Preston Rasmussen
ecb704364e
update lucene search ( #193 )
...
* update lucene search
* update max query length
* bump version
2024-10-20 14:37:40 -07:00
Preston Rasmussen
737a3bcda6
ZEPAI-676: Remove fuzzy query in fulltext search to avoid errors with large queries ( #192 )
...
* Remove fuzzy query in fulltext search to avoid errors with large queries
* bump version
2024-10-19 11:35:25 -04:00
Preston Rasmussen
194ecf5eb4
set content to empty after episode extractions have happened ( #191 )
...
* set content to empty after episode extractions have happened
* format
* bump version
2024-10-15 12:13:14 -04:00
Preston Rasmussen
7c15b729a9
fix duplicate search results bug ( #190 )
...
* fix bugs
* format
* syntax
2024-10-14 21:54:33 -04:00
Preston Rasmussen
fca1f7342e
Node group error type ( #185 )
...
* add new error
* update for compatibility wit hdev environment
* update
* fix mmr score
* make mmr more readable
2024-10-11 16:51:32 -04:00
Preston Rasmussen
6c3b32e620
make broader use of debug logs ( #187 )
2024-10-11 16:38:56 -04:00
Preston Rasmussen
49aeaf75f2
Add mmr reranking ( #180 )
...
* mmr start
* add mmr function
* normalize
* add mmr options to search
* update communities
* build communities
* format
* clean up normalization
* normalize in mmr
* update
2024-10-08 13:55:10 -04:00
Preston Rasmussen
e15c872900
Fix edge invalidation ( #174 )
...
* update edge operations
* add new tests
2024-10-07 11:45:31 -04:00
Preston Rasmussen
377225eec5
add addepisode return object ( #172 )
...
* add addepisode return
* format
2024-10-03 15:39:57 -04:00
Preston Rasmussen
c8ff5be8ce
Msc benchmark update ( #173 )
...
* eval update
* I sped it up
* make format
* search updates
* updates
* cleanup
* make format
* remove unused imports
* poetry lock
2024-10-03 15:39:35 -04:00
Preston Rasmussen
ec2e51c5ec
test escape characters ( #171 )
...
* test escape characters
* format
* tests
* run tests
* copyright
2024-10-03 10:08:30 -04:00
Preston Rasmussen
ae9b5eca9c
update lucene sanitizer ( #170 )
...
* update lucene sanitizer
* update
2024-10-02 11:58:12 -04:00
Pavlo Paliychuk
a7148d6260
feat: Dedicated embedder interface ( #159 )
...
* feat: Add Embedder interface and implement openai embedder
* feat: Add voyage ai embedder
2024-09-27 12:47:04 -04:00
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
b537cf56e5
chore: Make deleting groups safer ( #155 )
...
* chore: Make deleting groups safer
* chore: Use appropriate errors in delete group checks
* chore: Add GroupsEdgesNotFound error type
2024-09-24 20:08:09 -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
Daniel Chalef
5d2121e1a3
limit community building concurrency ( #142 )
2024-09-22 13:38:54 -07:00
Daniel Chalef
14d5ce0b36
Override default max tokens for Anthropic and Groq clients ( #143 )
...
* Override default max tokens for Anthropic and Groq clients
* Override default max tokens for Anthropic and Groq clients
* Override default max tokens for Anthropic and Groq clients
2024-09-22 11:33:54 -07:00
Daniel Chalef
a1d871e179
chore: Update DEFAULT_MAX_TOKENS to 16384 in config.py ( #138 )
2024-09-22 09:57:41 -07:00
Daniel Chalef
9b71b46c0f
feat: Refactor OpenAIClient initialization and add client parameter ( #140 )
...
The code changes refactor the `OpenAIClient` initialization to accept an optional `client` parameter. This allows the client to be passed in from outside, providing more flexibility and enabling easier testing.
2024-09-21 12:09:04 -07:00
Daniel Chalef
32b51530ec
feat: Fix bug in dedupe_node_list function ( #137 )
...
The code changes fix a bug in the `dedupe_node_list` function where a node instance was not found in the node map. The bug is now handled by logging a warning message and skipping the iteration. This ensures that the function continues to execute without any errors.
2024-09-20 21:03:20 -07:00
Daniel Chalef
6d065d363a
Handle JSONDecodeError in is_server_or_retry_error function ( #133 )
...
feat: handle JSONDecodeError in is_server_or_retry_error function
2024-09-20 11:16:04 -07:00
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
Pavlo Paliychuk
529a1aaecf
fix: update UUID generation and message handling ( #123 )
...
* chore: Update uuid generation + service fixes
* chore: Version bump
2024-09-18 12:48:44 -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
Pavlo Paliychuk
ebb1ec2463
fix: Syntax error on node crud ( #119 )
2024-09-17 12:19:20 -04:00
Pavlo Paliychuk
19a6ebc6fe
Fix groupless search ( #118 )
...
* fix(search): 🐛 Search across null group_ids
* chore: Version bump
* chore: Set group_ids to none if it's an empty list
* fix: Check for group ids being a list before setting it to None if empty
* fix check
* chore: Simplify group_ids check
* chore: Simplify the check further
2024-09-16 16:23:07 -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
85cf8e5840
Improve node distance reranker speed ( #107 )
...
* much faster
* clean up code
* variable rename
2024-09-12 11:23:45 -04:00
Pavlo Paliychuk
8085b52f2a
feat: add error handling for missing nodes and edges, introduce new API endpoints, and update ZepGraphiti class ( #104 )
...
* feat: Expose crud operations to service + add graphiti errors
* fix: linter
2024-09-11 12:53:17 -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
Preston Rasmussen
4122d350a5
add extract nodes from text prompt ( #106 )
2024-09-11 12:06:08 -04:00
Daniel Chalef
b214baa85f
Add py.typed file ( #105 )
...
* Add py.typed file
---
For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/getzep/graphiti?shareId=XXXX-XXXX-XXXX-XXXX ).
* Update pyproject.toml
2024-09-11 08:44:06 -04:00
Daniel Chalef
6851b1063a
Fix llm client retry ( #102 )
...
* Fix llm client retry
* feat: Improve llm client retry error message
2024-09-10 08:15:27 -07:00
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
a29c3557d3
fix clearing name embeddings bug ( #87 )
...
fix bug
2024-09-05 14:09:19 -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
Preston Rasmussen
06d8d9359f
Add Missing Node and edge CRUD ( #51 )
...
* add CRUD operations and fix search limit bugs
* format
* update tests
* å
* update tests to double limit call
* add default field
* format
* import correct field
2024-08-27 16:18:01 -04:00
Pavlo Paliychuk
e821a6195a
chore: Move anthropic to dev deps, remove anthropic and groq clients from __init__ ( #61 )
2024-08-27 16:03:08 -04:00
