Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-17 17:00:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

🪂 refactor: OCR Fallback for "Upload as Text" File Process (#10126)
Some checks failed
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Has been cancelled
Details
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Has been cancelled
Details
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Has been cancelled
Details
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Has been cancelled
Details
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Has been cancelled
Details
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Has been cancelled
Details

Browse source
This commit is contained in:
Danny Avila 2025-10-15 16:20:54 +03:00 • committed by GitHub
parent c602088178
commit bc77bbd1ba
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 16 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

13
api/server/services/Files/process.js
View file

@ -598,11 +598,22 @@ const processAgentFileUpload = async ({ req, res, metadata }) => {
if (shouldUseOCR && !(await checkCapability(req, AgentCapabilities.ocr))) { if (shouldUseOCR && !(await checkCapability(req, AgentCapabilities.ocr))) {
throw new Error('OCR capability is not enabled for Agents'); throw new Error('OCR capability is not enabled for Agents');
} else if (shouldUseOCR) { } else if (shouldUseOCR) {
try {
const { handleFileUpload: uploadOCR } = getStrategyFunctions( const { handleFileUpload: uploadOCR } = getStrategyFunctions(
appConfig?.ocr?.strategy ?? FileSources.mistral_ocr, appConfig?.ocr?.strategy ?? FileSources.mistral_ocr,
); );
const { text, bytes, filepath: ocrFileURL } = await uploadOCR({ req, file, loadAuthValues }); const {
text,
bytes,
filepath: ocrFileURL,
} = await uploadOCR({ req, file, loadAuthValues });
return await createTextFile({ text, bytes, filepath: ocrFileURL }); return await createTextFile({ text, bytes, filepath: ocrFileURL });
} catch (ocrError) {
logger.error(
`[processAgentFileUpload] OCR processing failed for file "${file.originalname}", falling back to text extraction:`,
ocrError,
);
}
} }
const shouldUseSTT = fileConfig.checkType( const shouldUseSTT = fileConfig.checkType(