LibreChat/api/server/utils/countTokens.js
Danny Avila ea1dd59ef4
refactor(api): Central Logging 📜 (#1348)
* WIP: initial logging changes
add several transports in ~/config/winston
omit messages in logs, truncate long strings
add short blurb in dotenv for debug logging
GoogleClient: using logger
OpenAIClient: using logger, handleOpenAIErrors
Adding typedef for payload message
bumped winston and using winston-daily-rotate-file
moved config for server paths to ~/config dir
Added `DEBUG_LOGGING=true` to .env.example

* WIP: Refactor logging statements in code

* WIP: Refactor logging statements and import configurations

* WIP: Refactor logging statements and import configurations

* refactor: broadcast Redis initialization message with `info` not `debug`

* refactor: complete Refactor logging statements and import configurations

* chore: delete unused tools

* fix: circular dependencies due to accessing logger

* refactor(handleText): handle booleans and write tests

* refactor: redact sensitive values, better formatting

* chore: improve log formatting, avoid passing strings to 2nd arg

* fix(ci): fix jest tests due to logger changes

* refactor(getAvailablePluginsController): cache plugins as they are static and avoids async addOpenAPISpecs call every time

* chore: update docs

* chore: update docs

* chore: create separate meiliSync logger, clean up logs to avoid being unnecessarily verbose

* chore: spread objects where they are commonly logged to allow string truncation

* chore: improve error log formatting
2023-12-14 07:49:27 -05:00

24 lines
729 B
JavaScript

const { load } = require('tiktoken/load');
const { Tiktoken } = require('tiktoken/lite');
const registry = require('tiktoken/registry.json');
const models = require('tiktoken/model_to_encoding.json');
const logger = require('~/config/winston');
const countTokens = async (text = '', modelName = 'gpt-3.5-turbo') => {
let encoder = null;
try {
const model = await load(registry[models[modelName]]);
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;