LibreChat/api/server/services/Files/VectorDB/crud.js
lia-by-librechat[bot] a51c45bbf3
🌳 fix: Preserve Primary Files Until Secondary Cleanup Succeeds (#17228)
* fix: Preserve primary files until secondary cleanup succeeds

* test: Use a flat deletion-strategy lookup

* fix: Preserve erasure retries and reconcile removed embeddings

* test: Match deletion regression formatting

* fix: Preserve search intent after vector cleanup

* fix: Repair retained project search files before tool execution

* fix: Normalize Retained Project File Runtime Types

* test: Use the Storage Source Enum in Project Repair Coverage

* fix: Confirm Secondary Cleanup and Preserve Repair Policy

* test: Correct Repair Fixture Types and Cleanup Retry Assertions

* fix: Reconcile Code Copies Compatibly and Charge Shared File Budgets

* fix: Reserve Admitted File Budgets Before Deferred Screening

* fix: Retain Concurrent File Copies and Scope Cleanup by Tenant

* fix: Bound Erasure File Checks and Correct Cleanup Fixtures

* fix: Preserve Provider-Only Assistant File Deletion

* fix: Reconcile Primary Vector Deletions Before Finalization

* fix: Finalize Successful Files in Mixed Cleanup Batches

* test: Load Real File Finalizer in Cleanup Integration Tests

* fix: Preserve Project Routing MIME and Fence File Storage Operations

* fix: Validate Provisioning Principal and Type Project Repair Fixtures

* fix: Recover Provisioning Claims and Retain Uncertain Storage Outcomes

* fix: Normalize File Recovery Results and Reconcile Transport Attempts

* test: Preserve Deployment Routes in Host Provisioning Fixtures

* fix: Recover Deletion Claims and Fence Generated Output Writes

* fix: Preserve Generated Output Commit Snapshots

* test: Use Persisted Owner Type in Generated File Fixture

* test: Type Generated Output Fixture with Its Commit Contract

* fix: Preserve Publication Error Handling and Cleanup Test Boundaries

---------

Co-authored-by: Lia <lia@librechat.ai>
2026-10-23 07:00:20 +02:00

105 lines
3.2 KiB
JavaScript

const fs = require('fs');
const axios = require('axios');
const FormData = require('form-data');
const { logger } = require('@librechat/data-schemas');
const { FileSources } = require('librechat-data-provider');
const {
logAxiosError,
generateShortLivedToken,
createVectorFileDeleter,
dispatchFileStorageOperation,
} = require('@librechat/api');
const deleteVectors = (req, file) =>
createVectorFileDeleter({
baseUrl: process.env.RAG_API_URL,
httpClient: axios,
generateToken: generateShortLivedToken,
})(req, file);
/**
* Uploads a file to the configured Vector database
*
* @param {Object} params - The params object.
* @param {Object} 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.
* @param {string} [params.entity_id] - The entity ID for shared resources.
* @param {Object} [params.storageMetadata] - Storage metadata for dual storage pattern.
*
* @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 uploadVectors({
req,
file,
file_id,
entity_id,
storageMetadata,
signal,
onUploadStart,
}) {
if (!process.env.RAG_API_URL) {
throw new Error('RAG_API_URL not defined');
}
try {
const jwtToken = generateShortLivedToken(req.user.id);
const formData = new FormData();
formData.append('file_id', file_id);
formData.append('file', fs.createReadStream(file.path));
if (entity_id != null && entity_id) {
formData.append('entity_id', entity_id);
}
// Include storage metadata for RAG API to store with embeddings
if (storageMetadata) {
formData.append('storage_metadata', JSON.stringify(storageMetadata));
}
const formHeaders = formData.getHeaders();
const response = await dispatchFileStorageOperation(onUploadStart, () =>
axios.post(`${process.env.RAG_API_URL}/embed`, formData, {
...(signal ? { signal } : {}),
headers: {
Authorization: `Bearer ${jwtToken}`,
accept: 'application/json',
...formHeaders,
},
}),
);
const responseData = response.data;
logger.debug('Response from embedding file', responseData);
if (responseData.known_type === false) {
throw new Error(`File embedding failed. The filetype ${file.mimetype} is not supported`);
}
if (!responseData.status) {
throw new Error('File embedding failed.');
}
return {
bytes: file.size,
filename: file.originalname,
filepath: FileSources.vectordb,
embedded: Boolean(responseData.known_type),
};
} catch (error) {
logAxiosError({
error,
message: 'Error uploading vectors',
});
throw new Error(error.message || 'An error occurred during file upload.', { cause: error });
}
}
module.exports = {
deleteVectors,
uploadVectors,
};