Commit graph

4555 commits

Author SHA1 Message Date
Vasilije
535d8281b4
Merge pull request #215 from topoteretes/clean_dspy
Remove dspy logic that confuses
2024-11-14 14:51:51 +01:00
Vasilije
bc2e17592d
Merge branch 'main' into clean_dspy 2024-11-14 14:50:43 +01:00
Vasilije
36ada5974d
Delete cognee/modules/cognify/dataset.py 2024-11-14 14:49:45 +01:00
Vasilije
8e9040815f
Delete cognee/modules/cognify/train.py 2024-11-14 14:49:34 +01:00
Vasilije
cf09a5ea37
Delete cognee/modules/cognify/test.py 2024-11-14 14:49:23 +01:00
Vasilije
c5d132ed14
Delete cognee/modules/cognify/evaluate.py 2024-11-14 14:49:08 +01:00
hajdul88
c1007091d1
Merge pull request #196 from topoteretes/feat/COG-553-graph-memory-projection
Feat/cog 553 graph memory projection
2024-11-14 14:48:41 +01:00
0xideas
8b681529b1
Update cognee/tasks/chunks/chunk_by_paragraph.py
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2024-11-14 14:42:15 +01:00
Leon Luithlen
73f24f9e4d Fix sentence_cut return value in inappropriate places 2024-11-14 14:40:42 +01:00
Leon Luithlen
b4d509e682 Set batch_paragraph=False in run_chunking_test 2024-11-14 14:23:09 +01:00
Leon Luithlen
a52d3ac6ba Change document test ground truth values for new chunk_by_word 2024-11-14 14:20:18 +01:00
Leon Luithlen
eaf9167fa1 Change chunk_by_word to collect newlines in prior words 2024-11-14 14:19:34 +01:00
hajdul88
867e18de86 fix: Changes GraphDBInterface typing in CogneeGraph 2024-11-14 14:01:20 +01:00
Leon Luithlen
57d8149732 Save paragraph_ids in chunk_by_paragraph 2024-11-14 13:59:54 +01:00
Leon Luithlen
6721eaee83 Fix chunk_index bug in chunk_by_paragraph 2024-11-14 13:50:40 +01:00
0xideas
f2206a09c0
Update cognee/tasks/chunks/chunk_by_word.py
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2024-11-14 13:16:17 +01:00
Leon Luithlen
8260647497 Add AudioDocument and ImageDocument tests 2024-11-14 12:42:10 +01:00
Leon Luithlen
f87fd12e9b Fix lambda bug in AudioDocument and ImageDocument 2024-11-14 12:41:47 +01:00
Leon Luithlen
8b3b2f8156 Add transcribe_image and create_transcript methods 2024-11-14 11:59:46 +01:00
hajdul88
32504255ef feat: Adds unit tests to CogneeGraph class 2024-11-14 11:46:17 +01:00
hajdul88
b516862edc Fix: Fixes import paths 2024-11-14 11:44:43 +01:00
Leon Luithlen
c905510f30 Change test_input order 2024-11-14 11:44:18 +01:00
Leon Luithlen
e6636754ff Add TextDocument_test.py 2024-11-14 11:39:14 +01:00
Leon Luithlen
8afb25e0d4 Move PdfDocument_test.py to integration tests 2024-11-14 11:24:11 +01:00
Leon Luithlen
e794bb8834 Return stripped value from get_embeddable_data if its string 2024-11-14 09:43:56 +01:00
Leon Luithlen
adc8a0b09c Add ellipsis test string 2024-11-14 09:43:32 +01:00
Leon Luithlen
d90698305b Simplify chunk_by_word 2024-11-14 09:43:10 +01:00
hajdul88
d3fdddaa52 Revert "Checks the pgvector test issue"
This reverts commit 0d27371467.
2024-11-13 17:55:52 +01:00
hajdul88
0d27371467 Checks the pgvector test issue 2024-11-13 17:51:25 +01:00
Rita Aleksziev
d0fcd25826 Merge branch 'main' into feat/COG-544-eval-on-swe-bench 2024-11-13 17:28:13 +01:00
hajdul88
d8024db002 fix: Fixes edge case handling 2024-11-13 17:18:07 +01:00
hajdul88
bf4eedd20e
Merge branch 'main' into feat/COG-553-graph-memory-projection 2024-11-13 16:45:13 +01:00
hajdul88
8e3a991dd0 feat: implements DB projection to memory 2024-11-13 16:38:57 +01:00
Leon Luithlen
45a60b7f19 Remove assert and move is_real_paragraph_end outside loop 2024-11-13 16:35:47 +01:00
hajdul88
68bfb87f3a feat: Extends graph elements with new features 2024-11-13 16:34:36 +01:00
Leon Luithlen
b787407db7 Add more adversarial examples 2024-11-13 16:23:14 +01:00
Leon Luithlen
fdec9a692e Test maximum_lenth parameter of chunk_by_sentence 2024-11-13 16:03:06 +01:00
Leon Luithlen
9ea2634480 Replace word_count with maximum_length in if clause 2024-11-13 15:53:44 +01:00
Leon Luithlen
9b2fb09c59 Fix PdfDocument teset, give chunk_by_sentence a maximum_length arg 2024-11-13 15:39:17 +01:00
Leon Luithlen
1b4a7e4fdc Adapt chunk_by_paragraph_test.py 2024-11-13 15:35:03 +01:00
Leon Luithlen
f8e5b529c3 Add maximum_length argument to chunk_sentences 2024-11-13 15:35:03 +01:00
Leon Luithlen
ef7a19043d Adapt chunk_by_paragraph test parametrization 2024-11-13 15:35:03 +01:00
Leon Luithlen
92a66dddb9 Autoformat chunking tests 2024-11-13 15:35:03 +01:00
Leon Luithlen
ce498d97dd Refactor chunk_by_paragraph to be isomorphic 2024-11-13 15:35:03 +01:00
Leon Luithlen
ab55a73d18 Adapt chunk_by_sentence to isomorphic chunk_by_word 2024-11-13 15:35:03 +01:00
Leon Luithlen
c054e897a3 Make chunk_by_word isomorphic 2024-11-13 15:35:03 +01:00
Leon Luithlen
830c6710e0 Fix chunk_by_word_test 2024-11-13 15:35:02 +01:00
Leon Luithlen
98cbaaff68 Add isomorphism tests 2024-11-13 15:35:02 +01:00
Leon Luithlen
6f0637a028 Small cosmetic changes 2024-11-13 15:35:02 +01:00
0xideas
7a72aa44d9
Merge pull request #197 from topoteretes/COG-577-add-unit-test-task
Cog 577 add unit test task
2024-11-13 15:34:13 +01:00