sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-24 07:55:07 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 33

Split entries by max tokens while converting Beancount entries To JSONL

Browse source
This commit is contained in:
Debanjum Singh Solanky 2022-12-26 15:14:32 -03:00
parent f209e30a3b
commit 17fa123b4e
1 changed files with 6 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
src/processor/ledger/beancount_to_jsonl.py
View file

@ -35,6 +35,12 @@ class BeancountToJsonl(TextToJsonl):
end = time.time() end = time.time()
logger.debug(f"Parse transactions from Beancount files into dictionaries: {end - start} seconds") logger.debug(f"Parse transactions from Beancount files into dictionaries: {end - start} seconds")
# Split entries by max tokens supported by model
start = time.time()
current_entries = self.split_entries_by_max_tokens(current_entries, max_tokens=256)
end = time.time()
logger.debug(f"Split entries by max token size supported by model: {end - start} seconds")
# Identify, mark and merge any new entries with previous entries # Identify, mark and merge any new entries with previous entries
start = time.time() start = time.time()
if not previous_entries: if not previous_entries: