Igor Ilic
07d9330e4a
feat: Add UnstructuredLibraryImportError
...
Added exception when unstructured libary is called but not installed
Feature COG-685
2024-12-08 14:53:19 +01:00
Igor Ilic
53b7806ccb
chore: Update pyproject file with unstructured library
...
Add unstructured library as docs optional extension to pyproject.toml
Chore COG-685
2024-12-08 14:42:08 +01:00
Igor Ilic
62db3f8598
feat: Remove the need for libmagic for unstructured documents
...
Remove the need for libmagic so for unstructured documents by providing mime_type information
Feature COG-685
2024-12-08 14:37:50 +01:00
Igor Ilic
78214456a6
feat: Add unstructured document handler
...
Added unstructured library and handling of certain document types through their library
Feature COG-685
2024-12-06 17:50:22 +01:00
Igor Ilic
8415279cb2
Merge pull request #260 from topoteretes/COG-505-data-dataset-model-changes
...
Cog 505 data dataset model changes
2024-12-06 14:42:35 +01:00
Igor Ilic
d7fa9f3cfd
Merge branch 'COG-505-data-dataset-model-changes' of github.com:topoteretes/cognee into COG-505-data-dataset-model-changes
2024-12-06 13:49:07 +01:00
Igor Ilic
cc6fbe2a5f
refactor: Add space to ingest function
...
Add space and newline to ingest function
Refactor COG-505
2024-12-06 13:48:39 +01:00
Boris
9429e5e1f5
Merge branch 'main' into COG-505-data-dataset-model-changes
2024-12-06 12:53:32 +01:00
Boris
348610e73c
fix: refactor get_graph_from_model to return nodes and edges correctly ( #257 )
...
* fix: handle rate limit error coming from llm model
* fix: fixes lost edges and nodes in get_graph_from_model
* fix: fixes database pruning issue in pgvector (#261 )
* fix: cognee_demo notebook pipeline is not saving summaries
---------
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
2024-12-06 12:52:01 +01:00
Igor Ilic
351ce92001
Merge pull request #263 from topoteretes/gh-actions-all-branches
...
test: Update gh actions so they can run outside of PR to main
2024-12-06 12:04:47 +01:00
Igor Ilic
d254471023
test: Update gh actions so they can run outside of PR to main
...
Allow github actions to run on PRs that aren't targeting main
Test
2024-12-06 11:09:26 +01:00
Igor Ilic
1e098ae70d
refactor: Add error handling to hash util
...
Added error handling to reading of file in hash util
Refactor COG-505
2024-12-05 20:54:55 +01:00
Igor Ilic
e80377b729
refactor: Move hash calculation of file to util
...
Moved hash calculation of file to shared utils, added better typing
Refactor COG-505
2024-12-05 20:33:30 +01:00
Igor Ilic
9ba5d49e69
test: Fix test for multimedia deduplication
...
Add missing function to get data from database to multimedia deduplication test
Test COG-505
2024-12-05 20:09:29 +01:00
Igor Ilic
add6730b9e
test: Add testing of dataset data table content
...
Add testing of dataset data table content
Test COG-505
2024-12-05 19:37:12 +01:00
Igor Ilic
387002d8ca
Merge branch 'COG-505-data-dataset-model-changes' of github.com:topoteretes/cognee into COG-505-data-dataset-model-changes
2024-12-05 19:26:17 +01:00
Igor Ilic
813b76c9c2
test: Add test for text deduplication
...
Added end to end test for text deduplication
Test COG-505
2024-12-05 19:25:50 +01:00
Igor Ilic
349ddfe794
Merge branch 'main' into COG-505-data-dataset-model-changes
2024-12-05 17:10:43 +01:00
Igor Ilic
378e7b81a5
fix: Fix merge of data for dlt
...
Resolve issue with dlt data not being merged for data_id
Fix COG-505
2024-12-05 17:03:36 +01:00
Igor Ilic
f5b5e56cc1
feat: Add deduplication of data
...
Data is deduplicated per user so if a user tries to add data which already exists it will just be redirected to existing data in database
Feature COG-505
2024-12-05 16:38:44 +01:00
hajdul88
acf036818e
Merge pull request #251 from topoteretes/feature/cog-717-create-edge-embeddings-in-vector-databases
...
Creates edge embeddings collection
2024-12-05 09:13:11 +01:00
hajdul88
68c3f42ab8
Merge branch 'main' into feature/cog-717-create-edge-embeddings-in-vector-databases
2024-12-05 09:08:37 +01:00
Vasilije
c4ad473861
Merge pull request #253 from topoteretes/feat/COG-711-temporal-awareness-task
...
Integrate graphiti's temporal awareness functionality as Tasks
2024-12-04 20:50:03 +01:00
Vasilije
b571fb5626
Merge branch 'main' into feat/COG-711-temporal-awareness-task
2024-12-04 20:49:36 +01:00
hajdul88
7f192e1c2b
Merge branch 'main' into feature/cog-717-create-edge-embeddings-in-vector-databases
2024-12-04 20:49:30 +01:00
Vasilije
7223b2c83b
Merge pull request #256 from topoteretes/fix-notebook-gh-actions
...
chore: Fix issue with notebook github actions
2024-12-04 20:42:18 +01:00
Igor Ilic
6be025e3d4
chore: Attempt to fix issue with notebook github actions
...
Attempt to resolve issue with running notebooks in github actions
Chore
2024-12-04 20:36:23 +01:00
hajdul88
59035c3f45
fix: puts index_graph_edges unit tests under unit test directory
2024-12-04 19:32:15 +01:00
hajdul88
e6bf428db5
feat: implements tests for index_graph_edges method
2024-12-04 19:27:09 +01:00
hajdul88
36a5a27f10
Merge branch 'main' into feature/cog-717-create-edge-embeddings-in-vector-databases
2024-12-04 18:15:46 +01:00
hajdul88
f444ae21b4
fix: adds back the ids to the nodes after node_link_graph
2024-12-04 18:14:08 +01:00
alekszievr
cedb9d6608
Merge branch 'main' into feat/COG-711-temporal-awareness-task
2024-12-04 17:31:50 +01:00
alekszievr
ac62e9809a
Skip empty files in get repo file dependencies ( #254 )
...
Co-authored-by: Rita Aleksziev <alekszievr@gmail..com>
2024-12-04 17:29:07 +01:00
Igor Ilic
0ce254b262
feat: Add text deduplication
...
If text is added to cognee it will be saved by hash so the same text can't be stored multiple times
Feature COG-505
2024-12-04 17:19:29 +01:00
Rita Aleksziev
5d71059f6c
fix credentials
2024-12-04 17:00:48 +01:00
alekszievr
0d2a9e9e17
Merge branch 'main' into feat/COG-711-temporal-awareness-task
2024-12-04 16:34:11 +01:00
Rita Aleksziev
dd94781033
Integrate graphiti's functionality as Tasks
2024-12-04 16:33:26 +01:00
Vasilije
080143cdad
Merge branch 'main' into feature/cog-717-create-edge-embeddings-in-vector-databases
2024-12-04 16:33:08 +01:00
alekszievr
df8fc829f9
check if repo path exists before starting the pipeline ( #252 )
...
Co-authored-by: Rita Aleksziev <alekszievr@gmail..com>
2024-12-04 16:25:05 +01:00
Igor Ilic
6bb0f3d8f2
feat: Add ability to store single data instance in multiple datasets
...
Added ability to store single data instance in multiple datasets
Feature COG-505
2024-12-04 15:53:25 +01:00
hajdul88
c20ee11e80
feat: implements graph edge indexing
2024-12-04 15:37:48 +01:00
hajdul88
46ee513f6c
chore: deletes comment from dynamic_steps_example
2024-12-04 14:59:01 +01:00
Igor Ilic
d793a5d9b5
Merge pull request #249 from topoteretes/fix-metadata-update
...
fix: Resolve issue when metadata is updated
2024-12-04 14:14:04 +01:00
Igor Ilic
0a0b030df5
fix: Resolve issue when metadata is updated
...
Resolve issue when attempting to update metadata related to data
Fix
2024-12-04 14:03:01 +01:00
Igor Ilic
3699b0dccb
Merge pull request #248 from topoteretes/fix-milvus-adapter
...
fix: Resolve issue with embedding data points for Milvus
2024-12-04 12:20:08 +01:00
Igor Ilic
58b17e5738
fix: Resolve issue with embedding data points for Milvus
...
Resolve issue with embedding data points for Milvus
fix
2024-12-04 12:12:25 +01:00
Vasilije
1a963f1dc8
Merge pull request #247 from topoteretes/fix-dlt-for-metadata
...
Fix dlt for metadata
2024-12-04 12:05:08 +01:00
Igor Ilic
c505ee5f98
Merge branch 'main' into fix-dlt-for-metadata
2024-12-04 11:56:41 +01:00
Igor Ilic
ceebcdb251
fix: Resolve issue with llama index type resolution
...
Resolve issue with llama index type resolution
Fix
2024-12-04 11:29:27 +01:00
Boris Arzentar
4678aaef52
Merge remote-tracking branch 'origin/main'
2024-12-04 11:16:16 +01:00
