max chars = 3000 + max rows =20, topk 60+ 60 = 120, cut off = 0.55

new normalizer C to Latin C

Extracts weld type from query

old utils + topk 50 + 50, hybrid = 100, cut off = 0.45

old utils + topk 70 + 70, hybrid = 100, cut off = 0.45

removed normalizing query

added the normalization of functions + max chars = 2500+ max rows = 15

new normalizing + max chars 3000 max rows =15

added the 100 topk

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

chunk size = 3000, 15 + normalized query

normalized fixed + in header text as well

query normalization

fixing normalizing hypens

removed normalization

added the new function to replace latin crylic c25

big debug change

top k 200, 50 + max chunk size = 10 000, max chunk row = 40

top k 200, 150 + max chunk size = 10 000, max chunk row = 40

added debugging functions for the c25

top k = 50 + topk rerank = 20 + max chunk size is 4000 + max rows =30 + sim cut off = 0.25

top k = 100 + topk rerank = 30 + max chunk size is 1024 + max rows =5 + sim cut off = 0.25

top k = 100 + max chunk size is 6000 + max rows =30 + sim cut off = 0.45

new utils py fixed

new api = retrieve chunks + some more text fixing

new dedublication

new documents prep

new documents prep

new documents prep

eski holat with utils

eski holat with utils

api key added

api key added

api key added

eski holat

eski holat

eski holat

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

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

removed normalization doc id

removed normalization doc id

index retriever = 100 + 100

index retriever = 100 + 100

max_chars = 1500 + doc id retriever

new keyword score based index retriever + answer question

new keyword score based index retriever + answer question

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

chunk siz = 1000, max_chars = 1500