fix pandas read file bypassing error 403

Update requirements.txt

Update api/docs.py

deprecated ocr parameter in ExtractionConfig

Update api/docs.py

Update api/docs.py

Update api/docs.py

fix bug extract_text_from_url

add endpoints to extract text

add search bar for agenda items and suggestion marks in .txt files

Hopefully fix task hang issues

Add debug statements to narrow issue

Add support for custom meeting URLS

Extract first supported file type in archive

Add doc for local dev mode

Enable Table Extraction

Unstuck space build

Add ability to do free form conversion of user files

Sort prompts + add doc for prompts

Misc + modify prompt

Add ability to bulk download files sorted by agenda item or not

Support disabling sort checks

Add support for downloading PowerPoint PPT files

Place files in agenda item directory when downloading tdocs

Hotfix : change max DL limit 120 -> 30 and limi

Add support for a smaller model for fast tasks

Fix

Random fixes + doc bits

Use kreuzberg for document extraction + rate limit downloads

Misc changes

Enable downloading multiple doc types

Make doc extraction async

wip

Use single method for retrieving TDocs + prepare code to refine

Remove usages of NLTK (that is unused actually)

Allow listing other document types than xxxxCRs

Include searched FTO report

Expose FTO individual topics

Fix TDoc download

Fix draft export

Add timeline export real quick

Update doc

Make FTO topic count configurable

Misc fixes

Fix UI to display if step is draft or FTO

reduce fto search size

Implement FTO

Prepare FTO

Implement user insights

Update prompt