dka/LibreChat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

🪂 refactor: OCR Fallback for "Upload as Text" File Process (#10126)

Browse Source
This commit is contained in:
Danny Avila
2025-10-15 16:20:54 +03:00
committed by GitHub
parent c602088178
commit bc77bbd1ba
1 changed files with 16 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
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))) {
throw new Error('OCR capability is not enabled for Agents');
} else if (shouldUseOCR) {
const { handleFileUpload: uploadOCR } = getStrategyFunctions(
appConfig?.ocr?.strategy ?? FileSources.mistral_ocr,
);
const { text, bytes, filepath: ocrFileURL } = await uploadOCR({ req, file, loadAuthValues });
return await createTextFile({ text, bytes, filepath: ocrFileURL });
try {
const { handleFileUpload: uploadOCR } = getStrategyFunctions(
appConfig?.ocr?.strategy ?? FileSources.mistral_ocr,
);
const {
text,
bytes,
filepath: ocrFileURL,
} = await uploadOCR({ req, file, loadAuthValues });
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(