graphiti-core 0.11.6rc7__py3-none-any.whl → 0.12.0__py3-none-any.whl

graphiti_core/utils/maintenance/node_operations.py

@@ -29,7 +29,7 @@ from graphiti_core.llm_client import LLMClient
 from graphiti_core.llm_client.config import ModelSize
 from graphiti_core.nodes import EntityNode, EpisodeType, EpisodicNode, create_entity_node_embeddings
 from graphiti_core.prompts import prompt_library
-from graphiti_core.prompts.dedupe_nodes import NodeDuplicate
+from graphiti_core.prompts.dedupe_nodes import NodeResolutions
 from graphiti_core.prompts.extract_nodes import (
     ExtractedEntities,
     ExtractedEntity,
@@ -241,73 +241,45 @@ async def resolve_extracted_nodes(
         ]
     )
 
-    existing_nodes_lists: list[list[EntityNode]] = [result.nodes for result in search_results]
-
-    resolved_nodes: list[EntityNode] = await semaphore_gather(
-        *[
-            resolve_extracted_node(
-                llm_client,
-                extracted_node,
-                existing_nodes,
-                episode,
-                previous_episodes,
-                entity_types.get(
-                    next((item for item in extracted_node.labels if item != 'Entity'), '')
-                )
-                if entity_types is not None
-                else None,
-            )
-            for extracted_node, existing_nodes in zip(
-                extracted_nodes, existing_nodes_lists, strict=True
-            )
-        ]
-    )
-
-    uuid_map: dict[str, str] = {}
-    for extracted_node, resolved_node in zip(extracted_nodes, resolved_nodes, strict=True):
-        uuid_map[extracted_node.uuid] = resolved_node.uuid
+    existing_nodes_dict: dict[str, EntityNode] = {
+        node.uuid: node for result in search_results for node in result.nodes
+    }
 
-    logger.debug(f'Resolved nodes: {[(n.name, n.uuid) for n in resolved_nodes]}')
+    existing_nodes: list[EntityNode] = list(existing_nodes_dict.values())
 
-    return resolved_nodes, uuid_map
+    existing_nodes_context = (
+        [
+            {
+                **{
+                    'idx': i,
+                    'name': candidate.name,
+                    'entity_types': candidate.labels,
+                },
+                **candidate.attributes,
+            }
+            for i, candidate in enumerate(existing_nodes)
+        ],
+    )
 
-
-async def resolve_extracted_node(
-    llm_client: LLMClient,
-    extracted_node: EntityNode,
-    existing_nodes: list[EntityNode],
-    episode: EpisodicNode | None = None,
-    previous_episodes: list[EpisodicNode] | None = None,
-    entity_type: BaseModel | None = None,
-) -> EntityNode:
-    start = time()
-    if len(existing_nodes) == 0:
-        return extracted_node
+    entity_types_dict: dict[str, BaseModel] = entity_types if entity_types is not None else {}
 
     # Prepare context for LLM
-    existing_nodes_context = [
+    extracted_nodes_context = [
         {
-            **{
-                'id': i,
-                'name': node.name,
-                'entity_types': node.labels,
-            },
-            **node.attributes,
+            'id': i,
+            'name': node.name,
+            'entity_type': node.labels,
+            'entity_type_description': entity_types_dict.get(
+                next((item for item in node.labels if item != 'Entity'), '')
+            ).__doc__
+            or 'Default Entity Type',
         }
-        for i, node in enumerate(existing_nodes)
+        for i, node in enumerate(extracted_nodes)
     ]
 
-    extracted_node_context = {
-        'name': extracted_node.name,
-        'entity_type': entity_type.__name__ if entity_type is not None else 'Entity',  # type: ignore
-    }
-
     context = {
+        'extracted_nodes': extracted_nodes_context,
         'existing_nodes': existing_nodes_context,
-        'extracted_node': extracted_node_context,
-        'entity_type_description': entity_type.__doc__
-        if entity_type is not None
-        else 'Default Entity Type',
         'episode_content': episode.content if episode is not None else '',
         'previous_episodes': [ep.content for ep in previous_episodes]
         if previous_episodes is not None
@@ -315,25 +287,34 @@ async def resolve_extracted_node(
     }
 
     llm_response = await llm_client.generate_response(
-        prompt_library.dedupe_nodes.node(context),
-        response_model=NodeDuplicate,
-        model_size=ModelSize.small,
+        prompt_library.dedupe_nodes.nodes(context),
+        response_model=NodeResolutions,
     )
 
-    duplicate_id: int = llm_response.get('duplicate_node_id', -1)
+    node_resolutions: list = llm_response.get('entity_resolutions', [])
 
-    node = (
-        existing_nodes[duplicate_id] if 0 <= duplicate_id < len(existing_nodes) else extracted_node
-    )
+    resolved_nodes: list[EntityNode] = []
+    uuid_map: dict[str, str] = {}
+    for resolution in node_resolutions:
+        resolution_id = resolution.get('id', -1)
+        duplicate_idx = resolution.get('duplicate_idx', -1)
 
-    node.name = llm_response.get('name', '')
+        extracted_node = extracted_nodes[resolution_id]
 
-    end = time()
-    logger.debug(
-        f'Resolved node: {extracted_node.name} is {node.name}, in {(end - start) * 1000} ms'
-    )
+        resolved_node = (
+            existing_nodes[duplicate_idx]
+            if 0 <= duplicate_idx < len(existing_nodes)
+            else extracted_node
+        )
 
-    return node
+        resolved_node.name = resolution.get('name')
+
+        resolved_nodes.append(resolved_node)
+        uuid_map[extracted_node.uuid] = resolved_node.uuid
+
+    logger.debug(f'Resolved nodes: {[(n.name, n.uuid) for n in resolved_nodes]}')
+
+    return resolved_nodes, uuid_map
 
 
 async def extract_attributes_from_nodes(
@@ -345,7 +326,6 @@ async def extract_attributes_from_nodes(
 ) -> list[EntityNode]:
     llm_client = clients.llm_client
     embedder = clients.embedder
-
     updated_nodes: list[EntityNode] = await semaphore_gather(
         *[
             extract_attributes_from_node(
@@ -410,6 +390,7 @@ async def extract_attributes_from_node(
     llm_response = await llm_client.generate_response(
         prompt_library.extract_nodes.extract_attributes(summary_context),
         response_model=entity_attributes_model,
+        model_size=ModelSize.small,
     )
 
     node.summary = llm_response.get('summary', node.summary)

{graphiti_core-0.11.6rc7.dist-info → graphiti_core-0.12.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: graphiti-core
-Version: 0.11.6rc7
+Version: 0.12.0
 Summary: A temporal graph building library
 License: Apache-2.0
 Author: Paul Paliychuk
@@ -17,12 +17,13 @@ Provides-Extra: google-genai
 Provides-Extra: groq
 Requires-Dist: anthropic (>=0.49.0) ; extra == "anthropic"
 Requires-Dist: diskcache (>=5.6.3)
+Requires-Dist: falkordb (>=1.1.2,<2.0.0)
 Requires-Dist: google-genai (>=1.8.0) ; extra == "google-genai"
 Requires-Dist: groq (>=0.2.0) ; extra == "groq"
-Requires-Dist: neo4j (>=5.23.0)
+Requires-Dist: neo4j (>=5.26.0)
 Requires-Dist: numpy (>=1.0.0)
 Requires-Dist: openai (>=1.53.0)
-Requires-Dist: pydantic (>=2.8.2)
+Requires-Dist: pydantic (>=2.11.5)
 Requires-Dist: python-dotenv (>=1.0.1)
 Requires-Dist: tenacity (>=9.0.0)
 Project-URL: Homepage, https://help.getzep.com/graphiti/graphiti/overview
@@ -136,7 +137,7 @@ Graphiti is specifically designed to address the challenges of dynamic and frequ
 Requirements:
 
 - Python 3.10 or higher
-- Neo4j 5.26 or higher (serves as the embeddings storage backend)
+- Neo4j 5.26 / FalkorDB 1.1.2 or higher (serves as the embeddings storage backend)
 - OpenAI API key (for LLM inference and embedding)
 
 > [!IMPORTANT]
@@ -236,7 +237,7 @@ Graphiti supports Azure OpenAI for both LLM inference and embeddings. To use Azu
 ```python
 from openai import AsyncAzureOpenAI
 from graphiti_core import Graphiti
-from graphiti_core.llm_client import OpenAIClient
+from graphiti_core.llm_client import LLMConfig, OpenAIClient
 from graphiti_core.embedder.openai import OpenAIEmbedder, OpenAIEmbedderConfig
 from graphiti_core.cross_encoder.openai_reranker_client import OpenAIRerankerClient
 
@@ -252,12 +253,19 @@ azure_openai_client = AsyncAzureOpenAI(
     azure_endpoint=azure_endpoint
 )
 
+# Create LLM Config with your Azure deployed model names
+azure_llm_config = LLMConfig(
+    small_model="gpt-4.1-nano",
+    model="gpt-4.1-mini",
+)
+
 # Initialize Graphiti with Azure OpenAI clients
 graphiti = Graphiti(
     "bolt://localhost:7687",
     "neo4j",
     "password",
     llm_client=OpenAIClient(
+        llm_config=azure_llm_config,
         client=azure_openai_client
     ),
     embedder=OpenAIEmbedder(
@@ -268,6 +276,7 @@ graphiti = Graphiti(
     ),
     # Optional: Configure the OpenAI cross encoder with Azure OpenAI
     cross_encoder=OpenAIRerankerClient(
+        llm_config=azure_llm_config,
         client=azure_openai_client
     )
 )

{graphiti_core-0.11.6rc7.dist-info → graphiti_core-0.12.0.dist-info}/RECORD

@@ -2,65 +2,72 @@ graphiti_core/__init__.py,sha256=e5SWFkRiaUwfprYIeIgVIh7JDedNiloZvd3roU-0aDY,55
 graphiti_core/cross_encoder/__init__.py,sha256=hry59vz21x-AtGZ0MJ7ugw0HTwJkXiddpp_Yqnwsen0,723
 graphiti_core/cross_encoder/bge_reranker_client.py,sha256=sY7RKsCp90vTjYxv6vmIHT4p3oCsFCRYWH-H0Ia0vN0,1449
 graphiti_core/cross_encoder/client.py,sha256=KLsbfWKOEaAV3adFe3XZlAeb-gje9_sVKCVZTaJP3ac,1441
-graphiti_core/cross_encoder/openai_reranker_client.py,sha256=R8NHHbIlPtnHMq_ZcCOAlgdULXuqzy5IzJoGuqYPEv0,4488
-graphiti_core/edges.py,sha256=WGJQAMtyj-huh343nmm5NMzIeNlnmNLBLO-d7JprNwQ,15256
+graphiti_core/cross_encoder/openai_reranker_client.py,sha256=_Hftiz250HbEkY_26z6A1oxg4pzM8Sbr8CwnbJEsggc,4522
+graphiti_core/driver/__init__.py,sha256=DumfxIEY3z_nkz5YGaYH1GM50HgeAdEowNK189jcdAg,626
+graphiti_core/driver/driver.py,sha256=-FHAA2gM8FA0re-q6udmjQ6pNFdFGRQrMRuAiqX_1A4,1829
+graphiti_core/driver/falkordb_driver.py,sha256=VQ3nxv2MjiPjWHIk8RaoQ0YXiWARG43_NAmfFSTL1NE,4667
+graphiti_core/driver/neo4j_driver.py,sha256=D8CV5GbhKoHIQ78BA9ozlwdvXPLUbBmFSfT2lww8PJk,1910
+graphiti_core/edges.py,sha256=h67vyXYhZYqlwaOmaqjHiGns6nEjuBVSIAFBMveNVo8,16257
 graphiti_core/embedder/__init__.py,sha256=EL564ZuE-DZjcuKNUK_exMn_XHXm2LdO9fzdXePVKL4,179
+graphiti_core/embedder/azure_openai.py,sha256=OyomPwC1fIsddI-3n6g00kQFdQznZorBhHwkQKCLUok,2384
 graphiti_core/embedder/client.py,sha256=qEpSHceL_Gc4QQPJWIOnuNLemNuR_TYA4r28t2Vldbg,1115
-graphiti_core/embedder/gemini.py,sha256=Dh80q21auMvDBjwqHsI_wFrJtgWwCXRHzwg31-BSR34,2661
+graphiti_core/embedder/gemini.py,sha256=7En-W46YxqC5qL3vYB5Ed-Xm0hqLxi7-LgZ95c4M7ME,3263
 graphiti_core/embedder/openai.py,sha256=bIThUoLMeGlHG2-3VikzK6JZfOHKn4PKvUMx5sHxJy8,2192
 graphiti_core/embedder/voyage.py,sha256=gQhdcz2IYPSyOcDn3w8aHToVS3KQhyZrUBm4vqr3WcE,2224
 graphiti_core/errors.py,sha256=Nib1uQx2cO_VOizupmRjpFfmuRg-hFAVqTtZAuBehR8,2405
-graphiti_core/graphiti.py,sha256=niRU1sZ2hf3a8WUPQAEIOsg8ixR_r_NUau5famfe1uM,27090
-graphiti_core/graphiti_types.py,sha256=46ueysKPwUCpxkMePHdCJLspfTImoZN7JiRwpz7cqd0,1013
-graphiti_core/helpers.py,sha256=iRN1gFMrYa07C5MyaQkefiD5t0itfNddczyLmLIxRs0,3465
-graphiti_core/llm_client/__init__.py,sha256=PA80TSMeX-sUXITXEAxMDEt3gtfZgcJrGJUcyds1mSo,207
+graphiti_core/graph_queries.py,sha256=KfWDp8xDnPa9bcHskw8NeMpeeHBtZWBCosVdu1Iwv34,7076
+graphiti_core/graphiti.py,sha256=oMLoKs87aoT3WhPVPuKCyd9H0i_ZTXl7FleuCNnBVms,28013
+graphiti_core/graphiti_types.py,sha256=rL-9bvnLobunJfXU4hkD6mAj14pofKp_wq8QsFDZwDU,1035
+graphiti_core/helpers.py,sha256=sfC1M6KefKaZll6FQcpcNvWnCN6iCvBSJksAkGTItT4,3059
+graphiti_core/llm_client/__init__.py,sha256=QgBWUiCeBp6YiA_xqyrDvJ9jIyy1hngH8g7FWahN3nw,776
 graphiti_core/llm_client/anthropic_client.py,sha256=392rtkH_I7yOJUlQvjoOnS8Lz14WBP8egQ3OfRH0nFs,12481
+graphiti_core/llm_client/azure_openai_client.py,sha256=B6EbNIktP9FBqiFrGunVQlego2e3C5zBAbcHI55Y-OY,2680
 graphiti_core/llm_client/client.py,sha256=v_w5TBbDJYYADCXSs2r287g5Ami2Urma-GGEbHSI_Jg,5826
 graphiti_core/llm_client/config.py,sha256=90IgSBxZE_3nWdaEONVLUznI8lytPA7ZyexQz-_c55U,2560
 graphiti_core/llm_client/errors.py,sha256=pn6brRiLW60DAUIXJYKBT6MInrS4ueuH1hNLbn_JbQo,1243
-graphiti_core/llm_client/gemini_client.py,sha256=JdcQTvwbaqko0alodUW3WP328i6Pu_GLUQ9yBAFBXwY,7558
+graphiti_core/llm_client/gemini_client.py,sha256=OdRAB2bWlXAi3gRmE1xVljYJ0T7JTZC82VK71wHyZi8,7722
 graphiti_core/llm_client/groq_client.py,sha256=k7zbXHfOpb4jhvvKFsccVYTq4yGGpxmY7xzNA02N2zk,2559
 graphiti_core/llm_client/openai_client.py,sha256=lLTZkd-PxEicTBmQefGoWLGTCb4QSU2Cq3x5W4kRYXg,7412
 graphiti_core/llm_client/openai_generic_client.py,sha256=WElMnPqdb1CxzYH4p2-m_9rVMr5M93-eXnc3yVxBgFg,7001
 graphiti_core/llm_client/utils.py,sha256=zKpxXEbKa369m4W7RDEf-m56kH46V1Mx3RowcWZEWWs,1000
 graphiti_core/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 graphiti_core/models/edges/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-graphiti_core/models/edges/edge_db_queries.py,sha256=S02lXOW-st2BVu9Mm3I1SyVfwISAquCxBB8666gv7I4,2674
+graphiti_core/models/edges/edge_db_queries.py,sha256=W2-ljKnZOt5MlD9_M4f_823GdyTMRzW2tJX0CezaixY,2284
 graphiti_core/models/nodes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 graphiti_core/models/nodes/node_db_queries.py,sha256=AQgRGVO-GgFWfLq1G6k8s86WItwpXruy3Mj4DBli-vM,2145
-graphiti_core/nodes.py,sha256=U19DZ0MIi8GfEsx8D-Jgl8c2SGXO8QovVQpYy6FmUpo,18542
+graphiti_core/nodes.py,sha256=kdJY-Ugyk6J2x70w4EF_EoFNgy7D3TMOMVSUfEth6rE,18665
 graphiti_core/prompts/__init__.py,sha256=EA-x9xUki9l8wnu2l8ek_oNf75-do5tq5hVq7Zbv8Kw,101
-graphiti_core/prompts/dedupe_edges.py,sha256=q60fqIjFQlOzOeL7Y35gwABWQBqKkMarBQBok1pj1C4,3409
-graphiti_core/prompts/dedupe_nodes.py,sha256=lwdz2Hhi1VIPAC0S8qMV9iaulYtR3FsiujsL7T1Ec8U,4494
+graphiti_core/prompts/dedupe_edges.py,sha256=AFVC1EQ0TvNkSp0G7QZmIh3YpGg9FVXo1_sT3TlRqA8,5473
+graphiti_core/prompts/dedupe_nodes.py,sha256=OIhMkKexRpQQ0dEr4NW_WE1ta7wLO3RibJA7Ge41uDg,7407
 graphiti_core/prompts/eval.py,sha256=gnBQTmwsCl3Qvwpcm7aieVszzo6y1sMCUT8jQiKTvvE,5317
 graphiti_core/prompts/extract_edge_dates.py,sha256=3Drs3CmvP0gJN5BidWSxrNvLet3HPoTybU3BUIAoc0Y,4218
-graphiti_core/prompts/extract_edges.py,sha256=uSoQS32rpUzQJGEhayErMdj72rocGdqVq54Macjf7po,5102
+graphiti_core/prompts/extract_edges.py,sha256=9NdxAKyXHiFOSuyAzzxRM38BmqtynGEbtmMUr3VTrtM,6513
 graphiti_core/prompts/extract_nodes.py,sha256=EYuX99P8ly7pSOBz87ZA9fJF8V6g6epbVj5Cq0YM8h8,9624
-graphiti_core/prompts/invalidate_edges.py,sha256=3KZQ-Hyop2hae1jK_8GIdUg4ltvFVEDQpvvzt98KvwY,3547
+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
 graphiti_core/prompts/prompt_helpers.py,sha256=-9TABwIcIQUVHcNANx6wIZd-FT2DgYKyGTfx4IGYq2I,64
 graphiti_core/prompts/summarize_nodes.py,sha256=tbg-AgWlzgFBeImKkZ28h2SpmqfPPqvN2Ol1Q71VF9Y,4146
 graphiti_core/py.typed,sha256=vlmmzQOt7bmeQl9L3XJP4W6Ry0iiELepnOrinKz5KQg,79
 graphiti_core/search/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-graphiti_core/search/search.py,sha256=0VTvRNncQIfavhOBYl4p1A9Ielzb3eieKvrhz7Ka_SE,16209
+graphiti_core/search/search.py,sha256=bJCFaNApu5396pXTa-xciu8ORDdRFJqfE3j2ieRVd7Y,15162
 graphiti_core/search/search_config.py,sha256=VvKg6AB_RPhoe56DBBXHRBXHThAVJ_OLFCyq_yKof-A,3765
 graphiti_core/search/search_config_recipes.py,sha256=4GquRphHhJlpXQhAZOySYnCzBWYoTwxlJj44eTOavZQ,7443
-graphiti_core/search/search_filters.py,sha256=JkP7NbM4Dor27dne5vAuxbJic12dIJDtWJxNqmVuRec,5884
+graphiti_core/search/search_filters.py,sha256=jG30nMWX03xoT9ohgyHNu_Xes8GwjIF2eTv6QaiWMqw,6466
 graphiti_core/search/search_helpers.py,sha256=G5Ceaq5Pfgx0Weelqgeylp_pUHwiBnINaUYsDbURJbE,2636
-graphiti_core/search/search_utils.py,sha256=D4A-tvViAZ3dV7AUb3R7n6-Pc_hY37jyoPodJ_G6u7s,30766
+graphiti_core/search/search_utils.py,sha256=k9KKN4sYde0Hqw9BKb5T-8q-3hInIPwq9aYoGfheq6E,34877
 graphiti_core/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-graphiti_core/utils/bulk_utils.py,sha256=_56TZ_gyOt3V5UAmiGhSNtcWOVgZdLZ9rAYCkvkMJuk,15221
+graphiti_core/utils/bulk_utils.py,sha256=8JgxHnp8whiNJEJjd6Pp4wVeNOquymbi4rczV1ygsBs,16176
 graphiti_core/utils/datetime_utils.py,sha256=Ti-2tnrDFRzBsbfblzsHybsM3jaDLP4-VT2t0VhpIzU,1357
 graphiti_core/utils/maintenance/__init__.py,sha256=vW4H1KyapTl-OOz578uZABYcpND4wPx3Vt6aAPaXh78,301
-graphiti_core/utils/maintenance/community_operations.py,sha256=TF-4eHuvMe_jMqvWg3swxK80zLLtOR0t1pmUUQlNulM,10067
-graphiti_core/utils/maintenance/edge_operations.py,sha256=vjeCUt_WlKZ3SRIIgaF9pqc8Na6ajLOzUIo2pWo7NyU,14756
-graphiti_core/utils/maintenance/graph_data_operations.py,sha256=BIJKc8tbvU4IjWxLgeotw57b1eE3Iw8YtV74j6eo4RQ,7493
-graphiti_core/utils/maintenance/node_operations.py,sha256=-gHQH2_jaAg6XYH33tC5Pna1B4VcGHyPTpaK0NY3xow,15308
+graphiti_core/utils/maintenance/community_operations.py,sha256=2rhRqtL9gDbjXKO4-S0nGpaWvS4ck5rFiazZiogIJao,10088
+graphiti_core/utils/maintenance/edge_operations.py,sha256=74HcCWaq7rfQuUH8RsWPr-OYE-5qe8s2BaiBYfkMNT0,19272
+graphiti_core/utils/maintenance/graph_data_operations.py,sha256=OHuiAyP1Z7dfR90dWVQ87TJQO83P0sQihJyr4WIhOhk,5362
+graphiti_core/utils/maintenance/node_operations.py,sha256=5kouyCkzAzIGYUBtViMhNWYL95tA1__TsSWuLj0_RdY,14795
 graphiti_core/utils/maintenance/temporal_operations.py,sha256=mJkw9xLB4W2BsLfC5POr0r-PHWL9SIfNj_l_xu0B5ug,3410
 graphiti_core/utils/maintenance/utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 graphiti_core/utils/ontology_utils/entity_types_utils.py,sha256=QJX5cG0GSSNF_Mm_yrldr69wjVAbN_MxLhOSznz85Hk,1279
-graphiti_core-0.11.6rc7.dist-info/LICENSE,sha256=KCUwCyDXuVEgmDWkozHyniRyWjnWUWjkuDHfU6o3JlA,11325
-graphiti_core-0.11.6rc7.dist-info/METADATA,sha256=Cni7Rvx1hdKkfI7590--qjIR8YA3Ht4yN71H0sNqeSw,15301
-graphiti_core-0.11.6rc7.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-graphiti_core-0.11.6rc7.dist-info/RECORD,,
+graphiti_core-0.12.0.dist-info/LICENSE,sha256=KCUwCyDXuVEgmDWkozHyniRyWjnWUWjkuDHfU6o3JlA,11325
+graphiti_core-0.12.0.dist-info/METADATA,sha256=2jfFx8UOesTVnbRaogI9KM089aakuuasGPe6XTtn4io,15590
+graphiti_core-0.12.0.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+graphiti_core-0.12.0.dist-info/RECORD,,