LibreChat/packages/api/src/files/validation.ts

187 lines
4.7 KiB
TypeScript
Raw Normal View History

📎 feat: Direct Provider Attachment Support for Multimodal Content (#9994) * 📎 feat: Direct Provider Attachment Support for Multimodal Content * 📑 feat: Anthropic Direct Provider Upload (#9072) * feat: implement Anthropic native PDF support with document preservation - Add comprehensive debug logging throughout PDF processing pipeline - Refactor attachment processing to separate image and document handling - Create distinct addImageURLs(), addDocuments(), and processAttachments() methods - Fix critical bugs in stream handling and parameter passing - Add streamToBuffer utility for proper stream-to-buffer conversion - Remove api/agents submodule from repository 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: remove out of scope formatting changes * fix: stop duplication of file in chat on end of response stream * chore: bring back file search and ocr options * chore: localize upload to provider string in file menu * refactor: change createMenuItems args to fit new pattern introduced by anthropic-native-pdf-support * feat: add cache point for pdfs processed by anthropic endpoint since they are unlikely to change and should benefit from caching * feat: combine Upload Image into Upload to Provider since they both perform direct upload and change provider upload icon to reflect multimodal upload * feat: add citations support according to docs * refactor: remove redundant 'document' check since documents are handled properly by formatMessage in the agents repo now * refactor: change upload logic so anthropic endpoint isn't exempted from normal upload path using Agents for consistency with the rest of the upload logic * fix: include width and height in return from uploadLocalFile so images are correctly identified when going through an AgentUpload in addImageURLs * chore: remove client specific handling since the direct provider stuff is handled by the agent client * feat: handle documents in AgentClient so no need for change to agents repo * chore: removed unused changes * chore: remove auto generated comments from OG commit * feat: add logic for agents to use direct to provider uploads if supported (currently just anthropic) * fix: reintroduce role check to fix render error because of undefined value for Content Part * fix: actually fix render bug by using proper isCreatedByUser check and making sure our mutation of formattedMessage.content is consistent --------- Co-authored-by: Andres Restrepo <andres@thelinuxkid.com> Co-authored-by: Claude <noreply@anthropic.com> 📁 feat: Send Attachments Directly to Provider (OpenAI) (#9098) * 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 🗂️ feat: Send Attachments Directly to Provider (Google) (#9100) * feat: add validation for google PDFs and add google endpoint as a document supporting endpoint * feat: add proper pdf formatting for google endpoints (requires PR #14 in agents) * feat: add multimodal support for google endpoint attachments * feat: add audio file svg * fix: refactor attachments logic so multi-attachment messages work properly * feat: add video file svg * fix: allows for followup questions of uploaded multimodal attachments * fix: remove incorrect final message filtering that was breaking Attachment component rendering fix: manualy rename 'documents' to 'Documents' in git since it wasn't picked up due to case insensitivity in dir name fix: add logic so filepicker for a google agent has proper filetype filtering 🛫 refactor: Move Encoding Logic to packages/api (#9182) * refactor: move audio encode over to TS * refactor: audio encoding now functional in LC again * refactor: move video encode over to TS * refactor: move document encode over to TS * refactor: video encoding now functional in LC again * refactor: document encoding now functional in LC again * fix: extend file type options in AttachFileMenu to include 'google_multimodal' and update dependency array to include agent?.provider * feat: only accept pdfs if responses api is enabled for openai convos chore: address ESLint comments chore: add missing audio mimetype * fix: type safety for message content parts and improve null handling * chore: reorder AttachFileMenuProps for consistency and clarity * chore: import order in AttachFileMenu * fix: improve null handling for text parts in parseTextParts function * fix: remove no longer used unsupported capability error message for file uploads * fix: OpenAI Direct File Attachment Format * fix: update encodeAndFormatDocuments to support OpenAI responses API and enhance document result types * refactor: broaden providers supported for documents * feat: enhance DragDrop context and modal to support document uploads based on provider capabilities * fix: reorder import statements for consistency in video encoding module --------- Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
2025-10-06 17:30:16 -04:00
import { Providers } from '@librechat/agents';
import { mbToBytes, isOpenAILikeProvider } from 'librechat-data-provider';
export interface PDFValidationResult {
isValid: boolean;
error?: string;
}
export interface VideoValidationResult {
isValid: boolean;
error?: string;
}
export interface AudioValidationResult {
isValid: boolean;
error?: string;
}
export async function validatePdf(
pdfBuffer: Buffer,
fileSize: number,
provider: Providers,
): Promise<PDFValidationResult> {
if (provider === Providers.ANTHROPIC) {
return validateAnthropicPdf(pdfBuffer, fileSize);
}
if (isOpenAILikeProvider(provider)) {
return validateOpenAIPdf(fileSize);
}
if (provider === Providers.GOOGLE || provider === Providers.VERTEXAI) {
return validateGooglePdf(fileSize);
}
return { isValid: true };
}
/**
* Validates if a PDF meets Anthropic's requirements
* @param pdfBuffer - The PDF file as a buffer
* @param fileSize - The file size in bytes
* @returns Promise that resolves to validation result
*/
async function validateAnthropicPdf(
pdfBuffer: Buffer,
fileSize: number,
): Promise<PDFValidationResult> {
try {
if (fileSize > mbToBytes(32)) {
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 ${estimatedPages} pages, exceeding Anthropic's 100-page limit`,
};
}
return { isValid: true };
} catch (error) {
console.error('PDF validation error:', error);
return {
isValid: false,
error: 'Failed to validate PDF file',
};
}
}
async function validateOpenAIPdf(fileSize: number): Promise<PDFValidationResult> {
if (fileSize > 10 * 1024 * 1024) {
return {
isValid: false,
error: "PDF file size exceeds OpenAI's 10MB limit",
};
}
return { isValid: true };
}
async function validateGooglePdf(fileSize: number): Promise<PDFValidationResult> {
if (fileSize > 20 * 1024 * 1024) {
return {
isValid: false,
error: "PDF file size exceeds Google's 20MB limit",
};
}
return { isValid: true };
}
/**
* Validates video files for different providers
* @param videoBuffer - The video file as a buffer
* @param fileSize - The file size in bytes
* @param provider - The provider to validate for
* @returns Promise that resolves to validation result
*/
export async function validateVideo(
videoBuffer: Buffer,
fileSize: number,
provider: Providers,
): Promise<VideoValidationResult> {
if (provider === Providers.GOOGLE || provider === Providers.VERTEXAI) {
if (fileSize > 20 * 1024 * 1024) {
return {
isValid: false,
error: `Video file size (${Math.round(fileSize / (1024 * 1024))}MB) exceeds Google's 20MB limit`,
};
}
}
if (!videoBuffer || videoBuffer.length < 10) {
return {
isValid: false,
error: 'Invalid video file: too small or corrupted',
};
}
return { isValid: true };
}
/**
* Validates audio files for different providers
* @param audioBuffer - The audio file as a buffer
* @param fileSize - The file size in bytes
* @param provider - The provider to validate for
* @returns Promise that resolves to validation result
*/
export async function validateAudio(
audioBuffer: Buffer,
fileSize: number,
provider: Providers,
): Promise<AudioValidationResult> {
if (provider === Providers.GOOGLE || provider === Providers.VERTEXAI) {
if (fileSize > 20 * 1024 * 1024) {
return {
isValid: false,
error: `Audio file size (${Math.round(fileSize / (1024 * 1024))}MB) exceeds Google's 20MB limit`,
};
}
}
if (!audioBuffer || audioBuffer.length < 10) {
return {
isValid: false,
error: 'Invalid audio file: too small or corrupted',
};
}
return { isValid: true };
}