LibreChat/api/server/routes/tokenizer.js

20 lines
580 B
JavaScript
Raw Normal View History

const express = require('express');
const { logger } = require('@librechat/data-schemas');
const requireJwtAuth = require('~/server/middleware/requireJwtAuth');
const { countTokens } = require('~/server/utils');
const router = express.Router();
feat: Auth and User System (#205) * server-side JWT auth implementation * move oauth routes and strategies, fix bugs * backend modifications for wiring up the frontend login and reg forms * Add frontend data services for login and registration * Add login and registration forms * Implment auth context, functional client side auth * protect routes with jwt auth * finish local strategy (using local storage) * Start setting up google auth * disable token refresh, remove old auth middleware * refactor client, add ApiErrorBoundary context * disable google and facebook strategies * fix: fix presets not displaying specific to user * fix: fix issue with browser refresh * fix: casing issue with User.js (#11) * delete user.js to be renamed * fix: fix casing issue with User.js * comment out api error watcher temporarily * fix: issue with api error watcher (#12) * delete user.js to be renamed * fix: fix casing issue with User.js * comment out api error watcher temporarily * feat: add google auth social login * fix: make google login url dynamic based on dev/prod * fix: bug where UI is briefly displayed before redirecting to login * fix: fix cookie expires value for local auth * Update README.md * Update LOCAL_INSTALL structure * Add local testing instructions * Only load google strategy if client id and secret are provided * Update .env.example files with new params * fix issue with not redirecting to register form * only show google login button if value is set in .env * cleanup log messages * Add label to button for google login on login form * doc: fix client/server url values in .env.example * feat: add error message details to registration failure * Restore preventing paste on confirm password * auto-login user after registering * feat: forgot password (#24) * make login/reg pages look like openai's * add password reset data services * new form designs similar to openai, add password reset pages * add api's for password reset * email utils for password reset * remove bcrypt salt rounds from process.env * refactor: restructure api auth code, consolidate routes (#25) * add api's for password reset * remove bcrypt salt rounds from process.env * refactor: consolidate auth routes, use controller pattern * refactor: code cleanup * feat: migrate data to first user (#26) * refactor: use /api for auth routes * fix: use user id instead of username * feat: migrate data to first user on register * fix: fix social login routes after refactor (#27) * refactor: use /api for auth routes * fix: use user id instead of username * feat: migrate data to first user on register * fix: fix social login routes * fix: issue with auto-login when logging out then logging in with new browser window (#28) * refactor: use /api for auth routes * fix: use user id instead of username * feat: migrate data to first user on register * fix: fix social login routes * fix: fix issue with auto-login in new tab * doc: Update README and .env.example files with user system information (#29) * refactor: use /api for auth routes * fix: use user id instead of username * feat: migrate data to first user on register * fix: fix social login routes * fix: fix issue with auto-login in new tab * doc: update README and .env.example files * Fixup: LOCAL_INSTALL.md PS instructions (#200) (#30) Co-authored-by: alfredo-f <alfredo.fomitchenko@mail.polimi.it> * feat: send user with completion to protect against abuse (#31) * Fixup: LOCAL_INSTALL.md PS instructions (#200) * server-side JWT auth implementation * move oauth routes and strategies, fix bugs * backend modifications for wiring up the frontend login and reg forms * Add frontend data services for login and registration * Add login and registration forms * Implment auth context, functional client side auth * protect routes with jwt auth * finish local strategy (using local storage) * Start setting up google auth * disable token refresh, remove old auth middleware * refactor client, add ApiErrorBoundary context * disable google and facebook strategies * fix: fix presets not displaying specific to user * fix: fix issue with browser refresh * fix: casing issue with User.js (#11) * delete user.js to be renamed * fix: fix casing issue with User.js * comment out api error watcher temporarily * feat: add google auth social login * fix: make google login url dynamic based on dev/prod * fix: bug where UI is briefly displayed before redirecting to login * fix: fix cookie expires value for local auth * Only load google strategy if client id and secret are provided * Update .env.example files with new params * fix issue with not redirecting to register form * only show google login button if value is set in .env * cleanup log messages * Add label to button for google login on login form * doc: fix client/server url values in .env.example * feat: add error message details to registration failure * Restore preventing paste on confirm password * auto-login user after registering * feat: forgot password (#24) * make login/reg pages look like openai's * add password reset data services * new form designs similar to openai, add password reset pages * add api's for password reset * email utils for password reset * remove bcrypt salt rounds from process.env * refactor: restructure api auth code, consolidate routes (#25) * add api's for password reset * remove bcrypt salt rounds from process.env * refactor: consolidate auth routes, use controller pattern * refactor: code cleanup * feat: migrate data to first user (#26) * refactor: use /api for auth routes * fix: use user id instead of username * feat: migrate data to first user on register * fix: fix social login routes after refactor (#27) * refactor: use /api for auth routes * fix: use user id instead of username * feat: migrate data to first user on register * fix: fix social login routes * fix: issue with auto-login when logging out then logging in with new browser window (#28) * refactor: use /api for auth routes * fix: use user id instead of username * feat: migrate data to first user on register * fix: fix social login routes * fix: fix issue with auto-login in new tab * doc: Update README and .env.example files with user system information (#29) * refactor: use /api for auth routes * fix: use user id instead of username * feat: migrate data to first user on register * fix: fix social login routes * fix: fix issue with auto-login in new tab * doc: update README and .env.example files * Send user id to openai to protect against abuse * add meilisearch to gitignore * Remove webpack --------- Co-authored-by: alfredo-f <alfredo.fomitchenko@mail.polimi.it> --------- Co-authored-by: Danny Avila <110412045+danny-avila@users.noreply.github.com> Co-authored-by: Alfredo Fomitchenko <alfredo.fomitchenko@mail.polimi.it>
2023-05-07 10:04:51 -07:00
router.post('/', requireJwtAuth, async (req, res) => {
try {
const { arg } = req.body;
feat: ConversationSummaryBufferMemory (#973) * refactor: pass model in message edit payload, use encoder in standalone util function * feat: add summaryBuffer helper * refactor(api/messages): use new countTokens helper and add auth middleware at top * wip: ConversationSummaryBufferMemory * refactor: move pre-generation helpers to prompts dir * chore: remove console log * chore: remove test as payload will no longer carry tokenCount * chore: update getMessagesWithinTokenLimit JSDoc * refactor: optimize getMessagesForConversation and also break on summary, feat(ci): getMessagesForConversation tests * refactor(getMessagesForConvo): count '00000000-0000-0000-0000-000000000000' as root message * chore: add newer model to token map * fix: condition was point to prop of array instead of message prop * refactor(BaseClient): use object for refineMessages param, rename 'summary' to 'summaryMessage', add previous_summary refactor(getMessagesWithinTokenLimit): replace text and tokenCount if should summarize, summary, and summaryTokenCount are present fix/refactor(handleContextStrategy): use the right comparison length for context diff, and replace payload first message when a summary is present * chore: log previous_summary if debugging * refactor(formatMessage): assume if role is defined that it's a valid value * refactor(getMessagesWithinTokenLimit): remove summary logic refactor(handleContextStrategy): add usePrevSummary logic in case only summary was pruned refactor(loadHistory): initial message query will return all ordered messages but keep track of the latest summary refactor(getMessagesForConversation): use object for single param, edit jsdoc, edit all files using the method refactor(ChatGPTClient): order messages before buildPrompt is called, TODO: add convoSumBuffMemory logic * fix: undefined handling and summarizing only when shouldRefineContext is true * chore(BaseClient): fix test results omitting system role for summaries and test edge case * chore: export summaryBuffer from index file * refactor(OpenAIClient/BaseClient): move refineMessages to subclass, implement LLM initialization for summaryBuffer * feat: add OPENAI_SUMMARIZE to enable summarizing, refactor: rename client prop 'shouldRefineContext' to 'shouldSummarize', change contextStrategy value to 'summarize' from 'refine' * refactor: rename refineMessages method to summarizeMessages for clarity * chore: clarify summary future intent in .env.example * refactor(initializeLLM): handle case for either 'model' or 'modelName' being passed * feat(gptPlugins): enable summarization for plugins * refactor(gptPlugins): utilize new initializeLLM method and formatting methods for messages, use payload array for currentMessages and assign pastMessages sooner * refactor(agents): use ConversationSummaryBufferMemory for both agent types * refactor(formatMessage): optimize original method for langchain, add helper function for langchain messages, add JSDocs and tests * refactor(summaryBuffer): add helper to createSummaryBufferMemory, and use new formatting helpers * fix: forgot to spread formatMessages also took opportunity to pluralize filename * refactor: pass memory to tools, namely openapi specs. not used and may never be used by new method but added for testing * ci(formatMessages): add more exhaustive checks for langchain messages * feat: add debug env var for OpenAI * chore: delete unnecessary comments * chore: add extra note about summary feature * fix: remove tokenCount from payload instructions * fix: test fail * fix: only pass instructions to payload when defined or not empty object * refactor: fromPromptMessages is deprecated, use renamed method fromMessages * refactor: use 'includes' instead of 'startsWith' for extended OpenRouter compatibility * fix(PluginsClient.buildPromptBody): handle undefined message strings * chore: log langchain titling error * feat: getModelMaxTokens helper * feat: tokenSplit helper * feat: summary prompts updated * fix: optimize _CUT_OFF_SUMMARIZER prompt * refactor(summaryBuffer): use custom summary prompt, allow prompt to be passed, pass humanPrefix and aiPrefix to memory, along with any future variables, rename messagesToRefine to context * fix(summaryBuffer): handle edge case where messagesToRefine exceeds summary context, refactor(BaseClient): allow custom maxContextTokens to be passed to getMessagesWithinTokenLimit, add defined check before unshifting summaryMessage, update shouldSummarize based on this refactor(OpenAIClient): use getModelMaxTokens, use cut-off message method for summary if no messages were left after pruning * fix(handleContextStrategy): handle case where incoming prompt is bigger than model context * chore: rename refinedContent to splitText * chore: remove unnecessary debug log
2023-09-26 21:02:28 -04:00
const count = await countTokens(arg?.text ?? arg);
res.send({ count });
} catch (e) {
logger.error('[/tokenizer] Error counting tokens', e);
res.status(500).json('Error counting tokens');
}
});
module.exports = router;