LibreChat/api/server/services/Files/strategies.js
Danny Avila 5f2d1c5dc9
👁️ feat: Azure Mistral OCR Strategy (#7888)
* 👁️ feat: Add Azure Mistral OCR strategy and endpoint integration

This commit introduces a new OCR strategy named 'azure_mistral_ocr', allowing the use of a Mistral OCR endpoint deployed on Azure. The configuration, schemas, and file upload strategies have been updated to support this integration, enabling seamless OCR processing via Azure-hosted Mistral services.

* 🗑️ chore: Clean up .gitignore by removing commented-out uncommon directory name

* chore: remove unused vars

* refactor: Move createAxiosInstance to packages/api/utils and update imports

- Removed the createAxiosInstance function from the config module and relocated it to a new utils module for better organization.
- Updated import paths in relevant files to reflect the new location of createAxiosInstance.
- Added tests for createAxiosInstance to ensure proper functionality and proxy configuration handling.

* chore: move axios helpers to packages/api

- Added logAxiosError function to @librechat/api for centralized error logging.
- Updated imports across various files to use the new logAxiosError function.
- Removed the old axios.js utility file as it is no longer needed.

* chore: Update Jest moduleNameMapper for improved path resolution

- Added a new mapping for '~/' to resolve module paths in Jest configuration, enhancing import handling for the project.

* feat: Implement Mistral OCR API integration in TS

* chore: Update MistralOCR tests based on new imports

* fix: Enhance MistralOCR configuration handling and tests

- Introduced helper functions for resolving configuration values from environment variables or hardcoded settings.
- Updated the uploadMistralOCR and uploadAzureMistralOCR functions to utilize the new configuration resolution logic.
- Improved test cases to ensure correct behavior when mixing environment variables and hardcoded values.
- Mocked file upload and signed URL responses in tests to validate functionality without external dependencies.

* feat: Enhance MistralOCR functionality with improved configuration and error handling

- Introduced helper functions for loading authentication configuration and resolving values from environment variables.
- Updated uploadMistralOCR and uploadAzureMistralOCR functions to utilize the new configuration logic.
- Added utility functions for processing OCR results and creating error messages.
- Improved document type determination and result aggregation for better OCR processing.

* refactor: Reorganize OCR type imports in Mistral CRUD file

- Moved OCRResult, OCRResultPage, and OCRImage imports to a more logical grouping for better readability and maintainability.

* feat: Add file exports to API and create files index

* chore: Update OCR types for enhanced structure and clarity

- Redesigned OCRImage interface to include mandatory fields and improved naming conventions.
- Added PageDimensions interface for better representation of page metrics.
- Updated OCRResultPage to include dimensions and mandatory images array.
- Refined OCRResult to include document annotation and usage information.

* refactor: use TS counterpart of uploadOCR methods

* ci: Update MistralOCR tests to reflect new OCR result structure

* chore: Bump version of @librechat/api to 1.2.3 in package.json and package-lock.json

* chore: Update CONFIG_VERSION to 1.2.8

* chore: remove unused sendEvent function from config module (now imported from '@librechat/api')

* chore: remove MistralOCR service files and tests (now in '@librechat/api')

* ci: update logger import in ModelService tests to use @librechat/data-schemas

---------

Co-authored-by: arthurolivierfortin <arthurolivier.fortin@gmail.com>
2025-06-13 15:14:57 -04:00

254 lines
7.1 KiB
JavaScript

const { FileSources } = require('librechat-data-provider');
const { uploadMistralOCR, uploadAzureMistralOCR } = require('@librechat/api');
const {
getFirebaseURL,
prepareImageURL,
saveURLToFirebase,
deleteFirebaseFile,
saveBufferToFirebase,
uploadFileToFirebase,
uploadImageToFirebase,
processFirebaseAvatar,
getFirebaseFileStream,
} = require('./Firebase');
const {
uploadLocalFile,
getLocalFileURL,
saveFileFromURL,
saveLocalBuffer,
deleteLocalFile,
uploadLocalImage,
prepareImagesLocal,
processLocalAvatar,
getLocalFileStream,
} = require('./Local');
const {
getS3URL,
saveURLToS3,
saveBufferToS3,
getS3FileStream,
uploadImageToS3,
prepareImageURLS3,
deleteFileFromS3,
processS3Avatar,
uploadFileToS3,
} = require('./S3');
const {
saveBufferToAzure,
saveURLToAzure,
getAzureURL,
deleteFileFromAzure,
uploadFileToAzure,
getAzureFileStream,
uploadImageToAzure,
prepareAzureImageURL,
processAzureAvatar,
} = require('./Azure');
const { uploadOpenAIFile, deleteOpenAIFile, getOpenAIFileStream } = require('./OpenAI');
const { getCodeOutputDownloadStream, uploadCodeEnvFile } = require('./Code');
const { uploadVectors, deleteVectors } = require('./VectorDB');
/**
* Firebase Storage Strategy Functions
*
* */
const firebaseStrategy = () => ({
handleFileUpload: uploadFileToFirebase,
saveURL: saveURLToFirebase,
getFileURL: getFirebaseURL,
deleteFile: deleteFirebaseFile,
saveBuffer: saveBufferToFirebase,
prepareImagePayload: prepareImageURL,
processAvatar: processFirebaseAvatar,
handleImageUpload: uploadImageToFirebase,
getDownloadStream: getFirebaseFileStream,
});
/**
* Local Server Storage Strategy Functions
*
* */
const localStrategy = () => ({
handleFileUpload: uploadLocalFile,
saveURL: saveFileFromURL,
getFileURL: getLocalFileURL,
saveBuffer: saveLocalBuffer,
deleteFile: deleteLocalFile,
processAvatar: processLocalAvatar,
handleImageUpload: uploadLocalImage,
prepareImagePayload: prepareImagesLocal,
getDownloadStream: getLocalFileStream,
});
/**
* S3 Storage Strategy Functions
*
* */
const s3Strategy = () => ({
handleFileUpload: uploadFileToS3,
saveURL: saveURLToS3,
getFileURL: getS3URL,
deleteFile: deleteFileFromS3,
saveBuffer: saveBufferToS3,
prepareImagePayload: prepareImageURLS3,
processAvatar: processS3Avatar,
handleImageUpload: uploadImageToS3,
getDownloadStream: getS3FileStream,
});
/**
* Azure Blob Storage Strategy Functions
*
* */
const azureStrategy = () => ({
handleFileUpload: uploadFileToAzure,
saveURL: saveURLToAzure,
getFileURL: getAzureURL,
deleteFile: deleteFileFromAzure,
saveBuffer: saveBufferToAzure,
prepareImagePayload: prepareAzureImageURL,
processAvatar: processAzureAvatar,
handleImageUpload: uploadImageToAzure,
getDownloadStream: getAzureFileStream,
});
/**
* VectorDB Storage Strategy Functions
*
* */
const vectorStrategy = () => ({
/** @type {typeof saveFileFromURL | null} */
saveURL: null,
/** @type {typeof getLocalFileURL | null} */
getFileURL: null,
/** @type {typeof saveLocalBuffer | null} */
saveBuffer: null,
/** @type {typeof processLocalAvatar | null} */
processAvatar: null,
/** @type {typeof uploadLocalImage | null} */
handleImageUpload: null,
/** @type {typeof prepareImagesLocal | null} */
prepareImagePayload: null,
/** @type {typeof getLocalFileStream | null} */
getDownloadStream: null,
handleFileUpload: uploadVectors,
deleteFile: deleteVectors,
});
/**
* OpenAI Strategy Functions
*
* Note: null values mean that the strategy is not supported.
* */
const openAIStrategy = () => ({
/** @type {typeof saveFileFromURL | null} */
saveURL: null,
/** @type {typeof getLocalFileURL | null} */
getFileURL: null,
/** @type {typeof saveLocalBuffer | null} */
saveBuffer: null,
/** @type {typeof processLocalAvatar | null} */
processAvatar: null,
/** @type {typeof uploadLocalImage | null} */
handleImageUpload: null,
/** @type {typeof prepareImagesLocal | null} */
prepareImagePayload: null,
deleteFile: deleteOpenAIFile,
handleFileUpload: uploadOpenAIFile,
getDownloadStream: getOpenAIFileStream,
});
/**
* Code Output Strategy Functions
*
* Note: null values mean that the strategy is not supported.
* */
const codeOutputStrategy = () => ({
/** @type {typeof saveFileFromURL | null} */
saveURL: null,
/** @type {typeof getLocalFileURL | null} */
getFileURL: null,
/** @type {typeof saveLocalBuffer | null} */
saveBuffer: null,
/** @type {typeof processLocalAvatar | null} */
processAvatar: null,
/** @type {typeof uploadLocalImage | null} */
handleImageUpload: null,
/** @type {typeof prepareImagesLocal | null} */
prepareImagePayload: null,
/** @type {typeof deleteLocalFile | null} */
deleteFile: null,
handleFileUpload: uploadCodeEnvFile,
getDownloadStream: getCodeOutputDownloadStream,
});
const mistralOCRStrategy = () => ({
/** @type {typeof saveFileFromURL | null} */
saveURL: null,
/** @type {typeof getLocalFileURL | null} */
getFileURL: null,
/** @type {typeof saveLocalBuffer | null} */
saveBuffer: null,
/** @type {typeof processLocalAvatar | null} */
processAvatar: null,
/** @type {typeof uploadLocalImage | null} */
handleImageUpload: null,
/** @type {typeof prepareImagesLocal | null} */
prepareImagePayload: null,
/** @type {typeof deleteLocalFile | null} */
deleteFile: null,
/** @type {typeof getLocalFileStream | null} */
getDownloadStream: null,
handleFileUpload: uploadMistralOCR,
});
const azureMistralOCRStrategy = () => ({
/** @type {typeof saveFileFromURL | null} */
saveURL: null,
/** @type {typeof getLocalFileURL | null} */
getFileURL: null,
/** @type {typeof saveLocalBuffer | null} */
saveBuffer: null,
/** @type {typeof processLocalAvatar | null} */
processAvatar: null,
/** @type {typeof uploadLocalImage | null} */
handleImageUpload: null,
/** @type {typeof prepareImagesLocal | null} */
prepareImagePayload: null,
/** @type {typeof deleteLocalFile | null} */
deleteFile: null,
/** @type {typeof getLocalFileStream | null} */
getDownloadStream: null,
handleFileUpload: uploadAzureMistralOCR,
});
// Strategy Selector
const getStrategyFunctions = (fileSource) => {
if (fileSource === FileSources.firebase) {
return firebaseStrategy();
} else if (fileSource === FileSources.local) {
return localStrategy();
} else if (fileSource === FileSources.openai) {
return openAIStrategy();
} else if (fileSource === FileSources.azure) {
return openAIStrategy();
} else if (fileSource === FileSources.azure_blob) {
return azureStrategy();
} else if (fileSource === FileSources.vectordb) {
return vectorStrategy();
} else if (fileSource === FileSources.s3) {
return s3Strategy();
} else if (fileSource === FileSources.execute_code) {
return codeOutputStrategy();
} else if (fileSource === FileSources.mistral_ocr) {
return mistralOCRStrategy();
} else if (fileSource === FileSources.azure_mistral_ocr) {
return azureMistralOCRStrategy();
} else {
throw new Error('Invalid file source');
}
};
module.exports = {
getStrategyFunctions,
};