LibreChat/api/app/clients/prompts/formatMessages.js
Danny Avila 365c39c405
feat: Accurate Token Usage Tracking & Optional Balance (#1018)
* refactor(Chains/llms): allow passing callbacks

* refactor(BaseClient): accurately count completion tokens as generation only

* refactor(OpenAIClient): remove unused getTokenCountForResponse, pass streaming var and callbacks in initializeLLM

* wip: summary prompt tokens

* refactor(summarizeMessages): new cut-off strategy that generates a better summary by adding context from beginning, truncating the middle, and providing the end
wip: draft out relevant providers and variables for token tracing

* refactor(createLLM): make streaming prop false by default

* chore: remove use of getTokenCountForResponse

* refactor(agents): use BufferMemory as ConversationSummaryBufferMemory token usage not easy to trace

* chore: remove passing of streaming prop, also console log useful vars for tracing

* feat: formatFromLangChain helper function to count tokens for ChatModelStart

* refactor(initializeLLM): add role for LLM tracing

* chore(formatFromLangChain): update JSDoc

* feat(formatMessages): formats langChain messages into OpenAI payload format

* chore: install openai-chat-tokens

* refactor(formatMessage): optimize conditional langChain logic
fix(formatFromLangChain): fix destructuring

* feat: accurate prompt tokens for ChatModelStart before generation

* refactor(handleChatModelStart): move to callbacks dir, use factory function

* refactor(initializeLLM): rename 'role' to 'context'

* feat(Balance/Transaction): new schema/models for tracking token spend
refactor(Key): factor out model export to separate file

* refactor(initializeClient): add req,res objects to client options

* feat: add-balance script to add to an existing users' token balance
refactor(Transaction): use multiplier map/function, return balance update

* refactor(Tx): update enum for tokenType, return 1 for multiplier if no map match

* refactor(Tx): add fair fallback value multiplier incase the config result is undefined

* refactor(Balance): rename 'tokens' to 'tokenCredits'

* feat: balance check, add tx.js for new tx-related methods and tests

* chore(summaryPrompts): update prompt token count

* refactor(callbacks): pass req, res
wip: check balance

* refactor(Tx): make convoId a String type, fix(calculateTokenValue)

* refactor(BaseClient): add conversationId as client prop when assigned

* feat(RunManager): track LLM runs with manager, track token spend from LLM,
refactor(OpenAIClient): use RunManager to create callbacks, pass user prop to langchain api calls

* feat(spendTokens): helper to spend prompt/completion tokens

* feat(checkBalance): add helper to check, log, deny request if balance doesn't have enough funds
refactor(Balance): static check method to return object instead of boolean now
wip(OpenAIClient): implement use of checkBalance

* refactor(initializeLLM): add token buffer to assure summary isn't generated when subsequent payload is too large
refactor(OpenAIClient): add checkBalance
refactor(createStartHandler): add checkBalance

* chore: remove prompt and completion token logging from route handler

* chore(spendTokens): add JSDoc

* feat(logTokenCost): record transactions for basic api calls

* chore(ask/edit): invoke getResponseSender only once per API call

* refactor(ask/edit): pass promptTokens to getIds and include in abort data

* refactor(getIds -> getReqData): rename function

* refactor(Tx): increase value if incomplete message

* feat: record tokenUsage when message is aborted

* refactor: subtract tokens when payload includes function_call

* refactor: add namespace for token_balance

* fix(spendTokens): only execute if corresponding token type amounts are defined

* refactor(checkBalance): throws Error if not enough token credits

* refactor(runTitleChain): pass and use signal, spread object props in create helpers, and use 'call' instead of 'run'

* fix(abortMiddleware): circular dependency, and default to empty string for completionTokens

* fix: properly cancel title requests when there isn't enough tokens to generate

* feat(predictNewSummary): custom chain for summaries to allow signal passing
refactor(summaryBuffer): use new custom chain

* feat(RunManager): add getRunByConversationId method, refactor: remove run and throw llm error on handleLLMError

* refactor(createStartHandler): if summary, add error details to runs

* fix(OpenAIClient): support aborting from summarization & showing error to user
refactor(summarizeMessages): remove unnecessary operations counting summaryPromptTokens and note for alternative, pass signal to summaryBuffer

* refactor(logTokenCost -> recordTokenUsage): rename

* refactor(checkBalance): include promptTokens in errorMessage

* refactor(checkBalance/spendTokens): move to models dir

* fix(createLanguageChain): correctly pass config

* refactor(initializeLLM/title): add tokenBuffer of 150 for balance check

* refactor(openAPIPlugin): pass signal and memory, filter functions by the one being called

* refactor(createStartHandler): add error to run if context is plugins as well

* refactor(RunManager/handleLLMError): throw error immediately if plugins, don't remove run

* refactor(PluginsClient): pass memory and signal to tools, cleanup error handling logic

* chore: use absolute equality for addTitle condition

* refactor(checkBalance): move checkBalance to execute after userMessage and tokenCounts are saved, also make conditional

* style: icon changes to match official

* fix(BaseClient): getTokenCountForResponse -> getTokenCount

* fix(formatLangChainMessages): add kwargs as fallback prop from lc_kwargs, update JSDoc

* refactor(Tx.create): does not update balance if CHECK_BALANCE is not enabled

* fix(e2e/cleanUp): cleanup new collections, import all model methods from index

* fix(config/add-balance): add uncaughtException listener

* fix: circular dependency

* refactor(initializeLLM/checkBalance): append new generations to errorMessage if cost exceeds balance

* fix(handleResponseMessage): only record token usage in this method if not error and completion is not skipped

* fix(createStartHandler): correct condition for generations

* chore: bump postcss due to moderate severity vulnerability

* chore: bump zod due to low severity vulnerability

* chore: bump openai & data-provider version

* feat(types): OpenAI Message types

* chore: update bun lockfile

* refactor(CodeBlock): add error block formatting

* refactor(utils/Plugin): factor out formatJSON and cn to separate files (json.ts and cn.ts), add extractJSON

* chore(logViolation): delete user_id after error is logged

* refactor(getMessageError -> Error): change to React.FC, add token_balance handling, use extractJSON to determine JSON instead of regex

* fix(DALL-E): use latest openai SDK

* chore: reorganize imports, fix type issue

* feat(server): add balance route

* fix(api/models): add auth

* feat(data-provider): /api/balance query

* feat: show balance if checking is enabled, refetch on final message or error

* chore: update docs, .env.example with token_usage info, add balance script command

* fix(Balance): fallback to empty obj for balance query

* style: slight adjustment of balance element

* docs(token_usage): add PR notes
2023-10-05 18:34:10 -04:00

90 lines
3.5 KiB
JavaScript

const { HumanMessage, AIMessage, SystemMessage } = require('langchain/schema');
/**
* Formats a message to OpenAI payload format based on the provided options.
*
* @param {Object} params - The parameters for formatting.
* @param {Object} params.message - The message object to format.
* @param {string} [params.message.role] - The role of the message sender (e.g., 'user', 'assistant').
* @param {string} [params.message._name] - The name associated with the message.
* @param {string} [params.message.sender] - The sender of the message.
* @param {string} [params.message.text] - The text content of the message.
* @param {string} [params.message.content] - The content of the message.
* @param {string} [params.userName] - The name of the user.
* @param {string} [params.assistantName] - The name of the assistant.
* @param {boolean} [params.langChain=false] - Whether to return a LangChain message object.
* @returns {(Object|HumanMessage|AIMessage|SystemMessage)} - The formatted message.
*/
const formatMessage = ({ message, userName, assistantName, langChain = false }) => {
let { role: _role, _name, sender, text, content: _content, lc_id } = message;
if (lc_id && lc_id[2] && !langChain) {
const roleMapping = {
SystemMessage: 'system',
HumanMessage: 'user',
AIMessage: 'assistant',
};
_role = roleMapping[lc_id[2]];
}
const role = _role ?? (sender && sender?.toLowerCase() === 'user' ? 'user' : 'assistant');
const content = text ?? _content ?? '';
const formattedMessage = {
role,
content,
};
if (_name) {
formattedMessage.name = _name;
}
if (userName && formattedMessage.role === 'user') {
formattedMessage.name = userName;
}
if (assistantName && formattedMessage.role === 'assistant') {
formattedMessage.name = assistantName;
}
if (!langChain) {
return formattedMessage;
}
if (role === 'user') {
return new HumanMessage(formattedMessage);
} else if (role === 'assistant') {
return new AIMessage(formattedMessage);
} else {
return new SystemMessage(formattedMessage);
}
};
/**
* Formats an array of messages for LangChain.
*
* @param {Array<Object>} messages - The array of messages to format.
* @param {Object} formatOptions - The options for formatting each message.
* @param {string} [formatOptions.userName] - The name of the user.
* @param {string} [formatOptions.assistantName] - The name of the assistant.
* @returns {Array<(HumanMessage|AIMessage|SystemMessage)>} - The array of formatted LangChain messages.
*/
const formatLangChainMessages = (messages, formatOptions) =>
messages.map((msg) => formatMessage({ ...formatOptions, message: msg, langChain: true }));
/**
* Formats a LangChain message object by merging properties from `lc_kwargs` or `kwargs` and `additional_kwargs`.
*
* @param {Object} message - The message object to format.
* @param {Object} [message.lc_kwargs] - Contains properties to be merged. Either this or `message.kwargs` should be provided.
* @param {Object} [message.kwargs] - Contains properties to be merged. Either this or `message.lc_kwargs` should be provided.
* @param {Object} [message.kwargs.additional_kwargs] - Additional properties to be merged.
*
* @returns {Object} The formatted LangChain message.
*/
const formatFromLangChain = (message) => {
const { additional_kwargs, ...message_kwargs } = message.lc_kwargs ?? message.kwargs;
return {
...message_kwargs,
...additional_kwargs,
};
};
module.exports = { formatMessage, formatLangChainMessages, formatFromLangChain };