semantic-search: increase maximal allowed chunk size, fix error when timeout

[PrimozGodec]

Issue

1. When doing a semantic search on laws, many of them are longer than 50000, all of them are below 300000
2. Sometimes embedding fails since timeout happens in embedding. In those cases result for a chunk is None and not a list. The current implementation fails since it wants to extend the list with None.

Description of changes

• handle error 2
• allow documents to be maximally 300000 long and still make chunks with max size 50000. Documents that are longer than MAX_CHUNK_SIZE will be in one request which is longer thank MAX_CHUNK_SIZE

Includes

• Code changes
• Tests
• Documentation

[codecov-commenter]

Codecov Report

Merging #752 (98e56c6) into master (b3511fa) will increase coverage by 0.27%.
The diff coverage is 77.77%.

❗ Current head 98e56c6 differs from pull request most recent head 0570321. Consider uploading reports for the commit 0570321 to get more accurate results

@@            Coverage Diff             @@
##           master     #752      +/-   ##
==========================================
+ Coverage   74.31%   74.59%   +0.27%     
==========================================
  Files          73       74       +1     
  Lines        9669     9876     +207     
  Branches     1321     1333      +12     
==========================================
+ Hits         7186     7367     +181     
- Misses       2228     2252      +24     
- Partials      255      257       +2