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

114 lines
3.4 KiB
TypeScript
Raw Normal View History

📎 feat: Upload as Text Support for Plaintext, STT, RAG, and Token Limits (#8868) * 🪶 feat: Add Support for Uploading Plaintext Files feat: delineate between OCR and text handling in fileConfig field of config file - also adds support for passing in mimetypes as just plain file extensions feat: add showLabel bool to support future synthetic component DynamicDropdownInput feat: add new combination dropdown-input component in params panel to support file type token limits refactor: move hovercard to side to align with other hovercards chore: clean up autogenerated comments feat: add delineation to file upload path between text and ocr configured filetypes feat: add token limit checks during file upload refactor: move textParsing out of ocrEnabled logic refactor: clean up types for filetype config refactor: finish decoupling DynamicDropdownInput from fileTokenLimits fix: move image token cost function into file to fix circular dependency causing unittest to fail and remove unused var for linter chore: remove out of scope code following review refactor: make fileTokenLimit conform to existing styles chore: remove unused localization string chore: undo changes to DynamicInput and other strays feat: add fileTokenLimit to all provider config panels fix: move textParsing back into ocr tool_resource block for now so that it doesn't interfere with other upload types * 📤 feat: Add RAG API Endpoint Support for Text Parsing (#8849) * feat: implement RAG API integration for text parsing with fallback to native parsing * chore: remove TODO now that placeholder and fllback are implemented * ✈️ refactor: Migrate Text Parsing to TS (#8892) * refactor: move generateShortLivedToken to packages/api * refactor: move textParsing logic into packages/api * refactor: reduce nesting and dry code with createTextFile * fix: add proper source handling * fix: mock new parseText and parseTextNative functions in jest file * ci: add test coverage for textParser * 💬 feat: Add Audio File Support to Upload as Text (#8893) * feat: add STT support for Upload as Text * refactor: move processAudioFile to packages/api * refactor: move textParsing from utils to files * fix: remove audio/mp3 from unsupported mimetypes test since it is now supported * ✂️ feat: Configurable File Token Limits and Truncation (#8911) * feat: add configurable fileTokenLimit default value * fix: add stt to fileConfig merge logic * fix: add fileTokenLimit to mergeFileConfig logic so configurable value is actually respected from yaml * feat: add token limiting to parsed text files * fix: add extraction logic and update tests so fileTokenLimit isnt sent to LLM providers * fix: address comments * refactor: rename textTokenLimiter.ts to text.ts * chore: update form-data package to address CVE-2025-7783 and update package-lock * feat: use default supported mime types for ocr on frontend file validation * fix: should be using logger.debug not console.debug * fix: mock existsSync in text.spec.ts * fix: mock logger rather than every one of its function calls * fix: reorganize imports and streamline file upload processing logic * refactor: update createTextFile function to use destructured parameters and improve readability * chore: update file validation to use EToolResources for improved type safety * chore: update import path for types in audio processing module * fix: update file configuration access and replace console.debug with logger.debug for improved logging --------- Co-authored-by: Dustin Healy <dustinhealy1@gmail.com> Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
2025-08-27 03:44:39 -04:00
import fs from 'fs';
import axios from 'axios';
import FormData from 'form-data';
import { logger } from '@librechat/data-schemas';
import { FileSources } from 'librechat-data-provider';
import type { Request as ServerRequest } from 'express';
import { generateShortLivedToken } from '~/crypto/jwt';
/**
* Attempts to parse text using RAG API, falls back to native text parsing
* @param {Object} params - The parameters object
* @param {Express.Request} params.req - The Express request object
* @param {Express.Multer.File} params.file - The uploaded file
* @param {string} params.file_id - The file ID
* @returns {Promise<{text: string, bytes: number, source: string}>}
*/
export async function parseText({
req,
file,
file_id,
}: {
req: Pick<ServerRequest, 'user'> & {
user?: { id: string };
};
file: Express.Multer.File;
file_id: string;
}): Promise<{ text: string; bytes: number; source: string }> {
if (!process.env.RAG_API_URL) {
logger.debug('[parseText] RAG_API_URL not defined, falling back to native text parsing');
return parseTextNative(file);
}
if (!req.user?.id) {
logger.debug('[parseText] No user ID provided, falling back to native text parsing');
return parseTextNative(file);
}
try {
const healthResponse = await axios.get(`${process.env.RAG_API_URL}/health`, {
timeout: 5000,
});
if (healthResponse?.statusText !== 'OK' && healthResponse?.status !== 200) {
logger.debug('[parseText] RAG API health check failed, falling back to native parsing');
return parseTextNative(file);
}
} catch (healthError) {
logger.debug(
'[parseText] RAG API health check failed, falling back to native parsing',
healthError,
);
return parseTextNative(file);
}
try {
const jwtToken = generateShortLivedToken(req.user.id);
const formData = new FormData();
formData.append('file_id', file_id);
formData.append('file', fs.createReadStream(file.path));
const formHeaders = formData.getHeaders();
const response = await axios.post(`${process.env.RAG_API_URL}/text`, formData, {
headers: {
Authorization: `Bearer ${jwtToken}`,
accept: 'application/json',
...formHeaders,
},
timeout: 30000,
});
const responseData = response.data;
logger.debug('[parseText] Response from RAG API', responseData);
if (!('text' in responseData)) {
throw new Error('RAG API did not return parsed text');
}
return {
text: responseData.text,
bytes: Buffer.byteLength(responseData.text, 'utf8'),
source: FileSources.text,
};
} catch (error) {
logger.warn('[parseText] RAG API text parsing failed, falling back to native parsing', error);
return parseTextNative(file);
}
}
/**
* Native JavaScript text parsing fallback
* Simple text file reading - complex formats handled by RAG API
* @param {Express.Multer.File} file - The uploaded file
* @returns {{text: string, bytes: number, source: string}}
*/
export function parseTextNative(file: Express.Multer.File): {
text: string;
bytes: number;
source: string;
} {
try {
const text = fs.readFileSync(file.path, 'utf8');
const bytes = Buffer.byteLength(text, 'utf8');
return {
text,
bytes,
source: FileSources.text,
};
} catch (error) {
console.error('[parseTextNative] Failed to parse file:', error);
throw new Error(`Failed to read file as text: ${error}`);
}
}