graphiti-core 0.22.0rc4__py3-none-any.whl → 0.22.1rc1__py3-none-any.whl

graphiti_core/nodes.py

@@ -27,10 +27,6 @@ from pydantic import BaseModel, Field
 from typing_extensions import LiteralString
 
 from graphiti_core.driver.driver import (
-    COMMUNITY_INDEX_NAME,
-    ENTITY_EDGE_INDEX_NAME,
-    ENTITY_INDEX_NAME,
-    EPISODE_INDEX_NAME,
     GraphDriver,
     GraphProvider,
 )
@@ -99,6 +95,9 @@ class Node(BaseModel, ABC):
     async def save(self, driver: GraphDriver): ...
 
     async def delete(self, driver: GraphDriver):
+        if driver.graph_operations_interface:
+            return await driver.graph_operations_interface.node_delete(self, driver)
+
         match driver.provider:
             case GraphProvider.NEO4J:
                 records, _, _ = await driver.execute_query(
@@ -113,27 +112,6 @@ class Node(BaseModel, ABC):
                     uuid=self.uuid,
                 )
 
-                edge_uuids: list[str] = records[0].get('edge_uuids', []) if records else []
-
-                if driver.aoss_client:
-                    # Delete the node from OpenSearch indices
-                    for index in (EPISODE_INDEX_NAME, ENTITY_INDEX_NAME, COMMUNITY_INDEX_NAME):
-                        await driver.aoss_client.delete(
-                            index=index,
-                            id=self.uuid,
-                            params={'routing': self.group_id},
-                        )
-
-                    # Bulk delete the detached edges
-                    if edge_uuids:
-                        actions = []
-                        for eid in edge_uuids:
-                            actions.append(
-                                {'delete': {'_index': ENTITY_EDGE_INDEX_NAME, '_id': eid}}
-                            )
-
-                        await driver.aoss_client.bulk(body=actions)
-
             case GraphProvider.KUZU:
                 for label in ['Episodic', 'Community']:
                     await driver.execute_query(
@@ -181,14 +159,18 @@ class Node(BaseModel, ABC):
 
     @classmethod
     async def delete_by_group_id(cls, driver: GraphDriver, group_id: str, batch_size: int = 100):
+        if driver.graph_operations_interface:
+            return await driver.graph_operations_interface.node_delete_by_group_id(
+                cls, driver, group_id, batch_size
+            )
+
         match driver.provider:
             case GraphProvider.NEO4J:
                 async with driver.session() as session:
                     await session.run(
                         """
                         MATCH (n:Entity|Episodic|Community {group_id: $group_id})
-                        CALL {
-                            WITH n
+                        CALL (n) {
                             DETACH DELETE n
                         } IN TRANSACTIONS OF $batch_size ROWS
                         """,
@@ -196,31 +178,6 @@ class Node(BaseModel, ABC):
                         batch_size=batch_size,
                     )
 
-                if driver.aoss_client:
-                    await driver.aoss_client.delete_by_query(
-                        index=EPISODE_INDEX_NAME,
-                        body={'query': {'term': {'group_id': group_id}}},
-                        params={'routing': group_id},
-                    )
-
-                    await driver.aoss_client.delete_by_query(
-                        index=ENTITY_INDEX_NAME,
-                        body={'query': {'term': {'group_id': group_id}}},
-                        params={'routing': group_id},
-                    )
-
-                    await driver.aoss_client.delete_by_query(
-                        index=COMMUNITY_INDEX_NAME,
-                        body={'query': {'term': {'group_id': group_id}}},
-                        params={'routing': group_id},
-                    )
-
-                    await driver.aoss_client.delete_by_query(
-                        index=ENTITY_EDGE_INDEX_NAME,
-                        body={'query': {'term': {'group_id': group_id}}},
-                        params={'routing': group_id},
-                    )
-
             case GraphProvider.KUZU:
                 for label in ['Episodic', 'Community']:
                     await driver.execute_query(
@@ -258,6 +215,11 @@ class Node(BaseModel, ABC):
 
     @classmethod
     async def delete_by_uuids(cls, driver: GraphDriver, uuids: list[str], batch_size: int = 100):
+        if driver.graph_operations_interface:
+            return await driver.graph_operations_interface.node_delete_by_uuids(
+                cls, driver, uuids, group_id=None, batch_size=batch_size
+            )
+
         match driver.provider:
             case GraphProvider.FALKORDB:
                 for label in ['Entity', 'Episodic', 'Community']:
@@ -300,7 +262,7 @@ class Node(BaseModel, ABC):
             case _:  # Neo4J, Neptune
                 async with driver.session() as session:
                     # Collect all edge UUIDs before deleting nodes
-                    result = await session.run(
+                    await session.run(
                         """
                         MATCH (n:Entity|Episodic|Community)
                         WHERE n.uuid IN $uuids
@@ -310,18 +272,12 @@ class Node(BaseModel, ABC):
                         uuids=uuids,
                     )
 
-                    record = await result.single()
-                    edge_uuids: list[str] = (
-                        record['edge_uuids'] if record and record['edge_uuids'] else []
-                    )
-
                     # Now delete the nodes in batches
                     await session.run(
                         """
                         MATCH (n:Entity|Episodic|Community)
                         WHERE n.uuid IN $uuids
-                        CALL {
-                            WITH n
+                        CALL (n) {
                             DETACH DELETE n
                         } IN TRANSACTIONS OF $batch_size ROWS
                         """,
@@ -329,20 +285,6 @@ class Node(BaseModel, ABC):
                         batch_size=batch_size,
                     )
 
-                if driver.aoss_client:
-                    for index in (EPISODE_INDEX_NAME, ENTITY_INDEX_NAME, COMMUNITY_INDEX_NAME):
-                        await driver.aoss_client.delete_by_query(
-                            index=index,
-                            body={'query': {'terms': {'uuid': uuids}}},
-                        )
-
-                    if edge_uuids:
-                        actions = [
-                            {'delete': {'_index': ENTITY_EDGE_INDEX_NAME, '_id': eid}}
-                            for eid in edge_uuids
-                        ]
-                        await driver.aoss_client.bulk(body=actions)
-
     @classmethod
     async def get_by_uuid(cls, driver: GraphDriver, uuid: str): ...
 
@@ -363,6 +305,9 @@ class EpisodicNode(Node):
     )
 
     async def save(self, driver: GraphDriver):
+        if driver.graph_operations_interface:
+            return await driver.graph_operations_interface.episodic_node_save(self, driver)
+
         episode_args = {
             'uuid': self.uuid,
             'name': self.name,
@@ -375,12 +320,6 @@ class EpisodicNode(Node):
             'source': self.source.value,
         }
 
-        if driver.aoss_client:
-            await driver.save_to_aoss(  # pyright: ignore reportAttributeAccessIssue
-                'episodes',
-                [episode_args],
-            )
-
         result = await driver.execute_query(
             get_episode_node_save_query(driver.provider), **episode_args
         )
@@ -510,26 +449,14 @@ class EntityNode(Node):
         return self.name_embedding
 
     async def load_name_embedding(self, driver: GraphDriver):
+        if driver.graph_operations_interface:
+            return await driver.graph_operations_interface.node_load_embeddings(self, driver)
+
         if driver.provider == GraphProvider.NEPTUNE:
             query: LiteralString = """
                 MATCH (n:Entity {uuid: $uuid})
                 RETURN [x IN split(n.name_embedding, ",") | toFloat(x)] as name_embedding
             """
-        elif driver.aoss_client:
-            resp = await driver.aoss_client.search(
-                body={
-                    'query': {'multi_match': {'query': self.uuid, 'fields': ['uuid']}},
-                    'size': 1,
-                },
-                index=ENTITY_INDEX_NAME,
-                params={'routing': self.group_id},
-            )
-
-            if resp['hits']['hits']:
-                self.name_embedding = resp['hits']['hits'][0]['_source']['name_embedding']
-                return
-            else:
-                raise NodeNotFoundError(self.uuid)
 
         else:
             query: LiteralString = """
@@ -548,6 +475,9 @@ class EntityNode(Node):
         self.name_embedding = records[0]['name_embedding']
 
     async def save(self, driver: GraphDriver):
+        if driver.graph_operations_interface:
+            return await driver.graph_operations_interface.node_save(self, driver)
+
         entity_data: dict[str, Any] = {
             'uuid': self.uuid,
             'name': self.name,
@@ -568,11 +498,8 @@ class EntityNode(Node):
             entity_data.update(self.attributes or {})
             labels = ':'.join(self.labels + ['Entity'])
 
-            if driver.aoss_client:
-                await driver.save_to_aoss(ENTITY_INDEX_NAME, [entity_data])  # pyright: ignore reportAttributeAccessIssue
-
             result = await driver.execute_query(
-                get_entity_node_save_query(driver.provider, labels, bool(driver.aoss_client)),
+                get_entity_node_save_query(driver.provider, labels),
                 entity_data=entity_data,
             )
 

graphiti_core/prompts/dedupe_edges.py

@@ -67,13 +67,13 @@ def edge(context: dict[str, Any]) -> list[Message]:
         Given the following context, determine whether the New Edge represents any of the edges in the list of Existing Edges.
 
         <EXISTING EDGES>
-        {to_prompt_json(context['related_edges'], indent=2)}
+        {to_prompt_json(context['related_edges'])}
         </EXISTING EDGES>
 
         <NEW EDGE>
-        {to_prompt_json(context['extracted_edges'], indent=2)}
+        {to_prompt_json(context['extracted_edges'])}
         </NEW EDGE>
-        
+
         Task:
         If the New Edges represents the same factual information as any edge in Existing Edges, return the id of the duplicate fact
             as part of the list of duplicate_facts.
@@ -98,7 +98,7 @@ def edge_list(context: dict[str, Any]) -> list[Message]:
         Given the following context, find all of the duplicates in a list of facts:
 
         Facts:
-        {to_prompt_json(context['edges'], indent=2)}
+        {to_prompt_json(context['edges'])}
 
         Task:
         If any facts in Facts is a duplicate of another fact, return a new fact with one of their uuid's.

graphiti_core/prompts/dedupe_nodes.py

@@ -64,20 +64,20 @@ def node(context: dict[str, Any]) -> list[Message]:
             role='user',
             content=f"""
         <PREVIOUS MESSAGES>
-        {to_prompt_json([ep for ep in context['previous_episodes']], indent=2)}
+        {to_prompt_json([ep for ep in context['previous_episodes']])}
         </PREVIOUS MESSAGES>
         <CURRENT MESSAGE>
         {context['episode_content']}
         </CURRENT MESSAGE>
         <NEW ENTITY>
-        {to_prompt_json(context['extracted_node'], indent=2)}
+        {to_prompt_json(context['extracted_node'])}
         </NEW ENTITY>
         <ENTITY TYPE DESCRIPTION>
-        {to_prompt_json(context['entity_type_description'], indent=2)}
+        {to_prompt_json(context['entity_type_description'])}
         </ENTITY TYPE DESCRIPTION>
 
         <EXISTING ENTITIES>
-        {to_prompt_json(context['existing_nodes'], indent=2)}
+        {to_prompt_json(context['existing_nodes'])}
         </EXISTING ENTITIES>
         
         Given the above EXISTING ENTITIES and their attributes, MESSAGE, and PREVIOUS MESSAGES; Determine if the NEW ENTITY extracted from the conversation
@@ -125,13 +125,13 @@ def nodes(context: dict[str, Any]) -> list[Message]:
             role='user',
             content=f"""
         <PREVIOUS MESSAGES>
-        {to_prompt_json([ep for ep in context['previous_episodes']], indent=2)}
+        {to_prompt_json([ep for ep in context['previous_episodes']])}
         </PREVIOUS MESSAGES>
         <CURRENT MESSAGE>
         {context['episode_content']}
         </CURRENT MESSAGE>
-        
-        
+
+
         Each of the following ENTITIES were extracted from the CURRENT MESSAGE.
         Each entity in ENTITIES is represented as a JSON object with the following structure:
         {{
@@ -142,11 +142,11 @@ def nodes(context: dict[str, Any]) -> list[Message]:
         }}
 
         <ENTITIES>
-        {to_prompt_json(context['extracted_nodes'], indent=2)}
+        {to_prompt_json(context['extracted_nodes'])}
         </ENTITIES>
 
         <EXISTING ENTITIES>
-        {to_prompt_json(context['existing_nodes'], indent=2)}
+        {to_prompt_json(context['existing_nodes'])}
         </EXISTING ENTITIES>
 
         Each entry in EXISTING ENTITIES is an object with the following structure:
@@ -197,7 +197,7 @@ def node_list(context: dict[str, Any]) -> list[Message]:
         Given the following context, deduplicate a list of nodes:
 
         Nodes:
-        {to_prompt_json(context['nodes'], indent=2)}
+        {to_prompt_json(context['nodes'])}
 
         Task:
         1. Group nodes together such that all duplicate nodes are in the same list of uuids

graphiti_core/prompts/extract_edges.py

@@ -80,7 +80,7 @@ def edge(context: dict[str, Any]) -> list[Message]:
 </FACT TYPES>
 
 <PREVIOUS_MESSAGES>
-{to_prompt_json([ep for ep in context['previous_episodes']], indent=2)}
+{to_prompt_json([ep for ep in context['previous_episodes']])}
 </PREVIOUS_MESSAGES>
 
 <CURRENT_MESSAGE>
@@ -88,7 +88,7 @@ def edge(context: dict[str, Any]) -> list[Message]:
 </CURRENT_MESSAGE>
 
 <ENTITIES>
-{to_prompt_json(context['nodes'], indent=2)}
+{to_prompt_json(context['nodes'])}
 </ENTITIES>
 
 <REFERENCE_TIME>
@@ -141,7 +141,7 @@ def reflexion(context: dict[str, Any]) -> list[Message]:
 
     user_prompt = f"""
 <PREVIOUS MESSAGES>
-{to_prompt_json([ep for ep in context['previous_episodes']], indent=2)}
+{to_prompt_json([ep for ep in context['previous_episodes']])}
 </PREVIOUS MESSAGES>
 <CURRENT MESSAGE>
 {context['episode_content']}
@@ -175,7 +175,7 @@ def extract_attributes(context: dict[str, Any]) -> list[Message]:
             content=f"""
 
         <MESSAGE>
-        {to_prompt_json(context['episode_content'], indent=2)}
+        {to_prompt_json(context['episode_content'])}
         </MESSAGE>
         <REFERENCE TIME>
         {context['reference_time']}

graphiti_core/prompts/extract_nodes.py

@@ -93,7 +93,7 @@ def extract_message(context: dict[str, Any]) -> list[Message]:
 </ENTITY TYPES>
 
 <PREVIOUS MESSAGES>
-{to_prompt_json([ep for ep in context['previous_episodes']], indent=2)}
+{to_prompt_json([ep for ep in context['previous_episodes']])}
 </PREVIOUS MESSAGES>
 
 <CURRENT MESSAGE>
@@ -201,7 +201,7 @@ def reflexion(context: dict[str, Any]) -> list[Message]:
 
     user_prompt = f"""
 <PREVIOUS MESSAGES>
-{to_prompt_json([ep for ep in context['previous_episodes']], indent=2)}
+{to_prompt_json([ep for ep in context['previous_episodes']])}
 </PREVIOUS MESSAGES>
 <CURRENT MESSAGE>
 {context['episode_content']}
@@ -225,22 +225,22 @@ def classify_nodes(context: dict[str, Any]) -> list[Message]:
 
     user_prompt = f"""
     <PREVIOUS MESSAGES>
-    {to_prompt_json([ep for ep in context['previous_episodes']], indent=2)}
+    {to_prompt_json([ep for ep in context['previous_episodes']])}
     </PREVIOUS MESSAGES>
     <CURRENT MESSAGE>
     {context['episode_content']}
     </CURRENT MESSAGE>
-    
+
     <EXTRACTED ENTITIES>
     {context['extracted_entities']}
     </EXTRACTED ENTITIES>
-    
+
     <ENTITY TYPES>
     {context['entity_types']}
     </ENTITY TYPES>
-    
+
     Given the above conversation, extracted entities, and provided entity types and their descriptions, classify the extracted entities.
-    
+
     Guidelines:
     1. Each entity must have exactly one type
     2. Only use the provided ENTITY TYPES as types, do not use additional types to classify entities.
@@ -269,10 +269,10 @@ def extract_attributes(context: dict[str, Any]) -> list[Message]:
         2. Only use the provided MESSAGES and ENTITY to set attribute values.
 
         <MESSAGES>
-        {to_prompt_json(context['previous_episodes'], indent=2)}
-        {to_prompt_json(context['episode_content'], indent=2)}
+        {to_prompt_json(context['previous_episodes'])}
+        {to_prompt_json(context['episode_content'])}
         </MESSAGES>
-        
+
         <ENTITY>
         {context['node']}
         </ENTITY>
@@ -292,12 +292,12 @@ def extract_summary(context: dict[str, Any]) -> list[Message]:
             content=f"""
         Given the MESSAGES and the ENTITY, update the summary that combines relevant information about the entity
         from the messages and relevant information from the existing summary.
-        
+
         {summary_instructions}
 
         <MESSAGES>
-        {to_prompt_json(context['previous_episodes'], indent=2)}
-        {to_prompt_json(context['episode_content'], indent=2)}
+        {to_prompt_json(context['previous_episodes'])}
+        {to_prompt_json(context['episode_content'])}
         </MESSAGES>
 
         <ENTITY>

graphiti_core/prompts/prompt_helpers.py

@@ -20,14 +20,14 @@ from typing import Any
 DO_NOT_ESCAPE_UNICODE = '\nDo not escape unicode characters.\n'
 
 
-def to_prompt_json(data: Any, ensure_ascii: bool = False, indent: int = 2) -> str:
+def to_prompt_json(data: Any, ensure_ascii: bool = False, indent: int | None = None) -> str:
     """
     Serialize data to JSON for use in prompts.
 
     Args:
         data: The data to serialize
         ensure_ascii: If True, escape non-ASCII characters. If False (default), preserve them.
-        indent: Number of spaces for indentation
+        indent: Number of spaces for indentation. Defaults to None (minified).
 
     Returns:
         JSON string representation of the data

graphiti_core/prompts/summarize_nodes.py

@@ -56,11 +56,11 @@ def summarize_pair(context: dict[str, Any]) -> list[Message]:
             role='user',
             content=f"""
         Synthesize the information from the following two summaries into a single succinct summary.
-        
+
         IMPORTANT: Keep the summary concise and to the point. SUMMARIES MUST BE LESS THAN 250 CHARACTERS.
 
         Summaries:
-        {to_prompt_json(context['node_summaries'], indent=2)}
+        {to_prompt_json(context['node_summaries'])}
         """,
         ),
     ]
@@ -77,28 +77,28 @@ def summarize_context(context: dict[str, Any]) -> list[Message]:
             content=f"""
         Given the MESSAGES and the ENTITY name, create a summary for the ENTITY. Your summary must only use
         information from the provided MESSAGES. Your summary should also only contain information relevant to the
-        provided ENTITY. 
-        
+        provided ENTITY.
+
         In addition, extract any values for the provided entity properties based on their descriptions.
         If the value of the entity property cannot be found in the current context, set the value of the property to the Python value None.
-        
+
         {summary_instructions}
 
         <MESSAGES>
-        {to_prompt_json(context['previous_episodes'], indent=2)}
-        {to_prompt_json(context['episode_content'], indent=2)}
+        {to_prompt_json(context['previous_episodes'])}
+        {to_prompt_json(context['episode_content'])}
         </MESSAGES>
-        
+
         <ENTITY>
         {context['node_name']}
         </ENTITY>
-        
+
         <ENTITY CONTEXT>
         {context['node_summary']}
         </ENTITY CONTEXT>
-        
+
         <ATTRIBUTES>
-        {to_prompt_json(context['attributes'], indent=2)}
+        {to_prompt_json(context['attributes'])}
         </ATTRIBUTES>
         """,
         ),
@@ -118,7 +118,7 @@ def summary_description(context: dict[str, Any]) -> list[Message]:
         Summaries must be under 250 characters.
 
         Summary:
-        {to_prompt_json(context['summary'], indent=2)}
+        {to_prompt_json(context['summary'])}
         """,
         ),
     ]

graphiti_core/search/search_filters.py

@@ -249,41 +249,3 @@ def edge_search_filter_query_constructor(
         filter_queries.append(expired_at_filter)
 
     return filter_queries, filter_params
-
-
-def build_aoss_node_filters(group_ids: list[str], search_filters: SearchFilters) -> list[dict]:
-    filters = [{'terms': {'group_id': group_ids}}]
-
-    if search_filters.node_labels:
-        filters.append({'terms': {'node_labels': search_filters.node_labels}})
-
-    return filters
-
-
-def build_aoss_edge_filters(group_ids: list[str], search_filters: SearchFilters) -> list[dict]:
-    filters: list[dict] = [{'terms': {'group_id': group_ids}}]
-
-    if search_filters.edge_types:
-        filters.append({'terms': {'edge_types': search_filters.edge_types}})
-
-    if search_filters.edge_uuids:
-        filters.append({'terms': {'uuid': search_filters.edge_uuids}})
-
-    for field in ['valid_at', 'invalid_at', 'created_at', 'expired_at']:
-        ranges = getattr(search_filters, field)
-        if ranges:
-            # OR of ANDs
-            should_clauses = []
-            for and_group in ranges:
-                and_filters = []
-                for df in and_group:  # df is a DateFilter
-                    range_query = {
-                        'range': {
-                            field: {cypher_to_opensearch_operator(df.comparison_operator): df.date}
-                        }
-                    }
-                    and_filters.append(range_query)
-                should_clauses.append({'bool': {'filter': and_filters}})
-            filters.append({'bool': {'should': should_clauses, 'minimum_should_match': 1}})
-
-    return filters

graphiti_core/search/search_helpers.py

@@ -56,16 +56,16 @@ def search_results_to_context_string(search_results: SearchResults) -> str:
     These are the most relevant facts and their valid and invalid dates. Facts are considered valid
     between their valid_at and invalid_at dates. Facts with an invalid_at date of "Present" are considered valid.
     <FACTS>
-            {to_prompt_json(fact_json, indent=12)}
+            {to_prompt_json(fact_json)}
     </FACTS>
     <ENTITIES>
-            {to_prompt_json(entity_json, indent=12)}
+            {to_prompt_json(entity_json)}
     </ENTITIES>
     <EPISODES>
-            {to_prompt_json(episode_json, indent=12)}
+            {to_prompt_json(episode_json)}
     </EPISODES>
     <COMMUNITIES>
-            {to_prompt_json(community_json, indent=12)}
+            {to_prompt_json(community_json)}
     </COMMUNITIES>
 """