📎 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>

packages/api/src/utils/index.ts

@@ -11,6 +11,7 @@ export * from './llm';
 export * from './math';
 export * from './openid';
 export * from './tempChatRetention';
+export * from './text';
 export { default as Tokenizer } from './tokenizer';
 export * from './yaml';
 export * from './http';

packages/api/src/utils/llm.test.ts

@@ -7,6 +7,7 @@ describe('extractLibreChatParams', () => {
     expect(result.resendFiles).toBe(true);
     expect(result.promptPrefix).toBeUndefined();
     expect(result.maxContextTokens).toBeUndefined();
+    expect(result.fileTokenLimit).toBeUndefined();
     expect(result.modelLabel).toBeUndefined();
     expect(result.modelOptions).toEqual({});
   });
@@ -17,6 +18,7 @@ describe('extractLibreChatParams', () => {
     expect(result.resendFiles).toBe(true);
     expect(result.promptPrefix).toBeUndefined();
     expect(result.maxContextTokens).toBeUndefined();
+    expect(result.fileTokenLimit).toBeUndefined();
     expect(result.modelLabel).toBeUndefined();
     expect(result.modelOptions).toEqual({});
   });
@@ -26,6 +28,7 @@ describe('extractLibreChatParams', () => {
       resendFiles: false,
       promptPrefix: 'You are a helpful assistant',
       maxContextTokens: 4096,
+      fileTokenLimit: 50000,
       modelLabel: 'GPT-4',
       model: 'gpt-4',
       temperature: 0.7,
@@ -37,6 +40,7 @@ describe('extractLibreChatParams', () => {
     expect(result.resendFiles).toBe(false);
     expect(result.promptPrefix).toBe('You are a helpful assistant');
     expect(result.maxContextTokens).toBe(4096);
+    expect(result.fileTokenLimit).toBe(50000);
     expect(result.modelLabel).toBe('GPT-4');
     expect(result.modelOptions).toEqual({
       model: 'gpt-4',
@@ -50,6 +54,7 @@ describe('extractLibreChatParams', () => {
       resendFiles: true,
       promptPrefix: null,
       maxContextTokens: 2048,
+      fileTokenLimit: undefined,
       modelLabel: null,
       model: 'claude-3',
     };
@@ -59,6 +64,7 @@ describe('extractLibreChatParams', () => {
     expect(result.resendFiles).toBe(true);
     expect(result.promptPrefix).toBeNull();
     expect(result.maxContextTokens).toBe(2048);
+    expect(result.fileTokenLimit).toBeUndefined();
     expect(result.modelLabel).toBeNull();
     expect(result.modelOptions).toEqual({
       model: 'claude-3',
@@ -77,6 +83,7 @@ describe('extractLibreChatParams', () => {
     expect(result.resendFiles).toBe(true); // Should use default
     expect(result.promptPrefix).toBe('Test prefix');
     expect(result.maxContextTokens).toBeUndefined();
+    expect(result.fileTokenLimit).toBeUndefined();
     expect(result.modelLabel).toBeUndefined();
     expect(result.modelOptions).toEqual({
       model: 'gpt-3.5-turbo',
@@ -90,6 +97,7 @@ describe('extractLibreChatParams', () => {
     expect(result.resendFiles).toBe(true); // Should use default
     expect(result.promptPrefix).toBeUndefined();
     expect(result.maxContextTokens).toBeUndefined();
+    expect(result.fileTokenLimit).toBeUndefined();
     expect(result.modelLabel).toBeUndefined();
     expect(result.modelOptions).toEqual({});
   });
@@ -99,6 +107,7 @@ describe('extractLibreChatParams', () => {
       resendFiles: false,
       promptPrefix: 'Custom prompt',
       maxContextTokens: 8192,
+      fileTokenLimit: 25000,
       modelLabel: 'Custom Model',
       // Model options
       model: 'gpt-4',
@@ -117,6 +126,7 @@ describe('extractLibreChatParams', () => {
     expect(result.resendFiles).toBe(false);
     expect(result.promptPrefix).toBe('Custom prompt');
     expect(result.maxContextTokens).toBe(8192);
+    expect(result.fileTokenLimit).toBe(25000);
     expect(result.modelLabel).toBe('Custom Model');
 
     // Model options should include everything else

packages/api/src/utils/llm.ts

@@ -8,6 +8,7 @@ type LibreChatParams = {
   resendFiles: boolean;
   promptPrefix?: string | null;
   maxContextTokens?: number;
+  fileTokenLimit?: number;
   modelLabel?: string | null;
 };
 
@@ -32,6 +33,7 @@ export function extractLibreChatParams(
     (librechat.resendFiles.default as boolean);
   const promptPrefix = (delete modelOptions.promptPrefix, options.promptPrefix);
   const maxContextTokens = (delete modelOptions.maxContextTokens, options.maxContextTokens);
+  const fileTokenLimit = (delete modelOptions.fileTokenLimit, options.fileTokenLimit);
   const modelLabel = (delete modelOptions.modelLabel, options.modelLabel);
 
   return {
@@ -40,6 +42,7 @@ export function extractLibreChatParams(
       LibreChatKeys
     >,
     maxContextTokens,
+    fileTokenLimit,
     promptPrefix,
     resendFiles,
     modelLabel,

packages/api/src/utils/text.ts

@@ -0,0 +1,65 @@
+import { logger } from '@librechat/data-schemas';
+
+/**
+ * Processes text content by counting tokens and truncating if it exceeds the specified limit.
+ * @param text - The text content to process
+ * @param tokenLimit - The maximum number of tokens allowed
+ * @param tokenCountFn - Function to count tokens
+ * @returns Promise resolving to object with processed text, token count, and truncation status
+ */
+export async function processTextWithTokenLimit({
+  text,
+  tokenLimit,
+  tokenCountFn,
+}: {
+  text: string;
+  tokenLimit: number;
+  tokenCountFn: (text: string) => number;
+}): Promise<{ text: string; tokenCount: number; wasTruncated: boolean }> {
+  const originalTokenCount = await tokenCountFn(text);
+
+  if (originalTokenCount <= tokenLimit) {
+    return {
+      text,
+      tokenCount: originalTokenCount,
+      wasTruncated: false,
+    };
+  }
+
+  /**
+   * Doing binary search here to find the truncation point efficiently
+   * (May be a better way to go about this)
+   */
+  let low = 0;
+  let high = text.length;
+  let bestText = '';
+
+  logger.debug(
+    `[textTokenLimiter] Text content exceeds token limit: ${originalTokenCount} > ${tokenLimit}, truncating...`,
+  );
+
+  while (low <= high) {
+    const mid = Math.floor((low + high) / 2);
+    const truncatedText = text.substring(0, mid);
+    const tokenCount = await tokenCountFn(truncatedText);
+
+    if (tokenCount <= tokenLimit) {
+      bestText = truncatedText;
+      low = mid + 1;
+    } else {
+      high = mid - 1;
+    }
+  }
+
+  const finalTokenCount = await tokenCountFn(bestText);
+
+  logger.warn(
+    `[textTokenLimiter] Text truncated from ${originalTokenCount} to ${finalTokenCount} tokens (limit: ${tokenLimit})`,
+  );
+
+  return {
+    text: bestText,
+    tokenCount: finalTokenCount,
+    wasTruncated: true,
+  };
+}