Commit graph

18 commits

Author SHA1 Message Date
Daniel Chalef
d7828d48d8
Fix index out of range errors in LLM deduplication responses (#939)
* add tests for llm dedupe guardrails

* document llm dedupe guardrails
2025-09-26 14:57:48 -07:00
Daniel Chalef
9aee3174bd
Refactor batch deduplication logic to enhance node resolution and track duplicate pairs (#929) (#936)
* Refactor deduplication logic to enhance node resolution and track duplicate pairs (#929)

* Simplify deduplication process in bulk_utils by reusing canonical nodes.
* Update dedup_helpers to store duplicate pairs during resolution.
* Modify node_operations to append duplicate pairs when resolving nodes.
* Add tests to verify deduplication behavior and ensure correct state updates.

* reveret to concurrent dedup with fanout and then reconcilation

* add performance note for deduplication loop in bulk_utils

* enhance deduplication logic in bulk_utils to handle missing canonical nodes gracefully

* Update graphiti_core/utils/bulk_utils.py

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>

* refactor deduplication logic in bulk_utils to use directed union-find for canonical UUID resolution

* implement _build_directed_uuid_map for efficient UUID resolution in bulk_utils

* document directed union-find lookup in bulk_utils for clarity

---------

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2025-09-26 08:40:18 -07:00
Daniel Chalef
7c469e8e2b
Improve node deduplication w/ deterministic matching, LLM fallbacks (#929)
* add repository guidelines and project structure documentation

* update neo4j image version and modify test command to disable specific databases

* implement deduplication helpers and integrate with node operations

* refactor string formatting to use single quotes in node operations

* enhance deduplication helpers with UUID indexing and update resolution logic

* implement exact fact matching (#931)
2025-09-25 07:13:19 -07:00
Preston Rasmussen
9422b6f5fb
Node dedupe efficiency (#490)
* update resolve extracted edge

* updated edge resolution

* dedupe nodes update

* single pass node resolution

* updates

* mypy updates

* Update graphiti_core/prompts/dedupe_nodes.py

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* remove unused imports

* mypy

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-05-15 13:56:33 -04:00
Preston Rasmussen
fd9969b5a1
Update dedupe prompt (#457)
* improve dedupe logic

* cut summary length

* update unit tests
2025-05-07 23:23:31 -04:00
Preston Rasmussen
1193b25fa3
add_episode() refactor (#421)
* temporal updates

* update resolve nodes

* dedupe edge updates

* edge dedupe

* extract attributes

* update dynamic pydantic model

* first pass of extract node attributes

* no errors

* bug fixes

* bug fixes

* prompt updates

* prompt updates

* updates

* updates

* remove unused imports

* update tests based on changes

* remove unused import
2025-04-30 12:08:52 -04:00
Daniel Chalef
445dccc021
refactor: use utc_now() for consistent UTC datetime handling (#234)
* ensure utc timezones

* fix: dep cycle

---------

Co-authored-by: paulpaliychuk <pavlo.paliychuk.ca@gmail.com>
2024-12-09 10:36:04 -08:00
Preston Rasmussen
3199e893ed
add_fact endpoint (#207)
* add_fact endpoint

* bump version

* add edge invalidation

* update
2024-11-06 09:12:21 -05:00
Preston Rasmussen
e15c872900
Fix edge invalidation (#174)
* update edge operations

* add new tests
2024-10-07 11:45:31 -04:00
Preston Rasmussen
42fb590606
Add group ids (#89)
* set and retrieve group ids

* update add episode with group id support

* add episode and search functional

* update bulk

* mypy updates

* remove unused imports

* update unit tests

* unit tests

* add optional uuid field

* format

* mypy

* ellipsis
2024-09-06 12:33:42 -04:00
Pavlo Paliychuk
6e8c964aef
chore: Add comments to graphiti methods (#40)
* chore: Add comments to graphiti methods

* chore: Update int test name + add header to test files

* chore: Add comments to episode type
2024-08-26 13:11:50 -04:00
Pavlo Paliychuk
0ed7739bc0
Controlled example (#37)
* chore: Add romeo runner

* fix: Linter

* dedupe fixes

* wip

* wip dump

* allbirds

* chore: Update romeo parser

* chore: Anthropic model fix

* allbirds runner

* format

* wip

* mypy updates

* update

* remove r

* update tests

* format

* wip

* wip

* wip

* chore: Strategically update the message

* chore: Add romeo runner

* fix: Linter

* wip

* wip dump

* chore: Update romeo parser

* chore: Anthropic model fix

* wip

* allbirds

* allbirds runner

* format

* wip

* wip

* mypy updates

* update

* remove r

* update tests

* format

* wip

* chore: Strategically update the message

* rebase and fix import issues

* Update package imports for graphiti_core in examples and utils

* nits

* chore: Update OpenAI GPT-4o model to gpt-4o-2024-08-06

* implement groq

* improvments & linting

* cleanup and nits

* Refactor package imports for graphiti_core in examples and utils

* Refactor package imports for graphiti_core in examples and utils

* chore: Nuke unused examples

* chore: Nuke unused examples

* chore: Only run type check on graphiti_core

* fix unit tests

* reformat

* unit test

* fix: Unit tests

* test: Add coverage for extract_date_strings_from_edge

* lint

* remove commented code

---------

Co-authored-by: prestonrasmussen <prasmuss15@gmail.com>
Co-authored-by: Daniel Chalef <131175+danielchalef@users.noreply.github.com>
2024-08-26 10:30:22 -04:00
Daniel Chalef
c5e52153c4
chore: Fix packaging (#38)
* feat: Update project name and description

The project name and description in the `pyproject.toml` file have been updated to reflect the changes made to the project.

* chore: Update pyproject.toml to include core package

The `pyproject.toml` file has been updated to include the `core` package in the list of packages. This change ensures that the `core` package is included when building the project.

* fix imports

* fix importats
2024-08-25 10:07:50 -07:00
Pavlo Paliychuk
605219f8c7
feat: Add real world dates extraction (#26)
* feat: Add real world dates extraction

* fix: Linter

* fix: 💄 mypy errors

* chore: handle invalid dates returned by the llm

* chore: Polish prompt

* reformat

* style: 💄 reformat
2024-08-23 14:18:45 -04:00
Pavlo Paliychuk
8a55f48f5e
Fix temporal invalidation unit tests (#23)
* wip

* wip

* wip

* fix: Linter errors

* fix formatting

* chore: fix ruff

* fix: Duplication

* chore: Fix unit tests for temporal invalidation

* attempt to fix unit tests

* fix: format

---------

Co-authored-by: Daniel Chalef <131175+danielchalef@users.noreply.github.com>
2024-08-22 19:02:20 -04:00
Daniel Chalef
73ec0146ff
ruff action (#17)
* ruff action

* chore: Update Python version to 3.10 in lint.yml workflow

* fix lint and formatting

* cleanup
2024-08-22 13:06:42 -07:00
Daniel Chalef
50da9d0f31
format and linting (#18)
* Makefile and format

* fix podcast stuff

* refactor: update import statement for transcript_parser in podcast_runner.py

* format and linting

* chore: Update import statements and remove unused code in maintenance module
2024-08-22 12:26:13 -07:00
Pavlo Paliychuk
a6fd0ddb75
feat: Initial version of temporal invalidation + tests (#8)
* feat: Initial version of temporal invalidation + tests

* fix: dont run int tests on CI

* fix: dont run int tests on CI

* fix: dont run int tests on CI

* fix: time of day issue

* fix: running non int tests in ci

* fix: running non int tests in ci

* fix: running non int tests in ci

* fix: running non int tests in ci

* fix: running non int tests in ci

* fix: running non int tests in ci

* fix: running non int tests in ci

* revert: Tests structural changes

* chore: Remove idea file

* chore: Get rid of NodesWithEdges class and define a triplet type instead
2024-08-20 16:29:19 -04:00