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

Throw exception if no valid entries found in specified content files

Browse source 
- Previously we were failing if no valid entries while computing
  embeddings. This was obscuring the actual issue of no valid entries
  found in the specified content files
- Throwing an exception early with clear message when no entries found
  should make clarify the issue to be fixed
- See issue #83 for details
This commit is contained in:
Debanjum Singh Solanky 2022-09-10 13:05:21 +03:00
parent e00bb53336
commit d835467f2c
2 changed files with 27 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
src/search_type/text_search.py
View file

@ -11,7 +11,7 @@ from src.search_filter.base_filter import BaseFilter
# Internal Packages
from src.utils import state
from src.utils.helpers import get_absolute_path, resolve_absolute_path, load_model
from src.utils.helpers import get_absolute_path, is_none_or_empty, resolve_absolute_path, load_model
from src.utils.config import TextSearchModel
from src.utils.rawconfig import TextSearchConfig, TextContentConfig
from src.utils.jsonl import load_jsonl
@ -174,6 +174,8 @@ def setup(text_to_jsonl, config: TextContentConfig, search_config: TextSearchCon
# Extract Entries
entries = extract_entries(config.compressed_jsonl)
if is_none_or_empty(entries):
raise ValueError(f"No valid entries found in specified files: {config.input_files} or {config.input_filter}")
top_k = min(len(entries), top_k) # top_k hits can't be more than the total entries in corpus
# Compute or Load Embeddings

25
tests/test_text_search.py
View file

@ -1,6 +1,10 @@
# System Packages
from copy import deepcopy
from pathlib import Path
# External Packages
import pytest
# Internal Packages
from src.utils.state import model
from src.search_type import text_search
@ -9,6 +13,25 @@ from src.processor.org_mode.org_to_jsonl import org_to_jsonl
# Test
# ----------------------------------------------------------------------------------------------------
def test_asymmetric_setup_with_empty_file_raises_error(content_config: ContentConfig, search_config: SearchConfig):
# Arrange
file_to_index = Path(content_config.org.input_filter).parent / "new_file_to_index.org"
file_to_index.touch()
new_org_content_config = deepcopy(content_config.org)
new_org_content_config.input_files = [f'{file_to_index}']
new_org_content_config.input_filter = None
# Act
# Generate notes embeddings during asymmetric setup
with pytest.raises(ValueError, match=r'^No valid entries found*'):
text_search.setup(org_to_jsonl, new_org_content_config, search_config.asymmetric, regenerate=True)
# Cleanup
# delete created test file
file_to_index.unlink()
# ----------------------------------------------------------------------------------------------------
def test_asymmetric_setup(content_config: ContentConfig, search_config: SearchConfig):
# Act
@ -23,7 +46,7 @@ def test_asymmetric_setup(content_config: ContentConfig, search_config: SearchCo
# ----------------------------------------------------------------------------------------------------
def test_asymmetric_search(content_config: ContentConfig, search_config: SearchConfig):
# Arrange
model.notes_search = text_search.setup(org_to_jsonl, content_config.org, search_config.asymmetric, regenerate=False)
model.notes_search = text_search.setup(org_to_jsonl, content_config.org, search_config.asymmetric, regenerate=True)
query = "How to git install application?"
# Act