added the 100 topk

removed the part removing hyperh + top 80, cutoff = 0.55

normalized fixed + in header text as well

fixing normalizing hypens

remove hyphens

normalize anyways + max row = 15 + max chars = 3000

removed normalization

added the new function to replace latin crylic c25

big debug change

big debug change

new debug functions + 2000 chunk size

new debug functions + 2000 chunk size

added debugging functions for the c25

top k = 150 + max chunk size is 4000 + max rows =15 + sim cut off = 0.45

top k = 80 + max chunk size is 3000

new api = retrieve chunks + some more text fixing

max chunk size= 4000 + max row = 5

max chunk size= 4000 + max row = 5

max chunk size= 4000 + max row = 5

new documents prep

new documents prep

eski holat

new function for should keep table whole for some files

max rows = 20, 150 + 150 bm25

chunk size = 2048 + rows=15

chunk size = 2048 + rows=15

chunk size = 2048 + rows=15

chunk size = 2048 + rows=15

chunk size = 2048 + rows=15

chunk size = 2048 + rows=15

chunk size = 1500

max rows = 20, 100 + 100 bm25

top k reranker = 20, max rows = 10, max chars= 2000 + new deduplication

top k reranker = 20, max rows = 10, max chars= 4000 + new deduplication

top k reranker = 25, max rows = 5, max chars= 4000

adaptive table chunking

Much lower reranking threshold (-0.5 instead of 0.1) + detailed score logging

Much lower reranking threshold (-0.5 instead of 0.1) + detailed score logging

Much lower reranking threshold (-0.5 instead of 0.1) + detailed score logging

removed normalization doc id

index retriever = 100 + 100

max_chars = 1500 + doc id retriever

chunk size = 1024 + max chars = 1200 + deduplication variant

chunk size = 1024 + max chars = 1200 + keyword based

chunk siz = 512, max_chars = 1000

chunk siz = 1000, max_chars = 1500

max chars = 3000 + removed normalize_doc_id

max chars = 2000 + removed normalize_doc_id

max chars = 2000 for tables + new answer_question

max rows = 10 + new answer_question + reranking