Commit graph

11 commits

Author SHA1 Message Date
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
Daniel Chalef
77685b063c
Feat/langgraph-example (#73)
* wip

* wip

* image + clean run

* chore: Update LANGCHAIN_TRACING_V2 to 'false' in agent.ipynb

* chore: Remove unused import in runner.ipynb

* lock file
2024-09-01 12:31:08 -07:00
Daniel Chalef
fe20c0f51d
Node Distance Reranker: Limit max hops (and cleanup prints) (#72)
* limit SHORTEST max hops

* cleanup prints
2024-09-01 12:16:04 -07:00
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
a6d63f0c0d
Add text episode type (#46)
Add a new `text` episode type and update the `extract_nodes` function to handle it.

* **EpisodeType Enum:**
  - Add `text` to the `EpisodeType` enum in `graphiti_core/nodes.py`.
  - Update the `from_str` method to handle the `text` episode type.

* **extract_nodes Function:**
  - Update the `extract_nodes` function in `graphiti_core/utils/maintenance/node_operations.py` to handle the `text` episode type.
  - Use the `message` type prompt for both `message` and `text` episodes.

---

For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/getzep/graphiti?shareId=XXXX-XXXX-XXXX-XXXX).
2024-08-26 15:51:13 -07:00
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
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