500 Internal Server Error about embedai

[Anil-matcha]

This shows document is uploaded, but you need to click on Ingest button to train the model on your document data

[Anil-matcha]

Have you done an ingest of the document ?

[dKonsalik]

Yes I did,

[dKonsalik]

Thank you @Anil-matcha
The result is gibberish, I assume we need to ingest more documents?

Loading documents from source_documentsLoaded 3 documents from source_documentsSplit into 96 chunks of text (max. 500 characters each)03@919:D5362GF%0='H(!4H",&-:-69);!=,'A<76H-D&75>"=#.4"@0.912&=8GC5=)"+EG7!))!&60>:,==$'+%'@(3:(,.>3$A+A"C&;"9GH#@):D:>+0A&%EEA@=),=G5H&C0GD5)8&G(A+5A>8*<.@3;<&A9.D4C,)>:+B<@,;G3643EAE6G>-)$27*"6&%79C10=#.H0@7H64H.*33(,2A9G.;:5B2%BD.@9&D0$75-59#>!HB,*D+
Source: source_documents/state_of_the_union.txt

[Anil-matcha]

What documents have you uploaded ?

Maybe you can clean the source documents and db folder and do upload your document, ingest and then run the query

[dKonsalik]

What documents have you uploaded ?

Maybe you can clean the source documents and db folder and do upload your document, ingest and then run the query

Removed DB and source documents.
I have uploaded PDF, but even tried a simple txt file with 2 sentences and the same output, just gibberish

192.168.70.36 - - [31/May/2023 17:44:11] "GET /download_model HTTP/1.1" 200 -
192.168.70.36 - - [31/May/2023 17:46:18] "POST /upload_doc HTTP/1.1" 200 -
Loading documents from source_documents
Loaded 1 documents from source_documents
Split into 69 chunks of text (max. 500 characters each)
Using embedded DuckDB with persistence: data will be stored in: db/
192.168.70.36 - - [31/May/2023 17:46:29] "GET /ingest HTTP/1.1" 200 -
192.168.70.36 - - [31/May/2023 17:46:50] "OPTIONS /get_answer HTTP/1.1" 200 -
Using embedded DuckDB with persistence: data will be stored in: db/
.A>#68*<$DC36G$(3<2H:3E26.H0#F*3@93#H7$,2DCDA(=''G$<F7G&()$34&(<2=;,GGF0))$6>5D,0C('&&.@eg#B'+A4H7!;2G7)C'&*3$-B@D<E""2)*5(***3@@6.1(<);$"*0&5;0