graphiti-core 0.21.0rc9__py3-none-any.whl → 0.21.0rc11__py3-none-any.whl

graphiti_core/edges.py

@@ -644,8 +644,11 @@ def get_community_edge_from_record(record: Any):
 
 
 async def create_entity_edge_embeddings(embedder: EmbedderClient, edges: list[EntityEdge]):
-    if len(edges) == 0:
+    # filter out falsey values from edges
+    filtered_edges = [edge for edge in edges if edge.fact]
+
+    if len(filtered_edges) == 0:
         return
-    fact_embeddings = await embedder.create_batch([edge.fact for edge in edges])
-    for edge, fact_embedding in zip(edges, fact_embeddings, strict=True):
+    fact_embeddings = await embedder.create_batch([edge.fact for edge in filtered_edges])
+    for edge, fact_embedding in zip(filtered_edges, fact_embeddings, strict=True):
         edge.fact_embedding = fact_embedding

graphiti_core/nodes.py

@@ -868,9 +868,12 @@ def get_community_node_from_record(record: Any) -> CommunityNode:
 
 
 async def create_entity_node_embeddings(embedder: EmbedderClient, nodes: list[EntityNode]):
-    if not nodes:  # Handle empty list case
+    # filter out falsey values from nodes
+    filtered_nodes = [node for node in nodes if node.name]
+
+    if not filtered_nodes:
         return
 
-    name_embeddings = await embedder.create_batch([node.name for node in nodes])
-    for node, name_embedding in zip(nodes, name_embeddings, strict=True):
+    name_embeddings = await embedder.create_batch([node.name for node in filtered_nodes])
+    for node, name_embedding in zip(filtered_nodes, name_embeddings, strict=True):
         node.name_embedding = name_embedding

graphiti_core/prompts/dedupe_nodes.py

@@ -166,7 +166,8 @@ def nodes(context: dict[str, Any]) -> list[Message]:
         - They have similar names or purposes but refer to separate instances or concepts.
 
         Task:
-        Respond with a JSON object that contains an "entity_resolutions" array with one entry for each entity in ENTITIES, ordered by the entity id.
+        ENTITIES contains {len(context['extracted_nodes'])} entities with IDs 0 through {len(context['extracted_nodes']) - 1}.
+        Your response MUST include EXACTLY {len(context['extracted_nodes'])} resolutions with IDs 0 through {len(context['extracted_nodes']) - 1}. Do not skip or add IDs.
 
         For every entity, return an object with the following keys:
         {{

graphiti_core/prompts/extract_nodes.py

@@ -151,7 +151,7 @@ For each entity extracted, also determine its entity type based on the provided
 Indicate the classified entity type by providing its entity_type_id.
 
 Guidelines:
-1. Always try to extract an entities that the JSON represents. This will often be something like a "name" or "user field
+1. Extract all entities that the JSON represents. This will often be something like a "name" or "user" field
 2. Extract all entities mentioned in all other properties throughout the JSON structure
 3. Do NOT extract any properties that contain dates
 """

graphiti_core/utils/maintenance/node_operations.py

@@ -15,6 +15,7 @@ limitations under the License.
 """
 
 import logging
+from collections.abc import Awaitable, Callable
 from time import time
 from typing import Any
 
@@ -55,6 +56,8 @@ from graphiti_core.utils.maintenance.edge_operations import (
 
 logger = logging.getLogger(__name__)
 
+NodeSummaryFilter = Callable[[EntityNode], Awaitable[bool]]
+
 
 async def extract_nodes_reflexion(
     llm_client: LLMClient,
@@ -266,6 +269,27 @@ async def _resolve_with_llm(
         for i, node in enumerate(llm_extracted_nodes)
     ]
 
+    sent_ids = [ctx['id'] for ctx in extracted_nodes_context]
+    logger.debug(
+        'Sending %d entities to LLM for deduplication with IDs 0-%d (actual IDs sent: %s)',
+        len(llm_extracted_nodes),
+        len(llm_extracted_nodes) - 1,
+        sent_ids if len(sent_ids) < 20 else f'{sent_ids[:10]}...{sent_ids[-10:]}',
+    )
+    if llm_extracted_nodes:
+        sample_size = min(3, len(extracted_nodes_context))
+        logger.debug(
+            'First %d entities: %s',
+            sample_size,
+            [(ctx['id'], ctx['name']) for ctx in extracted_nodes_context[:sample_size]],
+        )
+        if len(extracted_nodes_context) > 3:
+            logger.debug(
+                'Last %d entities: %s',
+                sample_size,
+                [(ctx['id'], ctx['name']) for ctx in extracted_nodes_context[-sample_size:]],
+            )
+
     existing_nodes_context = [
         {
             **{
@@ -298,15 +322,38 @@ async def _resolve_with_llm(
     valid_relative_range = range(len(state.unresolved_indices))
     processed_relative_ids: set[int] = set()
 
+    received_ids = {r.id for r in node_resolutions}
+    expected_ids = set(valid_relative_range)
+    missing_ids = expected_ids - received_ids
+    extra_ids = received_ids - expected_ids
+
+    logger.debug(
+        'Received %d resolutions for %d entities',
+        len(node_resolutions),
+        len(state.unresolved_indices),
+    )
+
+    if missing_ids:
+        logger.warning('LLM did not return resolutions for IDs: %s', sorted(missing_ids))
+
+    if extra_ids:
+        logger.warning(
+            'LLM returned invalid IDs outside valid range 0-%d: %s (all returned IDs: %s)',
+            len(state.unresolved_indices) - 1,
+            sorted(extra_ids),
+            sorted(received_ids),
+        )
+
     for resolution in node_resolutions:
         relative_id: int = resolution.id
         duplicate_idx: int = resolution.duplicate_idx
 
         if relative_id not in valid_relative_range:
             logger.warning(
-                'Skipping invalid LLM dedupe id %s (unresolved indices: %s)',
+                'Skipping invalid LLM dedupe id %d (valid range: 0-%d, received %d resolutions)',
                 relative_id,
-                state.unresolved_indices,
+                len(state.unresolved_indices) - 1,
+                len(node_resolutions),
             )
             continue
 
@@ -402,6 +449,7 @@ async def extract_attributes_from_nodes(
     episode: EpisodicNode | None = None,
     previous_episodes: list[EpisodicNode] | None = None,
     entity_types: dict[str, type[BaseModel]] | None = None,
+    should_summarize_node: NodeSummaryFilter | None = None,
 ) -> list[EntityNode]:
     llm_client = clients.llm_client
     embedder = clients.embedder
@@ -418,6 +466,7 @@ async def extract_attributes_from_nodes(
                     else None
                 ),
                 clients.ensure_ascii,
+                should_summarize_node,
             )
             for node in nodes
         ]
@@ -435,6 +484,7 @@ async def extract_attributes_from_node(
     previous_episodes: list[EpisodicNode] | None = None,
     entity_type: type[BaseModel] | None = None,
     ensure_ascii: bool = False,
+    should_summarize_node: NodeSummaryFilter | None = None,
 ) -> EntityNode:
     node_context: dict[str, Any] = {
         'name': node.name,
@@ -477,16 +527,22 @@ async def extract_attributes_from_node(
         else {}
     )
 
-    summary_response = await llm_client.generate_response(
-        prompt_library.extract_nodes.extract_summary(summary_context),
-        response_model=EntitySummary,
-        model_size=ModelSize.small,
-    )
+    # Determine if summary should be generated
+    generate_summary = True
+    if should_summarize_node is not None:
+        generate_summary = await should_summarize_node(node)
+
+    # Conditionally generate summary
+    if generate_summary:
+        summary_response = await llm_client.generate_response(
+            prompt_library.extract_nodes.extract_summary(summary_context),
+            response_model=EntitySummary,
+            model_size=ModelSize.small,
+        )
+        node.summary = summary_response.get('summary', '')
 
     if has_entity_attributes and entity_type is not None:
         entity_type(**llm_response)
-
-    node.summary = summary_response.get('summary', '')
     node_attributes = {key: value for key, value in llm_response.items()}
 
     node.attributes.update(node_attributes)

{graphiti_core-0.21.0rc9.dist-info → graphiti_core-0.21.0rc11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: graphiti-core
-Version: 0.21.0rc9
+Version: 0.21.0rc11
 Summary: A temporal graph building library
 Project-URL: Homepage, https://help.getzep.com/graphiti/graphiti/overview
 Project-URL: Repository, https://github.com/getzep/graphiti

{graphiti_core-0.21.0rc9.dist-info → graphiti_core-0.21.0rc11.dist-info}/RECORD

@@ -1,11 +1,11 @@
 graphiti_core/__init__.py,sha256=e5SWFkRiaUwfprYIeIgVIh7JDedNiloZvd3roU-0aDY,55
-graphiti_core/edges.py,sha256=PhJm_s28cHLEaIqcw66wP16hOq4P4bVQbC_sESHQkXU,20919
+graphiti_core/edges.py,sha256=2jA3x-9AGTldB52B5rWUhDtXXsj4PWM-MO1msIPsbdI,21048
 graphiti_core/errors.py,sha256=cH_v9TPgEPeQE6GFOHIg5TvejpUCBddGarMY2Whxbwc,2707
 graphiti_core/graph_queries.py,sha256=ZWMqAo5pwb8PO5ddg4zZ0ArhHWuWV42g3R9ULIxsHOs,8058
 graphiti_core/graphiti.py,sha256=5Y3SdcC_Ebhp-oqbbIxb0KGshWU24EQx4YYKvK8Id8g,41935
 graphiti_core/graphiti_types.py,sha256=C_p2XwScQlCzo7ets097TrSLs9ATxPZQ4WCsxDS7QHc,1066
 graphiti_core/helpers.py,sha256=q8kbL9gz8igdlh-oMUS-ylUyeMlXZb-ccf-HQkrES_0,5184
-graphiti_core/nodes.py,sha256=wYLQcVEXvQMxTpTc9LWSoPTzzaoUOm0rl07c9wS1XSY,30323
+graphiti_core/nodes.py,sha256=ox7uDYpaayc5J_mrbMaP-d-jACFx9R7Fb14tvh9aRI8,30426
 graphiti_core/py.typed,sha256=vlmmzQOt7bmeQl9L3XJP4W6Ry0iiELepnOrinKz5KQg,79
 graphiti_core/cross_encoder/__init__.py,sha256=hry59vz21x-AtGZ0MJ7ugw0HTwJkXiddpp_Yqnwsen0,723
 graphiti_core/cross_encoder/bge_reranker_client.py,sha256=y3TfFxZh0Yvj6HUShmfUm6MC7OPXwWUlv1Qe5HF3S3I,1797
@@ -44,11 +44,11 @@ graphiti_core/models/nodes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJ
 graphiti_core/models/nodes/node_db_queries.py,sha256=TCHZKG5bQNarV9C5k4hOFFqc-LwTVQ8Pnd6okVVNKbo,12826
 graphiti_core/prompts/__init__.py,sha256=EA-x9xUki9l8wnu2l8ek_oNf75-do5tq5hVq7Zbv8Kw,101
 graphiti_core/prompts/dedupe_edges.py,sha256=WRXQi7JQZdIfKDICWyU7Wbs5WyD_KBblLBSeKdbLyuk,5914
-graphiti_core/prompts/dedupe_nodes.py,sha256=H4sIzpi1gBwPedTMhdY175jnLj5JtnEeb_WNITitPLU,9171
+graphiti_core/prompts/dedupe_nodes.py,sha256=42txTc4QrXQDqM2XE8_USAB9vfsWUgvwS1no_EJNcbA,9320
 graphiti_core/prompts/eval.py,sha256=ijwxbE87G678imdhfPvRujepQMq_JZ3XHX4vOAcVnVI,5507
 graphiti_core/prompts/extract_edge_dates.py,sha256=3Drs3CmvP0gJN5BidWSxrNvLet3HPoTybU3BUIAoc0Y,4218
 graphiti_core/prompts/extract_edges.py,sha256=S115_KnenGJLjmVMzdarXBRj2wJ6y553UfYJgUTTDZI,6920
-graphiti_core/prompts/extract_nodes.py,sha256=GYX97qlSSrR_3QLc48EGCti8tdC1_OKpEdAR0Y2wfVY,11629
+graphiti_core/prompts/extract_nodes.py,sha256=Ksf3PRBZ8LoZ5bOStZVRlHvVrdh3rT3xsepL81Ewy3M,11617
 graphiti_core/prompts/invalidate_edges.py,sha256=yfpcs_pyctnoM77ULPZXEtKW0oHr1MeLsJzC5yrE-o4,3547
 graphiti_core/prompts/lib.py,sha256=DCyHePM4_q-CptTpEXGO_dBv9k7xDtclEaB1dGu7EcI,4092
 graphiti_core/prompts/models.py,sha256=NgxdbPHJpBEcpbXovKyScgpBc73Q-GIW-CBDlBtDjto,894
@@ -71,11 +71,11 @@ graphiti_core/utils/maintenance/community_operations.py,sha256=XMiokEemn96GlvjkO
 graphiti_core/utils/maintenance/dedup_helpers.py,sha256=B7k6KkB6Sii8PZCWNNTvsNiy4BNTNWpoLeGgrPLq6BE,9220
 graphiti_core/utils/maintenance/edge_operations.py,sha256=p16cLA2eJeIYS9W0o1i8wYtvUpjt9mGWzRXVemAr7Bk,25305
 graphiti_core/utils/maintenance/graph_data_operations.py,sha256=42icj3S_ELAJ-NK3jVS_rg_243dmnaZOyUitJj_uJ-M,6085
-graphiti_core/utils/maintenance/node_operations.py,sha256=TKpXPtnTVxxan8I1xQyVkGn3zyRdb_Q00cgUpLcloig,16860
+graphiti_core/utils/maintenance/node_operations.py,sha256=gzIE32D3vCY0RorKwCz6wI9xS95BaiJoO1WyKzuDDKk,19014
 graphiti_core/utils/maintenance/temporal_operations.py,sha256=IIaVtShpVkOYe6haxz3a1x3v54-MzaEXG8VsxFUNeoY,3582
 graphiti_core/utils/maintenance/utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 graphiti_core/utils/ontology_utils/entity_types_utils.py,sha256=4eVgxLWY6Q8k9cRJ5pW59IYF--U4nXZsZIGOVb_yHfQ,1285
-graphiti_core-0.21.0rc9.dist-info/METADATA,sha256=K8BMq3mCQ5o9NUY3M1ZImcnwLykmMAjYcvJMvp5MN6k,27084
-graphiti_core-0.21.0rc9.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-graphiti_core-0.21.0rc9.dist-info/licenses/LICENSE,sha256=KCUwCyDXuVEgmDWkozHyniRyWjnWUWjkuDHfU6o3JlA,11325
-graphiti_core-0.21.0rc9.dist-info/RECORD,,
+graphiti_core-0.21.0rc11.dist-info/METADATA,sha256=LQry-ruHgk3SEGYON167542JVQ-udutxUGRpA7FbRYc,27085
+graphiti_core-0.21.0rc11.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+graphiti_core-0.21.0rc11.dist-info/licenses/LICENSE,sha256=KCUwCyDXuVEgmDWkozHyniRyWjnWUWjkuDHfU6o3JlA,11325
+graphiti_core-0.21.0rc11.dist-info/RECORD,,