Skip to content

Support multi-field TSV parsing in collection loader #40

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mushkanrana73 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Support multi-field TSV parsing in collection loader #40

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 22 additions & 2 deletions src/indexing.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,12 +21,32 @@ Type representing an ColBERT indexer.
An [`Indexer`] wrapping a [`ColBERTConfig`](@ref) along with the trained ColBERT
model.
"""
function parse_tsv_line(line::String)
parts = split(line, '\t')

# Skip invalid lines
if length(parts) < 2
return nothing
end

# Combine title + body + extra fields
return strip(join(parts[2:end], " "))
end
function Indexer(config::ColBERTConfig)
tokenizer, bert, linear = load_hgf_pretrained_local(config.checkpoint)
bert = bert |> Flux.gpu
linear = linear |> Flux.gpu
collection = config.collection isa String ? readlines(config.collection) :
config.collection
collection =
if config.collection isa String
lines = readlines(config.collection)

[
doc for doc in (parse_tsv_line(line) for line in lines)
if doc !== nothing
]
else
config.collection
end
punctuations_and_padsym = [string.(collect("!\"#\$%&\'()*+,-./:;<=>?@[\\]^_`{|}~"));
tokenizer.padsym]
skiplist = config.mask_punctuation ?
Expand Down