Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-17 00:40:14 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

🔍 refactor: OCR Fully Optional with Defaults for "Upload as Text" (#9856)
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Details
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
Details
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Waiting to run
Details
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Waiting to run
Details
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Details
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
Details

Browse source 
* refactor: move `loadOCRConfig` from `packages/data-provider` to `packages/api` and return `undefined` if not explicitly configured

* fix: loadOCRConfig import from @librechat/api

* refactor: update defaultTextMimeTypes to support virtually all file types for text parsing

* fix: improve OCR capability check and error message for unsupported file types

* ci: remove unnecessary ocr expectation from AppService test
This commit is contained in:
Danny Avila 2025-09-26 11:56:11 -04:00 • committed by GitHub
parent 3d7eaf0fcc
commit 4b5b46604c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 15 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

8
api/server/services/AppService.js
View file

@ -1,16 +1,12 @@
const { FileSources, EModelEndpoint, getConfigDefaults } = require('librechat-data-provider');
const {
isEnabled,
loadOCRConfig,
loadMemoryConfig,
agentsConfigSetup,
loadWebSearchConfig,
loadDefaultInterface,
} = require('@librechat/api');
const {
FileSources,
loadOCRConfig,
EModelEndpoint,
getConfigDefaults,
} = require('librechat-data-provider');
const {
checkWebSearchConfig,
checkVariables,

1
api/server/services/AppService.spec.js
View file

@ -142,7 +142,6 @@ describe('AppService', () => {
turnstileConfig: mockedTurnstileConfig,
modelSpecs: undefined,
paths: expect.anything(),
ocr: expect.anything(),
imageOutputType: expect.any(String),
fileConfig: undefined,
secureImageLinks: undefined,

9
api/server/services/Files/process.js
View file

@ -594,10 +594,9 @@ const processAgentFileUpload = async ({ req, res, metadata }) => {
const fileConfig = mergeFileConfig(appConfig.fileConfig);
const shouldUseOCR = fileConfig.checkType(
file.mimetype,
fileConfig.ocr?.supportedMimeTypes || [],
);
const shouldUseOCR =
appConfig?.ocr != null &&
fileConfig.checkType(file.mimetype, fileConfig.ocr?.supportedMimeTypes || []);
if (shouldUseOCR && !(await checkCapability(req, AgentCapabilities.ocr))) {
throw new Error('OCR capability is not enabled for Agents');
@ -626,7 +625,7 @@ const processAgentFileUpload = async ({ req, res, metadata }) => {
);
if (!shouldUseText) {
throw new Error(`File type ${file.mimetype} is not supported for OCR or text parsing`);
throw new Error(`File type ${file.mimetype} is not supported for text parsing.`);
}
const { text, bytes } = await parseText({ req, file, file_id });