Debanjum Singh Solanky 826f9dc054 Drop long words from compiled entries to be within max token limit of models ... Long words (>500 characters) provide less useful context to models. Dropping very long words allow models to create better embeddings by passing more of the useful context from the entry to the model		2023-01-07 23:13:56 -03:00
..
data	Do not version API. Premature given current state of the codebase	2022-10-08 16:32:46 +03:00
__init__.py	Move tests out to project root. Use absolute import in project	2021-09-30 04:12:14 -07:00
conftest.py	Regenerate initial model in asymmetric reload test to reduce flakyness	2022-12-25 21:36:15 -03:00
test_beancount_to_jsonl.py	Use Base TextToJsonl class to standardize <text>_to_jsonl processors	2022-09-16 00:53:11 +03:00
test_chatbot.py	Fix the user intent extraction prompt for GPT. Clean up chatbot test	2022-01-12 10:36:01 -05:00
test_cli.py	Clean-up generated file after image search test run	2022-09-10 21:43:31 +03:00
test_client.py	Do not version API. Premature given current state of the codebase	2022-10-08 16:32:46 +03:00
test_date_filter.py	Remove unused imports, `embeddings' variable from text search tests	2022-10-08 12:06:05 +03:00
test_file_filter.py	Remove unused imports, `embeddings' variable from text search tests	2022-10-08 12:06:05 +03:00
test_helpers.py	Create LRU helper class for caching	2022-09-04 16:31:46 +03:00
test_image_search.py	Remove unused imports, `embeddings' variable from text search tests	2022-10-08 12:06:05 +03:00
test_markdown_to_jsonl.py	Use Base TextToJsonl class to standardize <text>_to_jsonl processors	2022-09-16 00:53:11 +03:00
test_org_to_jsonl.py	Drop long words from compiled entries to be within max token limit of models	2023-01-07 23:13:56 -03:00
test_orgnode.py	Fix OrgNode render of entries with property drawers and empty body	2022-09-11 16:09:19 +03:00
test_text_search.py	Fix comments, use minimal test case, regenerate test index, merge debug logs	2022-12-25 22:33:04 -03:00
test_word_filter.py	Remove unused imports, `embeddings' variable from text search tests	2022-10-08 12:06:05 +03:00