74 Commits

Author SHA1 Message Date
ARNO
5bd18fc7dd
feat: configurable embedding model (#156)
* feat: configurable embedding model

format

* chore: Update comment

* chore: Pass embedding model in search utils

---------

Co-authored-by: paulpaliychuk <pavlo.paliychuk.ca@gmail.com>
2024-09-26 13:31:22 -07:00
Preston Rasmussen
fd341a6f16
Add MSC benchmark and improve search performance (#157)
* test cases

* test

* benchmark

* eval updates

* improve search performance

* remove data

* formatting

* add None type to config

* update sanitization

* push version

* maketrans update

* mypy
2024-09-26 16:12:38 -04:00
Pavlo Paliychuk
44b016da6b
feat: async close and multi-group search support (#151)
* chore: Support a list of group_ids on search + await driver.close()

* fix: formatter and linter

* chore: Version bump
2024-09-24 16:13:04 -04:00
Preston Rasmussen
794b705664
Group id fix (#152)
* node distance and group_ids fixed

* get all with no group_id passed

* push

* push

* remove comments

* mypy

* mypy ids

* please mypy

* trust

* last one
2024-09-24 15:55:30 -04:00
Preston Rasmussen
5506a01e24
In memory label propagation community detection (#136)
* WIP

* in memory graph detection

* format

* add comments

* update readme

* fixed an issue where solo nodes would throw an error when building communities
2024-09-23 11:05:44 -04:00
Pavlo Paliychuk
2fc1b00602
feat: add FastAPI lifespan and healthcheck endpoint (#144)
* chore: Add healthcheck endpoint + build indexes and constraints on svc startup

* chore: Bring back driver close call
2024-09-23 10:12:35 -04:00
Preston Rasmussen
bfd8d3bb68
Add group_id CRUD endpoints and option store content bool (#130)
* add group_ids CRUD

* option to not store content

* ellipsis
2024-09-19 16:16:40 -04:00
Preston Rasmussen
e398f95612
Mentions reranker (#124)
* documentation update

* update communities

* mentions reranker

* fix episode edge mentions

* get episode mentions

* add communities to mentions endpoint

* rebase

* defaults episodes to empty list

* update
2024-09-18 15:44:28 -04:00
Preston Rasmussen
a18b3179ee
Add community update (#121)
* documentation update

* update communities

* update runner

* make format

* mypy

* oops

* add update_communities
2024-09-18 11:37:34 -04:00
Preston Rasmussen
d7c20c1f59
Search refactor + Community search (#111)
* WIP

* WIP

* WIP

* community search

* WIP

* WIP

* integration tested

* tests

* tests

* mypy

* mypy

* format
2024-09-16 14:03:05 -04:00
Preston Rasmussen
c0a740ff60
Community nodes (#103)
* add gds

* community work

* save progress

* community updates

* e2e communities

* troubleshooting

* updates

* communities

* remove unused import
2024-09-11 12:06:35 -04:00
Daniel Chalef
3f12254916
Fix missing default None for add_episode_bulk (#101)
Fix missing default None for add_episode and add_episode_bulk



---

For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/getzep/graphiti?shareId=XXXX-XXXX-XXXX-XXXX).
2024-09-09 22:12:59 -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
Preston Rasmussen
299021173b
Add episode refactor (#85)
* temp commit while moving

* fix name embedding bug

* invalidation

* format

* tests on runner examples

* format

* ellipsis

* ruff

* fix

* format

* minor prompt change
2024-09-05 12:05:44 -04:00
Preston Rasmussen
e56a599a72
search update (#81)
* search update

* update string literals
2024-09-04 10:05:45 -04:00
Preston Rasmussen
e9e6039b1e
Speed up add episode (#77)
* WIP

* updates

* use uuid for node dedupe

* pret-testing

* parallelized node resolution

* working add_episode

* revert to 4o

* format

* mypy update

* update types
2024-09-03 13:25:52 -04:00
Preston Rasmussen
35a4e5172b
add bulk temporal extraction and improve bulk quality and performance (#67)
* parallelize edge deduping more

* parallelize node insertion more

* improve bulk behavior performance

* dedupe nodes actually works

* add a reranker to search

* bulk dedupe episodes only across the same nodes

* add temporal extraction bulk function

* cleaned up bulk

* default to 4o

* format

* mypy

* mympy

* mypy ignore
2024-08-30 10:48:28 -04:00
Daniel Chalef
2d0705fc1b
Add get_nodes_by_query method to Graphiti class (#49)
* Add get_nodes_by_query method to Graphiti class

Add a method to the Graphiti class that wraps `get_relevant_nodes` and returns a list of nodes given a query.

* Add `get_nodes_by_query` method to the `Graphiti` class in `graphiti_core/graphiti.py`.
* Import `generate_embedding` from `graphiti_core/llm_client/utils.py`.
* Use `generate_embedding` to generate an embedding for the query.
* Call `get_relevant_nodes` with the generated embedding and return the relevant nodes.

Add an embedding function to `llm_client/utils.py`.

* Add `generate_embedding` function to `graphiti_core/llm_client/utils.py`.
* Accept an embedder and model_id as parameters.
* Generate an embedding for the given text and return it.

---

For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/getzep/graphiti?shareId=XXXX-XXXX-XXXX-XXXX).

* address comments left by @danielchalef on #49 (Add get_nodes_by_query method to Graphiti class);

* fix ellipsis name in cla config

* feat: Add get_nodes_by_query method to Graphiti class

* chore: Cleanup unused files, add hybrid node search, add tests

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: paulpaliychuk <pavlo.paliychuk.ca@gmail.com>
2024-08-26 20:00:28 -07:00
Daniel Chalef
7ca4f7fe5b
Update search method to return EntityEdge objects (#48)
---

For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/getzep/graphiti?shareId=XXXX-XXXX-XXXX-XXXX).
2024-08-26 17:24:35 -07:00
Preston Rasmussen
2d01e5d7b7
Search node centering (#45)
* add new search reranker and update search

* node distance reranking

* format

* rebase

* no need for enumerate

* mypy typing

* defaultdict update

* rrf prelim ranking
2024-08-26 18:34:57 -04:00
Daniel Chalef
895afc7be1
implement diskcache (#39)
* 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

* implement diskcache

* remove debug stuff

* log cache hit when debugging only

* Improve LLM config. Fix bugs (#41)

Refactor LLMConfig class to allow None values for model and base_url

* chore: Resolve mc

---------

Co-authored-by: paulpaliychuk <pavlo.paliychuk.ca@gmail.com>
Co-authored-by: prestonrasmussen <prasmuss15@gmail.com>
2024-08-26 13:13:05 -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