LibreChat/api/server/services/Files/Local/crud.js
Danny Avila bcd97aad2f
Some checks failed
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Has been cancelled
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Has been cancelled
📎 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

367 lines
14 KiB
JavaScript

const fs = require('fs');
const path = require('path');
const axios = require('axios');
const { logger } = require('@librechat/data-schemas');
const { EModelEndpoint } = require('librechat-data-provider');
const { generateShortLivedToken } = require('@librechat/api');
const { resizeImageBuffer } = require('~/server/services/Files/images/resize');
const { getBufferMetadata } = require('~/server/utils');
const paths = require('~/config/paths');
/**
* Saves a file to a specified output path with a new filename.
*
* @param {Express.Multer.File} file - The file object to be saved. Should contain properties like 'originalname' and 'path'.
* @param {string} outputPath - The path where the file should be saved.
* @param {string} outputFilename - The new filename for the saved file (without extension).
* @returns {Promise<string>} The full path of the saved file.
* @throws Will throw an error if the file saving process fails.
*/
async function saveLocalFile(file, outputPath, outputFilename) {
try {
if (!fs.existsSync(outputPath)) {
fs.mkdirSync(outputPath, { recursive: true });
}
const fileExtension = path.extname(file.originalname);
const filenameWithExt = outputFilename + fileExtension;
const outputFilePath = path.join(outputPath, filenameWithExt);
fs.copyFileSync(file.path, outputFilePath);
fs.unlinkSync(file.path);
return outputFilePath;
} catch (error) {
logger.error('[saveFile] Error while saving the file:', error);
throw error;
}
}
/**
* Saves an uploaded image file to a specified directory based on the user's ID and a filename.
*
* @param {ServerRequest} req - The Express request object, containing the user's information and app configuration.
* @param {Express.Multer.File} file - The uploaded file object.
* @param {string} filename - The new filename to assign to the saved image (without extension).
* @returns {Promise<void>}
* @throws Will throw an error if the image saving process fails.
*/
const saveLocalImage = async (req, file, filename) => {
const appConfig = req.config;
const imagePath = appConfig.paths.imageOutput;
const outputPath = path.join(imagePath, req.user.id ?? '');
await saveLocalFile(file, outputPath, filename);
};
/**
* Saves a buffer to a specified directory on the local file system.
*
* @param {Object} params - The parameters object.
* @param {string} params.userId - The user's unique identifier. This is used to create a user-specific directory.
* @param {Buffer} params.buffer - The buffer to be saved.
* @param {string} params.fileName - The name of the file to be saved.
* @param {string} [params.basePath='images'] - Optional. The base path where the file will be stored.
* Defaults to 'images' if not specified.
* @returns {Promise<string>} - A promise that resolves to the path of the saved file.
*/
async function saveLocalBuffer({ userId, buffer, fileName, basePath = 'images' }) {
try {
const { publicPath, uploads } = paths;
const directoryPath = path.join(basePath === 'images' ? publicPath : uploads, basePath, userId);
if (!fs.existsSync(directoryPath)) {
fs.mkdirSync(directoryPath, { recursive: true });
}
fs.writeFileSync(path.join(directoryPath, fileName), buffer);
const filePath = path.posix.join('/', basePath, userId, fileName);
return filePath;
} catch (error) {
logger.error('[saveLocalBuffer] Error while saving the buffer:', error);
throw error;
}
}
/**
* Saves a file from a given URL to a local directory. The function fetches the file using the provided URL,
* determines the content type, and saves it to a specified local directory with the correct file extension.
* If the specified directory does not exist, it is created. The function returns the name of the saved file
* or null in case of an error.
*
* @param {Object} params - The parameters object.
* @param {string} params.userId - The user's unique identifier. This is used to create a user-specific path
* in the local file system.
* @param {string} params.URL - The URL of the file to be downloaded and saved.
* @param {string} params.fileName - The desired file name for the saved file. This may be modified to include
* the correct file extension based on the content type.
* @param {string} [params.basePath='images'] - Optional. The base directory where the file will be saved.
* Defaults to 'images' if not specified.
*
* @returns {Promise<{ bytes: number, type: string, dimensions: Record<string, number>} | null>}
* A promise that resolves to the file metadata if the file is successfully saved, or null if there is an error.
*/
async function saveFileFromURL({ userId, URL, fileName, basePath = 'images' }) {
try {
const response = await axios({
url: URL,
responseType: 'arraybuffer',
});
const buffer = Buffer.from(response.data, 'binary');
const { bytes, type, dimensions, extension } = await getBufferMetadata(buffer);
// Construct the outputPath based on the basePath and userId
const outputPath = path.join(paths.publicPath, basePath, userId.toString());
// Check if the output directory exists, if not, create it
if (!fs.existsSync(outputPath)) {
fs.mkdirSync(outputPath, { recursive: true });
}
// Replace or append the correct extension
const extRegExp = new RegExp(path.extname(fileName) + '$');
fileName = fileName.replace(extRegExp, `.${extension}`);
if (!path.extname(fileName)) {
fileName += `.${extension}`;
}
// Save the file to the output path
const outputFilePath = path.join(outputPath, fileName);
fs.writeFileSync(outputFilePath, buffer);
return {
bytes,
type,
dimensions,
};
} catch (error) {
logger.error('[saveFileFromURL] Error while saving the file:', error);
return null;
}
}
/**
* Constructs a local file path for a given file name and base path. This function simply joins the base
* path and the file name to create a file path. It does not check for the existence of the file at the path.
*
* @param {Object} params - The parameters object.
* @param {string} params.fileName - The name of the file for which the path is to be constructed. This should
* include the file extension.
* @param {string} [params.basePath='images'] - Optional. The base directory to be used for constructing the file path.
* Defaults to 'images' if not specified.
*
* @returns {string}
* The constructed local file path.
*/
async function getLocalFileURL({ fileName, basePath = 'images' }) {
return path.posix.join('/', basePath, fileName);
}
/**
* Validates if a given filepath is within a specified subdirectory under a base path. This function constructs
* the expected base path using the base, subfolder, and user id from the request, and then checks if the
* provided filepath starts with this constructed base path.
*
* @param {ServerRequest} req - The request object from Express. It should contain a `user` property with an `id`.
* @param {string} base - The base directory path.
* @param {string} subfolder - The subdirectory under the base path.
* @param {string} filepath - The complete file path to be validated.
*
* @returns {boolean}
* Returns true if the filepath is within the specified base and subfolder, false otherwise.
*/
const isValidPath = (req, base, subfolder, filepath) => {
const normalizedBase = path.resolve(base, subfolder, req.user.id);
const normalizedFilepath = path.resolve(filepath);
return normalizedFilepath.startsWith(normalizedBase);
};
/**
* @param {string} filepath
*/
const unlinkFile = async (filepath) => {
try {
await fs.promises.unlink(filepath);
} catch (error) {
logger.error('Error deleting file:', error);
}
};
/**
* Deletes a file from the filesystem. This function takes a file object, constructs the full path, and
* verifies the path's validity before deleting the file. If the path is invalid, an error is thrown.
*
* @param {ServerRequest} req - The request object from Express.
* @param {MongoFile} file - The file object to be deleted. It should have a `filepath` property that is
* a string representing the path of the file relative to the publicPath.
*
* @returns {Promise<void>}
* A promise that resolves when the file has been successfully deleted, or throws an error if the
* file path is invalid or if there is an error in deletion.
*/
const deleteLocalFile = async (req, file) => {
const appConfig = req.config;
const { publicPath, uploads } = appConfig.paths;
/** Filepath stripped of query parameters (e.g., ?manual=true) */
const cleanFilepath = file.filepath.split('?')[0];
if (file.embedded && process.env.RAG_API_URL) {
const jwtToken = generateShortLivedToken(req.user.id);
axios.delete(`${process.env.RAG_API_URL}/documents`, {
headers: {
Authorization: `Bearer ${jwtToken}`,
'Content-Type': 'application/json',
accept: 'application/json',
},
data: [file.file_id],
});
}
if (cleanFilepath.startsWith(`/uploads/${req.user.id}`)) {
const userUploadDir = path.join(uploads, req.user.id);
const basePath = cleanFilepath.split(`/uploads/${req.user.id}/`)[1];
if (!basePath) {
throw new Error(`Invalid file path: ${cleanFilepath}`);
}
const filepath = path.join(userUploadDir, basePath);
const rel = path.relative(userUploadDir, filepath);
if (rel.startsWith('..') || path.isAbsolute(rel) || rel.includes(`..${path.sep}`)) {
throw new Error(`Invalid file path: ${cleanFilepath}`);
}
await unlinkFile(filepath);
return;
}
const parts = cleanFilepath.split(path.sep);
const subfolder = parts[1];
if (!subfolder && parts[0] === EModelEndpoint.agents) {
logger.warn(`Agent File ${file.file_id} is missing filepath, may have been deleted already`);
return;
}
const filepath = path.join(publicPath, cleanFilepath);
if (!isValidPath(req, publicPath, subfolder, filepath)) {
throw new Error('Invalid file path');
}
await unlinkFile(filepath);
};
/**
* Uploads a file to the specified upload directory.
*
* @param {Object} params - The params object.
* @param {ServerRequest} params.req - The request object from Express. It should have a `user` property with an `id` representing the user
* @param {Express.Multer.File} params.file - The file object, which is part of the request. The file object should
* have a `path` property that points to the location of the uploaded file.
* @param {string} params.file_id - The file ID.
*
* @returns {Promise<{ filepath: string, bytes: number }>}
* A promise that resolves to an object containing:
* - filepath: The path where the file is saved.
* - bytes: The size of the file in bytes.
*/
async function uploadLocalFile({ req, file, file_id }) {
const appConfig = req.config;
const inputFilePath = file.path;
const inputBuffer = await fs.promises.readFile(inputFilePath);
const bytes = Buffer.byteLength(inputBuffer);
const { uploads } = appConfig.paths;
const userPath = path.join(uploads, req.user.id);
if (!fs.existsSync(userPath)) {
fs.mkdirSync(userPath, { recursive: true });
}
const fileName = `${file_id}__${path.basename(inputFilePath)}`;
const newPath = path.join(userPath, fileName);
await fs.promises.writeFile(newPath, inputBuffer);
const filepath = path.posix.join('/', 'uploads', req.user.id, path.basename(newPath));
let height, width;
if (file.mimetype && file.mimetype.startsWith('image/')) {
try {
const { width: imgWidth, height: imgHeight } = await resizeImageBuffer(inputBuffer, 'high');
height = imgHeight;
width = imgWidth;
} catch (error) {
logger.warn('[uploadLocalFile] Could not get image dimensions:', error.message);
}
}
return { filepath, bytes, height, width };
}
/**
* Retrieves a readable stream for a file from local storage.
*
* @param {ServerRequest} req - The request object from Express
* @param {string} filepath - The filepath.
* @returns {ReadableStream} A readable stream of the file.
*/
async function getLocalFileStream(req, filepath) {
try {
const appConfig = req.config;
if (filepath.includes('/uploads/')) {
const basePath = filepath.split('/uploads/')[1];
if (!basePath) {
logger.warn(`Invalid base path: ${filepath}`);
throw new Error(`Invalid file path: ${filepath}`);
}
const fullPath = path.join(appConfig.paths.uploads, basePath);
const uploadsDir = appConfig.paths.uploads;
const rel = path.relative(uploadsDir, fullPath);
if (rel.startsWith('..') || path.isAbsolute(rel) || rel.includes(`..${path.sep}`)) {
logger.warn(`Invalid relative file path: ${filepath}`);
throw new Error(`Invalid file path: ${filepath}`);
}
return fs.createReadStream(fullPath);
} else if (filepath.includes('/images/')) {
const basePath = filepath.split('/images/')[1];
if (!basePath) {
logger.warn(`Invalid base path: ${filepath}`);
throw new Error(`Invalid file path: ${filepath}`);
}
const fullPath = path.join(appConfig.paths.imageOutput, basePath);
const publicDir = appConfig.paths.imageOutput;
const rel = path.relative(publicDir, fullPath);
if (rel.startsWith('..') || path.isAbsolute(rel) || rel.includes(`..${path.sep}`)) {
logger.warn(`Invalid relative file path: ${filepath}`);
throw new Error(`Invalid file path: ${filepath}`);
}
return fs.createReadStream(fullPath);
}
return fs.createReadStream(filepath);
} catch (error) {
logger.error('Error getting local file stream:', error);
throw error;
}
}
module.exports = {
saveLocalFile,
saveLocalImage,
saveLocalBuffer,
saveFileFromURL,
getLocalFileURL,
deleteLocalFile,
uploadLocalFile,
getLocalFileStream,
};