Deleted node2vec implementation

lightrag/kg/age_impl.py

@@ -88,11 +88,6 @@ class AGEStorage(BaseGraphStorage):
 
         return None
 
-    def __post_init__(self):
-        self._node_embed_algorithms = {
-            "node2vec": self._node2vec_embed,
-        }
-
     async def close(self):
         if self._driver:
             await self._driver.close()
@@ -592,9 +587,6 @@ class AGEStorage(BaseGraphStorage):
             logger.error("Error during edge upsert: {%s}", e)
             raise
 
-    async def _node2vec_embed(self):
-        print("Implemented but never called.")
-
     @asynccontextmanager
     async def _get_pool_connection(self, timeout: Optional[float] = None):
         """Workaround for a psycopg_pool bug"""

lightrag/kg/gremlin_impl.py

@@ -69,11 +69,6 @@ class GremlinStorage(BaseGraphStorage):
             transport_factory=lambda: AiohttpTransport(call_from_event_loop=True),
         )
 
-    def __post_init__(self):
-        self._node_embed_algorithms = {
-            "node2vec": self._node2vec_embed,
-        }
-
     async def close(self):
         if self._driver:
             self._driver.close()
@@ -389,9 +384,6 @@ class GremlinStorage(BaseGraphStorage):
             logger.error("Error during edge upsert: {%s}", e)
             raise
 
-    async def _node2vec_embed(self):
-        print("Implemented but never called.")
-
     async def delete_node(self, node_id: str) -> None:
         """Delete a node with the specified entity_name
 

lightrag/kg/neo4j_impl.py

@@ -50,11 +50,6 @@ class Neo4JStorage(BaseGraphStorage):
         )
         self._driver = None
 
-    def __post_init__(self):
-        self._node_embed_algorithms = {
-            "node2vec": self._node2vec_embed,
-        }
-
     async def initialize(self):
         URI = os.environ.get("NEO4J_URI", config.get("neo4j", "uri", fallback=None))
         USERNAME = os.environ.get(
@@ -634,9 +629,6 @@ class Neo4JStorage(BaseGraphStorage):
             logger.error(f"Error during edge upsert: {str(e)}")
             raise
 
-    async def _node2vec_embed(self):
-        print("Implemented but never called.")
-
     async def get_knowledge_graph(
         self,
         node_label: str,

lightrag/kg/networkx_impl.py

@@ -58,10 +58,6 @@ class NetworkXStorage(BaseGraphStorage):
             logger.info("Created new empty graph")
         self._graph = preloaded_graph or nx.Graph()
 
-        self._node_embed_algorithms = {
-            "node2vec": self._node2vec_embed,
-        }
-
     async def initialize(self):
         """Initialize storage data"""
         # Get the update flag for cross-process update notification

lightrag/kg/postgres_impl.py

@@ -1021,9 +1021,6 @@ class PGGraphQueryException(Exception):
 class PGGraphStorage(BaseGraphStorage):
     def __post_init__(self):
         self.graph_name = self.namespace or os.environ.get("AGE_GRAPH_NAME", "lightrag")
-        self._node_embed_algorithms = {
-            "node2vec": self._node2vec_embed,
-        }
         self.db: PostgreSQLDB | None = None
 
     async def initialize(self):
@@ -1396,9 +1393,6 @@ class PGGraphStorage(BaseGraphStorage):
             )
             raise
 
-    async def _node2vec_embed(self):
-        print("Implemented but never called.")
-
     async def delete_node(self, node_id: str) -> None:
         """
         Delete a node from the graph.

lightrag/lightrag.py

@@ -155,31 +155,6 @@ class LightRAG:
     Defaults to `chunking_by_token_size` if not specified.
     """
 
-    # Node embedding
-    # ---
-
-    node_embedding_algorithm: str = field(default="node2vec")
-    """Algorithm used for node embedding in knowledge graphs."""
-
-    node2vec_params: dict[str, int] = field(
-        default_factory=lambda: {
-            "dimensions": 1536,
-            "num_walks": 10,
-            "walk_length": 40,
-            "window_size": 2,
-            "iterations": 3,
-            "random_seed": 3,
-        }
-    )
-    """Configuration for the node2vec embedding algorithm:
-    - dimensions: Number of dimensions for embeddings.
-    - num_walks: Number of random walks per node.
-    - walk_length: Number of steps per random walk.
-    - window_size: Context window size for training.
-    - iterations: Number of iterations for training.
-    - random_seed: Seed value for reproducibility.
-    """
-
     # Embedding
     # ---