LibreChat/packages/data-provider/src/file-config.ts
Danny Avila 48f6f8f2f8
📎 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

406 lines
11 KiB
TypeScript

import { z } from 'zod';
import { EModelEndpoint } from './schemas';
import type { EndpointFileConfig, FileConfig } from './types/files';
export const supportsFiles = {
[EModelEndpoint.openAI]: true,
[EModelEndpoint.google]: true,
[EModelEndpoint.assistants]: true,
[EModelEndpoint.azureAssistants]: true,
[EModelEndpoint.agents]: true,
[EModelEndpoint.azureOpenAI]: true,
[EModelEndpoint.anthropic]: true,
[EModelEndpoint.custom]: true,
[EModelEndpoint.bedrock]: true,
};
export const excelFileTypes = [
'application/vnd.ms-excel',
'application/msexcel',
'application/x-msexcel',
'application/x-ms-excel',
'application/x-excel',
'application/x-dos_ms_excel',
'application/xls',
'application/x-xls',
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
];
export const fullMimeTypesList = [
'text/x-c',
'text/x-c++',
'application/csv',
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'text/html',
'text/x-java',
'application/json',
'text/markdown',
'application/pdf',
'text/x-php',
'application/vnd.openxmlformats-officedocument.presentationml.presentation',
'text/x-python',
'text/x-script.python',
'text/x-ruby',
'text/x-tex',
'text/plain',
'text/css',
'text/vtt',
'image/jpeg',
'text/javascript',
'image/gif',
'image/png',
'image/heic',
'image/heif',
'application/x-tar',
'application/typescript',
'application/xml',
'application/zip',
'image/svg',
'image/svg+xml',
...excelFileTypes,
];
export const codeInterpreterMimeTypesList = [
'text/x-c',
'text/x-c++',
'application/csv',
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'text/html',
'text/x-java',
'application/json',
'text/markdown',
'application/pdf',
'text/x-php',
'application/vnd.openxmlformats-officedocument.presentationml.presentation',
'text/x-python',
'text/x-script.python',
'text/x-ruby',
'text/x-tex',
'text/plain',
'text/css',
'image/jpeg',
'text/javascript',
'image/gif',
'image/png',
'image/heic',
'image/heif',
'application/x-tar',
'application/typescript',
'application/xml',
'application/zip',
...excelFileTypes,
];
export const retrievalMimeTypesList = [
'text/x-c',
'text/x-c++',
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'text/html',
'text/x-java',
'application/json',
'text/markdown',
'application/pdf',
'text/x-php',
'application/vnd.openxmlformats-officedocument.presentationml.presentation',
'text/x-python',
'text/x-script.python',
'text/x-ruby',
'text/x-tex',
'text/plain',
];
export const imageExtRegex = /\.(jpg|jpeg|png|gif|webp|heic|heif)$/i;
export const excelMimeTypes =
/^application\/(vnd\.ms-excel|msexcel|x-msexcel|x-ms-excel|x-excel|x-dos_ms_excel|xls|x-xls|vnd\.openxmlformats-officedocument\.spreadsheetml\.sheet)$/;
export const textMimeTypes =
/^(text\/(x-c|x-csharp|tab-separated-values|x-c\+\+|x-h|x-java|html|markdown|x-php|x-python|x-script\.python|x-ruby|x-tex|plain|css|vtt|javascript|csv))$/;
export const applicationMimeTypes =
/^(application\/(epub\+zip|csv|json|pdf|x-tar|typescript|vnd\.openxmlformats-officedocument\.(wordprocessingml\.document|presentationml\.presentation|spreadsheetml\.sheet)|xml|zip))$/;
export const imageMimeTypes = /^image\/(jpeg|gif|png|webp|heic|heif)$/;
export const audioMimeTypes =
/^audio\/(mp3|mpeg|mpeg3|wav|wave|x-wav|ogg|vorbis|mp4|x-m4a|flac|x-flac|webm)$/;
export const defaultOCRMimeTypes = [
imageMimeTypes,
/^application\/pdf$/,
/^application\/vnd\.openxmlformats-officedocument\.(wordprocessingml\.document|presentationml\.presentation|spreadsheetml\.sheet)$/,
/^application\/vnd\.ms-(word|powerpoint|excel)$/,
/^application\/epub\+zip$/,
];
export const defaultTextMimeTypes = [textMimeTypes];
export const defaultSTTMimeTypes = [audioMimeTypes];
export const supportedMimeTypes = [
textMimeTypes,
excelMimeTypes,
applicationMimeTypes,
imageMimeTypes,
audioMimeTypes,
/** Supported by LC Code Interpreter PAI */
/^image\/(svg|svg\+xml)$/,
];
export const codeInterpreterMimeTypes = [
textMimeTypes,
excelMimeTypes,
applicationMimeTypes,
imageMimeTypes,
];
export const codeTypeMapping: { [key: string]: string } = {
c: 'text/x-c',
cs: 'text/x-csharp',
cpp: 'text/x-c++',
h: 'text/x-h',
md: 'text/markdown',
php: 'text/x-php',
py: 'text/x-python',
rb: 'text/x-ruby',
tex: 'text/x-tex',
js: 'text/javascript',
sh: 'application/x-sh',
ts: 'application/typescript',
tar: 'application/x-tar',
zip: 'application/zip',
yml: 'application/x-yaml',
yaml: 'application/x-yaml',
log: 'text/plain',
tsv: 'text/tab-separated-values',
};
export const retrievalMimeTypes = [
/^(text\/(x-c|x-c\+\+|x-h|html|x-java|markdown|x-php|x-python|x-script\.python|x-ruby|x-tex|plain|vtt|xml))$/,
/^(application\/(json|pdf|vnd\.openxmlformats-officedocument\.(wordprocessingml\.document|presentationml\.presentation)))$/,
];
export const megabyte = 1024 * 1024;
/** Helper function to get megabytes value */
export const mbToBytes = (mb: number): number => mb * megabyte;
const defaultSizeLimit = mbToBytes(512);
const defaultTokenLimit = 100000;
const assistantsFileConfig = {
fileLimit: 10,
fileSizeLimit: defaultSizeLimit,
totalSizeLimit: defaultSizeLimit,
supportedMimeTypes,
disabled: false,
};
export const fileConfig = {
endpoints: {
[EModelEndpoint.assistants]: assistantsFileConfig,
[EModelEndpoint.azureAssistants]: assistantsFileConfig,
[EModelEndpoint.agents]: assistantsFileConfig,
default: {
fileLimit: 10,
fileSizeLimit: defaultSizeLimit,
totalSizeLimit: defaultSizeLimit,
supportedMimeTypes,
disabled: false,
},
},
serverFileSizeLimit: defaultSizeLimit,
avatarSizeLimit: mbToBytes(2),
fileTokenLimit: defaultTokenLimit,
clientImageResize: {
enabled: false,
maxWidth: 1900,
maxHeight: 1900,
quality: 0.92,
},
ocr: {
supportedMimeTypes: defaultOCRMimeTypes,
},
text: {
supportedMimeTypes: defaultTextMimeTypes,
},
stt: {
supportedMimeTypes: defaultSTTMimeTypes,
},
checkType: function (fileType: string, supportedTypes: RegExp[] = supportedMimeTypes) {
return supportedTypes.some((regex) => regex.test(fileType));
},
};
const supportedMimeTypesSchema = z
.array(z.any())
.optional()
.refine(
(mimeTypes) => {
if (!mimeTypes) {
return true;
}
return mimeTypes.every(
(mimeType) => mimeType instanceof RegExp || typeof mimeType === 'string',
);
},
{
message: 'Each mimeType must be a string or a RegExp object.',
},
);
export const endpointFileConfigSchema = z.object({
disabled: z.boolean().optional(),
fileLimit: z.number().min(0).optional(),
fileSizeLimit: z.number().min(0).optional(),
totalSizeLimit: z.number().min(0).optional(),
supportedMimeTypes: supportedMimeTypesSchema.optional(),
});
export const fileConfigSchema = z.object({
endpoints: z.record(endpointFileConfigSchema).optional(),
serverFileSizeLimit: z.number().min(0).optional(),
avatarSizeLimit: z.number().min(0).optional(),
fileTokenLimit: z.number().min(0).optional(),
imageGeneration: z
.object({
percentage: z.number().min(0).max(100).optional(),
px: z.number().min(0).optional(),
})
.optional(),
clientImageResize: z
.object({
enabled: z.boolean().optional(),
maxWidth: z.number().min(0).optional(),
maxHeight: z.number().min(0).optional(),
quality: z.number().min(0).max(1).optional(),
})
.optional(),
ocr: z
.object({
supportedMimeTypes: supportedMimeTypesSchema.optional(),
})
.optional(),
text: z
.object({
supportedMimeTypes: supportedMimeTypesSchema.optional(),
})
.optional(),
});
/** Helper function to safely convert string patterns to RegExp objects */
export const convertStringsToRegex = (patterns: string[]): RegExp[] =>
patterns.reduce((acc: RegExp[], pattern) => {
try {
const regex = new RegExp(pattern);
acc.push(regex);
} catch (error) {
console.error(`Invalid regex pattern "${pattern}" skipped.`, error);
}
return acc;
}, []);
export function mergeFileConfig(dynamic: z.infer<typeof fileConfigSchema> | undefined): FileConfig {
const mergedConfig: FileConfig = {
...fileConfig,
ocr: {
...fileConfig.ocr,
supportedMimeTypes: fileConfig.ocr?.supportedMimeTypes || [],
},
text: {
...fileConfig.text,
supportedMimeTypes: fileConfig.text?.supportedMimeTypes || [],
},
stt: {
...fileConfig.stt,
supportedMimeTypes: fileConfig.stt?.supportedMimeTypes || [],
},
};
if (!dynamic) {
return mergedConfig;
}
if (dynamic.serverFileSizeLimit !== undefined) {
mergedConfig.serverFileSizeLimit = mbToBytes(dynamic.serverFileSizeLimit);
}
if (dynamic.avatarSizeLimit !== undefined) {
mergedConfig.avatarSizeLimit = mbToBytes(dynamic.avatarSizeLimit);
}
if (dynamic.fileTokenLimit !== undefined) {
mergedConfig.fileTokenLimit = dynamic.fileTokenLimit;
}
// Merge clientImageResize configuration
if (dynamic.clientImageResize !== undefined) {
mergedConfig.clientImageResize = {
...mergedConfig.clientImageResize,
...dynamic.clientImageResize,
};
}
if (dynamic.ocr !== undefined) {
mergedConfig.ocr = {
...mergedConfig.ocr,
...dynamic.ocr,
};
if (dynamic.ocr.supportedMimeTypes) {
mergedConfig.ocr.supportedMimeTypes = convertStringsToRegex(dynamic.ocr.supportedMimeTypes);
}
}
if (dynamic.text !== undefined) {
mergedConfig.text = {
...mergedConfig.text,
...dynamic.text,
};
if (dynamic.text.supportedMimeTypes) {
mergedConfig.text.supportedMimeTypes = convertStringsToRegex(dynamic.text.supportedMimeTypes);
}
}
if (!dynamic.endpoints) {
return mergedConfig;
}
for (const key in dynamic.endpoints) {
const dynamicEndpoint = (dynamic.endpoints as Record<string, EndpointFileConfig>)[key];
if (!mergedConfig.endpoints[key]) {
mergedConfig.endpoints[key] = {};
}
const mergedEndpoint = mergedConfig.endpoints[key];
if (dynamicEndpoint.disabled === true) {
mergedEndpoint.disabled = true;
mergedEndpoint.fileLimit = 0;
mergedEndpoint.fileSizeLimit = 0;
mergedEndpoint.totalSizeLimit = 0;
mergedEndpoint.supportedMimeTypes = [];
continue;
}
if (dynamicEndpoint.fileSizeLimit !== undefined) {
mergedEndpoint.fileSizeLimit = mbToBytes(dynamicEndpoint.fileSizeLimit);
}
if (dynamicEndpoint.totalSizeLimit !== undefined) {
mergedEndpoint.totalSizeLimit = mbToBytes(dynamicEndpoint.totalSizeLimit);
}
const configKeys = ['fileLimit'] as const;
configKeys.forEach((field) => {
if (dynamicEndpoint[field] !== undefined) {
mergedEndpoint[field] = dynamicEndpoint[field];
}
});
if (dynamicEndpoint.supportedMimeTypes) {
mergedEndpoint.supportedMimeTypes = convertStringsToRegex(
dynamicEndpoint.supportedMimeTypes as unknown as string[],
);
}
}
return mergedConfig;
}