Commit graph

258 commits

Author SHA1 Message Date
Igor Ilic
599e1d478b fix: Resolve issue regrading not having Vector column type defined when using vector search
Issue happens when search is called in a session without previously adding data or creating tables as an import of Vector column type was missing

Fix
2024-12-12 13:37:18 +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
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
349ddfe794
Merge branch 'main' into COG-505-data-dataset-model-changes 2024-12-05 17:10:43 +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
f444ae21b4 fix: adds back the ids to the nodes after node_link_graph 2024-12-04 18:14:08 +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
Boris Arzentar
4678aaef52 Merge remote-tracking branch 'origin/main' 2024-12-04 11:16:16 +01:00
Boris Arzentar
d49ab4c3b5 feat: update code-graph notebook 2024-12-03 23:48:12 +01:00
Boris Arzentar
0b8b270933 fix: make get_embeddable_data static 2024-12-03 21:47:23 +01:00
Boris Arzentar
b89a4b8054 Merge remote-tracking branch 'origin/main' into code-graph 2024-12-03 21:14:19 +01:00
Boris Arzentar
27416afed0 fix: lancedb batch merge 2024-12-03 21:13:50 +01:00
alekszievr
706101113a
feat/add correctness score calculation with LLM as a judge (#30) 2024-12-03 17:47:18 +01:00
Boris Arzentar
e07364fc25 Merge remote-tracking branch 'origin/main' into code-graph 2024-12-03 12:44:57 +01:00
Igor Ilic
c301498da0 fix: Fix batch search function
Rewrite batch search to work as async gather

Fix
2024-12-03 11:58:34 +01:00
Igor Ilic
764c0895df fix: Resolve Milvus connection issue, add config to milvus test, add milvus gh action
Resolved if statement resolution issue regrading api key,
Added vector db config to milvus test,
Added milvus gh action

Fix
2024-12-03 11:13:54 +01:00
Ryan Lin
f65070087f Feature: Integrate Milvus as the VectorDatabase 2024-12-03 03:40:28 -05:00
Igor Ilic
f41228aa51 fix: Resolve import of optional package
Resolve issue with forced import of optional pgvector package.

Fix COG-595
2024-12-02 14:52:24 +01:00
Igor Ilic
343ac47fd4 fix: Update import location for LanceDB
Updated import path for LanceDB exceptions

Fix COG-502
2024-12-02 13:19:55 +01:00
Igor Ilic
04960eeb4e Merge branch 'main' of github.com:topoteretes/cognee-private into COG-502-backend-error-handling 2024-12-02 13:12:20 +01:00
Igor Ilic
34971d16cc
Cog 678 relational database singleton (#38)
1. Set relational database in cognee to be used as singleton and made
necessary changes to enable this
2. Added SQLite support to dlt pipeline in ingest_data
2024-12-02 13:02:34 +01:00
Rita Aleksziev
f966f099fc Prompt renaming to more specific names. Minor code changes. 2024-12-02 12:18:00 +01:00
Boris Arzentar
11acabdb6a fix: remove duplicate nodes and edges before saving; Fix FalkorDB vector index; 2024-12-02 10:10:18 +01:00
Boris Arzentar
d6f0d65b63 Merge remote-tracking branch 'origin/code-graph' 2024-12-01 11:51:54 +01:00
Vasilije
bbaf78f54e
Cog 669 implement dummy llm adapter (#37)
Adds the `class DummyLLMAdapter(LLMInterface)` class for profiling of
large datasets without actual LLM calls in the top level
`profiling/util` location.

I also move the `show_prompt` implementation from the child classes to
`LLMInterface`, since the implementations were identical.

I expanded the scope to also include a DummyEmbeddingEngine.
2024-11-30 17:02:49 +01:00
Vasilije
4d02560f1c
Cog 519 develop metadata storage integration (#35)
@borisarzentar this PR is ready, the all checks run through in the
"sister" MR targeting main:
https://github.com/topoteretes/cognee-private/pull/26
2024-11-30 17:02:18 +01:00
Igor Ilic
6b97e95e14 refactor: Split entity related exceptions into graph and database exceptions
Move and split database entity related exceptions into graph and database exceptions

Refactor COG-502
2024-11-29 17:40:48 +01:00
Rita Aleksziev
a4c56f118d Connect code graph pipeline + retriever + benchmarking 2024-11-29 15:24:49 +01:00
Leon Luithlen
bc82430fb5 Merge latest COG-519 2024-11-29 14:36:03 +01:00
Igor Ilic
335b8ca0de fix: Remove creation of tables for PGVector
As PGVector is used as a vector database it doesn't need to create tables based on models

Fix COG-678
2024-11-29 13:14:25 +01:00
Leon Luithlen
a5ae9185cd Replicate PR 33 2024-11-29 11:40:51 +01:00
Igor Ilic
be5cb86cb2 feat: Add singleton way of working to graph databases
Added signleton type of functioning to graph databases

Feature
2024-11-28 22:15:53 +01:00
Igor Ilic
b56a1dee59 refactor: formatting fix for PR
Fixed formatting for files in pull request

Refactor COG-678
2024-11-28 20:23:27 +01:00
Igor Ilic
56367cb0c3 feat: Add Dlt support for Sqlite
Added support for using sqlite with dlt

Feature COG-678
2024-11-28 16:50:30 +01:00
Leon Luithlen
3e1949d895 Remove unnecessary nesting in embed_text and add DummyEmbeddingEngine 2024-11-28 15:42:20 +01:00
Igor Ilic
9bd3011264 feat: Make relational databases work as singleton
Moved dlt pipeline to run in it's own fuction so it doesn't use get_relational_database.
Dlt has it's own async event loop and object can't be shared between event loops

Feature COG-678
2024-11-28 12:59:04 +01:00
Leon Luithlen
5c9fd44680 Fix DummyLLMAdapter 2024-11-28 12:26:01 +01:00
Leon Luithlen
a2ff42332e DummyLLMAdapter WIP 2024-11-28 11:49:28 +01:00
Boris Arzentar
2408fd7a01 fix: falkordb adapter errors 2024-11-28 09:12:37 +01:00
Boris
6403d15a76
fix: enable falkordb and add test for it (#31) 2024-11-27 22:55:30 +01:00
Boris Arzentar
d885a047ac Merge remote-tracking branch 'origin/main' into code-graph 2024-11-27 22:54:49 +01:00
Igor Ilic
204b5e9fe1 Merge branch 'main' of github.com:topoteretes/cognee-private into COG-502-backend-error-handling 2024-11-27 14:30:53 +01:00
Igor Ilic
ae568409a7 feat: Add custom exceptions to cognee lib
Added use of custom exceptions to cognee lib
2024-11-27 14:29:33 +01:00
hajdul88
3146ef75c9 Fix: renames new vector db and cogneegraph methods 2024-11-27 13:47:26 +01:00
Rita Aleksziev
f47b185a9e feat/add correctness score calculation with LLM as a judge 2024-11-27 10:53:48 +01:00
Boris
64b8aac86f
feat: code graph swe integration
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
Co-authored-by: hande-k <handekafkas7@gmail.com>
Co-authored-by: Igor Ilic <igorilic03@gmail.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
2024-11-27 09:32:29 +01:00
hajdul88
98a517dd9f feat: extends brute force triplet search for weaviate db 2024-11-26 17:20:53 +01:00
hajdul88
4c9d816f87 feat: extends bruteforce triplet search for Qdrant db 2024-11-26 17:05:38 +01:00
hajdul88
59f8ec665f Merge remote-tracking branch 'origin/main' into feature/cog-537-implement-retrieval-algorithm-from-research-paper 2024-11-26 16:38:32 +01:00