sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-27 17:35:07 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

Update state vars after regeneration. Minimize time app in inconsistent state

Browse source
This commit is contained in:
Debanjum Singh Solanky 2021-08-16 23:47:33 -07:00
parent 0509854e14
commit 02a84df37a
1 changed files with 14 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
main.py
View file

@ -38,15 +38,24 @@ def search(q: str, n: Optional[int] = 5, t: Optional[str] = 'notes'):
@app.get('/regenerate') @app.get('/regenerate')
def regenerate(): def regenerate():
# Generate Compressed JSONL from Notes in Input Files
org_to_jsonl(args.input_files, args.input_filter, args.compressed_jsonl, args.verbose) org_to_jsonl(args.input_files, args.input_filter, args.compressed_jsonl, args.verbose)
# Extract Entries # Extract Entries from Compressed JSONL
global entries extracted_entries = asymmetric.extract_entries(args.compressed_jsonl, args.verbose)
entries = asymmetric.extract_entries(args.compressed_jsonl, args.verbose)
# Compute or Load Embeddings # Compute Embeddings from Extracted Entries
computed_embeddings = asymmetric.compute_embeddings(extracted_entries, bi_encoder, args.embeddings, regenerate=True, verbose=args.verbose)
# Now Update State
# update state variables after regeneration complete
# minimize time the application is in inconsistent, partially updated state
global corpus_embeddings global corpus_embeddings
corpus_embeddings = asymmetric.compute_embeddings(entries, bi_encoder, args.embeddings, regenerate=True, verbose=args.verbose) global entries
entries = extracted_entries
corpus_embeddings = computed_embeddings
return {'status': 'ok', 'message': 'regeneration completed'}
if __name__ == '__main__': if __name__ == '__main__':