense. direct_attach better describes the different methods of sending attachments to providers anyways even if we later introduce direct upload support

* feat: add upload to provider option for openai (and agent) ui

* chore: move anthropic pdf validator over to packages/api

* feat: simple pdf validation according to openai docs

* feat: add provider agnostic validatePdf logic to start handling multiple endpoints

* feat: add handling for openai specific documentPart formatting

* refactor: move require statement to proper place at top of file

* chore: add in openAI endpoint for the rest of the document handling logic

* feat: add direct attach support for azureOpenAI endpoint and agents

* feat: add pdf validation for azureOpenAI endpoint

* refactor: unify all the endpoint checks with isDocumentSupportedEndpoint

* refactor: consolidate Upload to Provider vs Upload image logic for clarity

* refactor: remove anthropic from anthropic_multimodal fileType since we support multiple providers now
This commit is contained in:
Dustin Healy 2025-08-17 02:14:25 -07:00 • committed by Dustin Healy
parent 89843262b2
commit b5aadf1302
10 changed files with 122 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

72
api/server/services/Files/validation/pdfValidator.js
View file

@ -1,72 +0,0 @@
const { logger } = require('~/config');
const { anthropicPdfSizeLimit } = require('librechat-data-provider');
/**
* Validates if a PDF meets Anthropic's requirements
* @param {Buffer} pdfBuffer - The PDF file as a buffer
* @param {number} fileSize - The file size in bytes
* @returns {Promise<{isValid: boolean, error?: string}>}
*/
async function validateAnthropicPdf(pdfBuffer, fileSize) {
try {
if (fileSize > anthropicPdfSizeLimit) {
return {
isValid: false,
error: `PDF file size (${Math.round(fileSize / (1024 * 1024))}MB) exceeds Anthropic's 32MB limit`,
};
}
if (!pdfBuffer || pdfBuffer.length < 5) {
return {
isValid: false,
error: 'Invalid PDF file: too small or corrupted',
};
}
const pdfHeader = pdfBuffer.subarray(0, 5).toString();
if (!pdfHeader.startsWith('%PDF-')) {
return {
isValid: false,
error: 'Invalid PDF file: missing PDF header',
};
}
const pdfContent = pdfBuffer.toString('binary');
if (
pdfContent.includes('/Encrypt ') ||
pdfContent.includes('/U (') ||
pdfContent.includes('/O (')
) {
return {
isValid: false,
error: 'PDF is password-protected or encrypted. Anthropic requires unencrypted PDFs.',
};
}
const pageMatches = pdfContent.match(/\/Type[\s]*\/Page[^s]/g);
const estimatedPages = pageMatches ? pageMatches.length : 1;
if (estimatedPages > 100) {
return {
isValid: false,
error: `PDF has approximately ${estimatedPages} pages, exceeding Anthropic's 100-page limit`,
};
}
logger.debug(
`PDF validation passed: ${Math.round(fileSize / 1024)}KB, ~${estimatedPages} pages`,
);
return { isValid: true };
} catch (error) {
logger.error('PDF validation error:', error);
return {
isValid: false,
error: 'Failed to validate PDF file',
};
}
}
module.exports = {
validateAnthropicPdf,
};