LibreChat/api/models/File.js
Danny Avila ded3cd8876
🔍 feat: Mistral OCR API / Upload Files as Text (#6274)
* refactor: move `loadAuthValues` to `~/services/Tools/credentials`

* feat: add createAxiosInstance function to configure axios with proxy support

* WIP: First pass mistral ocr

* refactor: replace getConvoFiles with getToolFiles for improved file retrieval logic

* refactor: improve document formatting in encodeAndFormat function

* refactor: remove unused resendFiles parameter from buildOptions function (this option comes from the agent config)

* fix: update getFiles call to include files with `text` property as well

* refactor: move file handling to `initializeAgentOptions`

* refactor: enhance addImageURLs method to handle OCR text and improve message formatting

* refactor: update message formatting to handle OCR text in various content types

* refactor: remove unused resendFiles property from compactAgentsSchema

* fix: add error handling for Mistral OCR document upload and logging

* refactor: integrate OCR capability into file upload options and configuration

* refactor: skip processing for text source files in delete request, as they are directly tied to database

* feat: add metadata field to ExtendedFile type and update PanelColumns and PanelTable components for localization and metadata handling

* fix: source icon styling

* wip: first pass, frontend file context agent resources

* refactor: add hover card with contextual information for File Context (OCR) in FileContext component

* feat: enhance file processing by integrating file retrieval for OCR resources in agent initialization

* feat: implement OCR config; fix: agent resource deletion for ocr files

* feat: enhance agent initialization by adding OCR capability check in resource priming

* ci: fix `~/config` module mock

* ci: add OCR property expectation in AppService tests

* refactor: simplify OCR config loading by removing environment variable extraction, to be done when OCR is actually performed

* ci: add unit test to ensure environment variable references are not parsed in OCR config

* refactor: disable base64 image inclusion in OCR request

* refactor: enhance OCR configuration handling by validating environment variables and providing defaults

* refactor: use file stream from disk for mistral ocr api
2025-03-10 17:23:46 -04:00

120 lines
4.1 KiB
JavaScript

const mongoose = require('mongoose');
const { fileSchema } = require('@librechat/data-schemas');
const File = mongoose.model('File', fileSchema);
/**
* Finds a file by its file_id with additional query options.
* @param {string} file_id - The unique identifier of the file.
* @param {object} options - Query options for filtering, projection, etc.
* @returns {Promise<IMongoFile>} A promise that resolves to the file document or null.
*/
const findFileById = async (file_id, options = {}) => {
return await File.findOne({ file_id, ...options }).lean();
};
/**
* Retrieves files matching a given filter, sorted by the most recently updated.
* @param {Object} filter - The filter criteria to apply.
* @param {Object} [_sortOptions] - Optional sort parameters.
* @param {Object|String} [selectFields={ text: 0 }] - Fields to include/exclude in the query results.
* Default excludes the 'text' field.
* @returns {Promise<Array<IMongoFile>>} A promise that resolves to an array of file documents.
*/
const getFiles = async (filter, _sortOptions, selectFields = { text: 0 }) => {
const sortOptions = { updatedAt: -1, ..._sortOptions };
return await File.find(filter).select(selectFields).sort(sortOptions).lean();
};
/**
* Creates a new file with a TTL of 1 hour.
* @param {IMongoFile} data - The file data to be created, must contain file_id.
* @param {boolean} disableTTL - Whether to disable the TTL.
* @returns {Promise<IMongoFile>} A promise that resolves to the created file document.
*/
const createFile = async (data, disableTTL) => {
const fileData = {
...data,
expiresAt: new Date(Date.now() + 3600 * 1000),
};
if (disableTTL) {
delete fileData.expiresAt;
}
return await File.findOneAndUpdate({ file_id: data.file_id }, fileData, {
new: true,
upsert: true,
}).lean();
};
/**
* Updates a file identified by file_id with new data and removes the TTL.
* @param {IMongoFile} data - The data to update, must contain file_id.
* @returns {Promise<IMongoFile>} A promise that resolves to the updated file document.
*/
const updateFile = async (data) => {
const { file_id, ...update } = data;
const updateOperation = {
$set: update,
$unset: { expiresAt: '' }, // Remove the expiresAt field to prevent TTL
};
return await File.findOneAndUpdate({ file_id }, updateOperation, { new: true }).lean();
};
/**
* Increments the usage of a file identified by file_id.
* @param {IMongoFile} data - The data to update, must contain file_id and the increment value for usage.
* @returns {Promise<IMongoFile>} A promise that resolves to the updated file document.
*/
const updateFileUsage = async (data) => {
const { file_id, inc = 1 } = data;
const updateOperation = {
$inc: { usage: inc },
$unset: { expiresAt: '', temp_file_id: '' },
};
return await File.findOneAndUpdate({ file_id }, updateOperation, { new: true }).lean();
};
/**
* Deletes a file identified by file_id.
* @param {string} file_id - The unique identifier of the file to delete.
* @returns {Promise<IMongoFile>} A promise that resolves to the deleted file document or null.
*/
const deleteFile = async (file_id) => {
return await File.findOneAndDelete({ file_id }).lean();
};
/**
* Deletes a file identified by a filter.
* @param {object} filter - The filter criteria to apply.
* @returns {Promise<IMongoFile>} A promise that resolves to the deleted file document or null.
*/
const deleteFileByFilter = async (filter) => {
return await File.findOneAndDelete(filter).lean();
};
/**
* Deletes multiple files identified by an array of file_ids.
* @param {Array<string>} file_ids - The unique identifiers of the files to delete.
* @returns {Promise<Object>} A promise that resolves to the result of the deletion operation.
*/
const deleteFiles = async (file_ids, user) => {
let deleteQuery = { file_id: { $in: file_ids } };
if (user) {
deleteQuery = { user: user };
}
return await File.deleteMany(deleteQuery);
};
module.exports = {
File,
findFileById,
getFiles,
createFile,
updateFile,
updateFileUsage,
deleteFile,
deleteFiles,
deleteFileByFilter,
};