Merge branch 'main' of github.com:getzep/graphiti into extract-dates-…

…from-context

# Conflicts:
#	core/graphiti.py
#	core/prompts/dedupe_edges.py
#	core/prompts/invalidate_edges.py
#	core/utils/bulk_utils.py
#	core/utils/maintenance/edge_operations.py
#	core/utils/maintenance/node_operations.py
#	core/utils/maintenance/temporal_operations.py
#	core/utils/search/search_utils.py
#	runner.py

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "pip" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"

.github/workflows/lint.yml

@@ -0,0 +1,24 @@
+name: Lint with Ruff
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    branches: ["main"]
+
+jobs:
+  ruff:
+    environment: development
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install "ruff>0.1.7"
+      - name: Run Ruff linting
+        run: ruff check --output-format=github

.github/workflows/unit_tests.yml

@@ -9,6 +9,8 @@ on:
 jobs:
   test:
     runs-on: ubuntu-latest
+    environment:
+      name: development
     steps:
     - uses: actions/checkout@v3
     - name: Set up Python

Makefile

@@ -0,0 +1,32 @@
+.PHONY: install format lint test all check
+
+# Define variables
+PYTHON = python3
+POETRY = poetry
+PYTEST = $(POETRY) run pytest
+RUFF = $(POETRY) run ruff
+MYPY = $(POETRY) run mypy
+
+# Default target
+all: format lint test
+
+# Install dependencies
+install:
+	$(POETRY) install --with dev
+
+# Format code
+format:
+	$(RUFF) check --select I --fix
+	$(RUFF) format
+
+# Lint code
+lint:
+	$(RUFF) check
+# 	$(MYPY) .
+
+# Run tests
+test:
+	$(PYTEST)
+
+# Run format, lint, and test
+check: format lint test

README.md

@@ -47,4 +47,4 @@ graphiti.close()
 
 ## License
 
-(Add license information)
+(Add license information)

SECURITY.md

@@ -0,0 +1,15 @@
+# Security Policy
+
+## Supported Versions
+
+Use this section to tell people about which versions of your project are
+currently being supported with security updates.
+
+| Version | Supported          |
+|---------|--------------------|
+| 0.x     | :white_check_mark: |
+
+
+## Reporting a Vulnerability
+
+Please use GitHub's Private Vulnerability Reporting mechanism found in the Security section of this repo.

conftest.py

@@ -1,5 +1,5 @@
-import sys
 import os
+import sys
 
 # This code adds the project root directory to the Python path, allowing imports to work correctly when running tests.
 # Without this file, you might encounter ModuleNotFoundError when trying to import modules from your project, especially when running tests.

core/__init__.py

@@ -1,3 +1,3 @@
 from .graphiti import Graphiti
 
-__all__ = ["Graphiti"]
+__all__ = ['Graphiti']

core/edges.py

@@ -1,10 +1,11 @@
+import logging
 from abc import ABC, abstractmethod
-from pydantic import BaseModel, Field
 from datetime import datetime
 from time import time
-from neo4j import AsyncDriver
 from uuid import uuid4
-import logging
+
+from neo4j import AsyncDriver
+from pydantic import BaseModel, Field
 
 from core.llm_client.config import EMBEDDING_DIM
 from core.nodes import Node
@@ -13,104 +14,100 @@
 
 
 class Edge(BaseModel, ABC):
-    uuid: str = Field(default_factory=lambda: uuid4().hex)
-    source_node_uuid: str
-    target_node_uuid: str
-    created_at: datetime
+	uuid: str = Field(default_factory=lambda: uuid4().hex)
+	source_node_uuid: str
+	target_node_uuid: str
+	created_at: datetime
 
-    @abstractmethod
-    async def save(self, driver: AsyncDriver): ...
+	@abstractmethod
+	async def save(self, driver: AsyncDriver): ...
 
-    def __hash__(self):
-        return hash(self.uuid)
+	def __hash__(self):
+		return hash(self.uuid)
 
-    def __eq__(self, other):
-        if isinstance(other, Node):
-            return self.uuid == other.uuid
-        return False
+	def __eq__(self, other):
+		if isinstance(other, Node):
+			return self.uuid == other.uuid
+		return False
 
 
 class EpisodicEdge(Edge):
-    async def save(self, driver: AsyncDriver):
-        result = await driver.execute_query(
-            """
+	async def save(self, driver: AsyncDriver):
+		result = await driver.execute_query(
+			"""
         MATCH (episode:Episodic {uuid: $episode_uuid}) 
         MATCH (node:Entity {uuid: $entity_uuid}) 
         MERGE (episode)-[r:MENTIONS {uuid: $uuid}]->(node)
         SET r = {uuid: $uuid, created_at: $created_at}
         RETURN r.uuid AS uuid""",
-            episode_uuid=self.source_node_uuid,
-            entity_uuid=self.target_node_uuid,
-            uuid=self.uuid,
-            created_at=self.created_at,
-        )
+			episode_uuid=self.source_node_uuid,
+			entity_uuid=self.target_node_uuid,
+			uuid=self.uuid,
+			created_at=self.created_at,
+		)
 
-        logger.info(f"Saved edge to neo4j: {self.uuid}")
+		logger.info(f'Saved edge to neo4j: {self.uuid}')
 
-        return result
+		return result
 
 
 # TODO: Neo4j doesn't support variables for edge types and labels.
 #  Right now we have all edge nodes as type RELATES_TO
 
 
 class EntityEdge(Edge):
-    name: str = Field(description="name of the edge, relation name")
-    fact: str = Field(
-        description="fact representing the edge and nodes that it connects"
-    )
-    fact_embedding: list[float] | None = Field(
-        default=None, description="embedding of the fact"
-    )
-    episodes: list[str] | None = Field(
-        default=None,
-        description="list of episode ids that reference these entity edges",
-    )
-    expired_at: datetime | None = Field(
-        default=None, description="datetime of when the node was invalidated"
-    )
-    valid_at: datetime | None = Field(
-        default=None, description="datetime of when the fact became true"
-    )
-    invalid_at: datetime | None = Field(
-        default=None, description="datetime of when the fact stopped being true"
-    )
-
-    async def generate_embedding(self, embedder, model="text-embedding-3-small"):
-        start = time()
-
-        text = self.fact.replace("\n", " ")
-        embedding = (await embedder.create(input=[text], model=model)).data[0].embedding
-        self.fact_embedding = embedding[:EMBEDDING_DIM]
-
-        end = time()
-        logger.info(f"embedded {text} in {end-start} ms")
-
-        return embedding
-
-    async def save(self, driver: AsyncDriver):
-        result = await driver.execute_query(
-            """
+	name: str = Field(description='name of the edge, relation name')
+	fact: str = Field(description='fact representing the edge and nodes that it connects')
+	fact_embedding: list[float] | None = Field(default=None, description='embedding of the fact')
+	episodes: list[str] | None = Field(
+		default=None,
+		description='list of episode ids that reference these entity edges',
+	)
+	expired_at: datetime | None = Field(
+		default=None, description='datetime of when the node was invalidated'
+	)
+	valid_at: datetime | None = Field(
+		default=None, description='datetime of when the fact became true'
+	)
+	invalid_at: datetime | None = Field(
+		default=None, description='datetime of when the fact stopped being true'
+	)
+
+	async def generate_embedding(self, embedder, model='text-embedding-3-small'):
+		start = time()
+
+		text = self.fact.replace('\n', ' ')
+		embedding = (await embedder.create(input=[text], model=model)).data[0].embedding
+		self.fact_embedding = embedding[:EMBEDDING_DIM]
+
+		end = time()
+		logger.info(f'embedded {text} in {end-start} ms')
+
+		return embedding
+
+	async def save(self, driver: AsyncDriver):
+		result = await driver.execute_query(
+			"""
         MATCH (source:Entity {uuid: $source_uuid}) 
         MATCH (target:Entity {uuid: $target_uuid}) 
         MERGE (source)-[r:RELATES_TO {uuid: $uuid}]->(target)
         SET r = {uuid: $uuid, name: $name, fact: $fact, fact_embedding: $fact_embedding, 
         episodes: $episodes, created_at: $created_at, expired_at: $expired_at, 
         valid_at: $valid_at, invalid_at: $invalid_at}
         RETURN r.uuid AS uuid""",
-            source_uuid=self.source_node_uuid,
-            target_uuid=self.target_node_uuid,
-            uuid=self.uuid,
-            name=self.name,
-            fact=self.fact,
-            fact_embedding=self.fact_embedding,
-            episodes=self.episodes,
-            created_at=self.created_at,
-            expired_at=self.expired_at,
-            valid_at=self.valid_at,
-            invalid_at=self.invalid_at,
-        )
-
-        logger.info(f"Saved edge to neo4j: {self.uuid}")
-
-        return result
+			source_uuid=self.source_node_uuid,
+			target_uuid=self.target_node_uuid,
+			uuid=self.uuid,
+			name=self.name,
+			fact=self.fact,
+			fact_embedding=self.fact_embedding,
+			episodes=self.episodes,
+			created_at=self.created_at,
+			expired_at=self.expired_at,
+			valid_at=self.valid_at,
+			invalid_at=self.invalid_at,
+		)
+
+		logger.info(f'Saved edge to neo4j: {self.uuid}')
+
+		return result