💾 feat: Anthropic Prompt Caching (#3670)

* wip: initial cache control implementation, add typing for transactions handling

* feat: first pass of Anthropic Prompt Caching

* feat: standardize stream usage as pass in when calculating token counts

* feat: Add getCacheMultiplier function to calculate cache multiplier for different valueKeys and cacheTypes

* chore: imports order

* refactor: token usage recording in AnthropicClient, no need to "correct" as we have the correct amount

* feat: more accurate token counting using stream usage data

* feat: Improve token counting accuracy with stream usage data

* refactor: ensure more accurate than not token estimations if custom instructions or files are not being resent with every request

* refactor: cleanup updateUserMessageTokenCount to allow transactions to be as accurate as possible even if we shouldn't update user message token counts

* ci: fix tests
This commit is contained in:
Danny Avila 2024-08-17 03:24:09 -04:00 committed by GitHub
parent 9f4c516615
commit a45b384bbc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 973 additions and 34 deletions

View file

@ -2,9 +2,9 @@ const { isAssistantsEndpoint } = require('librechat-data-provider');
const { sendMessage, sendError, countTokens, isEnabled } = require('~/server/utils');
const { truncateText, smartTruncateText } = require('~/app/clients/prompts');
const clearPendingReq = require('~/cache/clearPendingReq');
const { spendTokens } = require('~/models/spendTokens');
const abortControllers = require('./abortControllers');
const { saveMessage, getConvo } = require('~/models');
const spendTokens = require('~/models/spendTokens');
const { abortRun } = require('./abortRun');
const { logger } = require('~/config');