MODSetter
xlsx/csv files error on docker setup
Discussed in https://github.com/MODSetter/SurfSense/discussions/153
Originally posted by eyo4eh June 6, 2025 Hi, I launched the program according to the docker setup guide and the program works correctly for PDF files, but for xlsx/csv files it throws an error: `backend-1 | 2025-06-06 13:22:27 - httpx - INFO - HTTP Request: POST https://api.cloud.llamaindex.ai/api/parsing/upload "HTTP/1.1 200 OK"
backend-1 | 2025-06-06 13:22:28 - httpx - INFO - HTTP Request: GET https://api.cloud.llamaindex.ai/api/parsing/job/0ecd6f52-34d1-4eb6-8f32-07b46168dbf7 "HTTP/1.1 200 OK"
backend-1 | 2025-06-06 13:22:30 - httpx - INFO - HTTP Request: GET https://api.cloud.llamaindex.ai/api/parsing/job/0ecd6f52-34d1-4eb6-8f32-07b46168dbf7 "HTTP/1.1 200 OK"
backend-1 | 2025-06-06 13:22:31 - httpx - INFO - HTTP Request: GET https://api.cloud.llamaindex.ai/api/parsing/job/0ecd6f52-34d1-4eb6-8f32-07b46168dbf7/result/json "HTTP/1.1 200 OK"
backend-1 | 2025-06-06 13:22:31 - root - ERROR - Error processing file in background: 6 validation errors for JobResult
backend-1 | pages.0.status
backend-1 | Field required [type=missing, input_value={'page': 1, 'text': 'Tota...8","1","1","1","1"\n'}]}, input_type=dict]
backend-1 | For further information visit https://errors.pydantic.dev/2.11/v/missing
backend-1 | pages.0.triggeredAutoMode
backend-1 | Field required [type=missing, input_value={'page': 1, 'text': 'Tota...8","1","1","1","1"\n'}]}, input_type=dict]
backend-1 | For further information visit https://errors.pydantic.dev/2.11/v/missing
backend-1 | pages.0.parsingMode
backend-1 | Field required [type=missing, input_value={'page': 1, 'text': 'Tota...8","1","1","1","1"\n'}]}, input_type=dict]
backend-1 | For further information visit https://errors.pydantic.dev/2.11/v/missing
backend-1 | pages.0.structuredData
backend-1 | Field required [type=missing, input_value={'page': 1, 'text': 'Tota...8","1","1","1","1"\n'}]}, input_type=dict]
backend-1 | For further information visit https://errors.pydantic.dev/2.11/v/missing
backend-1 | pages.0.noStructuredContent
backend-1 | Field required [type=missing, input_value={'page': 1, 'text': 'Tota...8","1","1","1","1"\n'}]}, input_type=dict]
backend-1 | For further information visit https://errors.pydantic.dev/2.11/v/missing
backend-1 | pages.0.noTextContent
backend-1 | Field required [type=missing, input_value={'page': 1, 'text': 'Tota...8","1","1","1","1"\n'}]}, input_type=dict]
backend-1 | For further information visit https://errors.pydantic.dev/2.11/v/missing`
What is causing this error?
LLamaCloud support was just added a week back https://github.com/MODSetter/SurfSense/issues/113 so could be the impl issue. I will look into this soon.