⚡ refactor: Optimize & Standardize Tokenizer Usage (#10777)

* refactor: Token Limit Processing with Enhanced Efficiency

- Added a new test suite for `processTextWithTokenLimit`, ensuring comprehensive coverage of various scenarios including under, at, and exceeding token limits.
- Refactored the `processTextWithTokenLimit` function to utilize a ratio-based estimation method, significantly reducing the number of token counting function calls compared to the previous binary search approach.
- Improved handling of edge cases and variable token density, ensuring accurate truncation and performance across diverse text inputs.
- Included direct comparisons with the old implementation to validate correctness and efficiency improvements.

* refactor: Remove Tokenizer Route and Related References

- Deleted the tokenizer route from the server and removed its references from the routes index and server files, streamlining the API structure.
- This change simplifies the routing configuration by eliminating unused endpoints.

* refactor: Migrate countTokens Utility to API Module

- Removed the local countTokens utility and integrated it into the @librechat/api module for centralized access.
- Updated various files to reference the new countTokens import from the API module, ensuring consistent usage across the application.
- Cleaned up unused references and imports related to the previous countTokens implementation.

* refactor: Centralize escapeRegExp Utility in API Module

- Moved the escapeRegExp function from local utility files to the @librechat/api module for consistent usage across the application.
- Updated imports in various files to reference the new centralized escapeRegExp function, ensuring cleaner code and reducing redundancy.
- Removed duplicate implementations of escapeRegExp from multiple files, streamlining the codebase.

* refactor: Enhance Token Counting Flexibility in Text Processing

- Updated the `processTextWithTokenLimit` function to accept both synchronous and asynchronous token counting functions, improving its versatility.
- Introduced a new `TokenCountFn` type to define the token counting function signature.
- Added comprehensive tests to validate the behavior of `processTextWithTokenLimit` with both sync and async token counting functions, ensuring consistent results.
- Implemented a wrapper to track call counts for the `countTokens` function, optimizing performance and reducing unnecessary calls.
- Enhanced existing tests to compare the performance of the new implementation against the old one, demonstrating significant improvements in efficiency.

* chore: documentation for Truncation Safety Buffer in Token Processing

- Added a safety buffer multiplier to the character position estimates during text truncation to prevent overshooting token limits.
- Updated the `processTextWithTokenLimit` function to utilize the new `TRUNCATION_SAFETY_BUFFER` constant, enhancing the accuracy of token limit processing.
- Improved documentation to clarify the rationale behind the buffer and its impact on performance and efficiency in token counting.

api/server/utils/countTokens.js

@@ -1,37 +0,0 @@
-const { Tiktoken } = require('tiktoken/lite');
-const { logger } = require('@librechat/data-schemas');
-const p50k_base = require('tiktoken/encoders/p50k_base.json');
-const cl100k_base = require('tiktoken/encoders/cl100k_base.json');
-
-/**
- * Counts the number of tokens in a given text using a specified encoding model.
- *
- * This function utilizes the 'Tiktoken' library to encode text based on the selected model.
- * It supports two models, 'text-davinci-003' and 'gpt-3.5-turbo', each with its own encoding strategy.
- * For 'text-davinci-003', the 'p50k_base' encoder is used, whereas for other models, the 'cl100k_base' encoder is applied.
- * In case of an error during encoding, the error is logged, and the function returns 0.
- *
- * @async
- * @param {string} text - The text to be tokenized. Defaults to an empty string if not provided.
- * @param {string} modelName - The name of the model used for tokenizing. Defaults to 'gpt-3.5-turbo'.
- * @returns {Promise<number>} The number of tokens in the provided text. Returns 0 if an error occurs.
- * @throws Logs the error to a logger and rethrows if any error occurs during tokenization.
- */
-const countTokens = async (text = '', modelName = 'gpt-3.5-turbo') => {
-  let encoder = null;
-  try {
-    const model = modelName.includes('text-davinci-003') ? p50k_base : cl100k_base;
-    encoder = new Tiktoken(model.bpe_ranks, model.special_tokens, model.pat_str);
-    const tokens = encoder.encode(text);
-    encoder.free();
-    return tokens.length;
-  } catch (e) {
-    logger.error('[countTokens]', e);
-    if (encoder) {
-      encoder.free();
-    }
-    return 0;
-  }
-};
-
-module.exports = countTokens;

api/server/utils/handleText.js

@@ -10,14 +10,6 @@ const {
 const { sendEvent } = require('@librechat/api');
 const partialRight = require('lodash/partialRight');
 
-/** Helper function to escape special characters in regex
- * @param {string} string - The string to escape.
- * @returns {string} The escaped string.
- */
-function escapeRegExp(string) {
-  return string.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
-}
-
 const addSpaceIfNeeded = (text) => (text.length > 0 && !text.endsWith(' ') ? text + ' ' : text);
 
 const base = { message: true, initial: true };
@@ -181,7 +173,6 @@ function generateConfig(key, baseURL, endpoint) {
 module.exports = {
   handleText,
   formatSteps,
-  escapeRegExp,
   formatAction,
   isUserProvided,
   generateConfig,

api/server/utils/index.js

@@ -1,5 +1,4 @@
 const removePorts = require('./removePorts');
-const countTokens = require('./countTokens');
 const handleText = require('./handleText');
 const sendEmail = require('./sendEmail');
 const queue = require('./queue');
@@ -7,7 +6,6 @@ const files = require('./files');
 
 module.exports = {
   ...handleText,
-  countTokens,
   removePorts,
   sendEmail,
   ...files,