Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
feat: extend scoped search (source_ids/tags) to AutoHypergraph and AutoSet
yifanfeng9749ed4ba9d516
diff --git a/hyperextract/types/hypergraph.py b/hyperextract/types/hypergraph.pyindex 7978ca2..541c2c1 100644--- a/hyperextract/types/hypergraph.py+++ b/hyperextract/types/hypergraph.py@@ -752,10 +752,17 @@ class AutoHypergraph(top_k_nodes: int = 3,top_k_edges: int = 3,top_k: int | None = None,+ *,+ source_ids: list[str] | None = None,+ tags: list[str] | None = None,) -> tuple[list[NodeSchema], list[EdgeSchema]]:"""Unified hypergraph search interface.Retrieves nodes and hyperedges semantically related to the query.++ Args:+ source_ids: Optional scope — only knowledge contributed by these source documents.+ tags: Optional scope — only knowledge from sources carrying any of these tags.Always returns a tuple of (nodes, edges). If a count is 0, the corresponding list will be empty.Args:@@ -797,13 +804,31 @@ class AutoHypergraph(return nodes, edges- def search_nodes(self, query: str, top_k: int = 3) -> list[NodeSchema]:+ def search_nodes(+ self,+ query: str,+ top_k: int = 3,+ *,+ source_ids: list[str] | None = None,+ tags: list[str] | None = None,+ ) -> list[NodeSchema]:"""Semantic search for nodes/entities only."""- return self._node_memory.search(query=query, top_k=top_k)+ return self._node_memory.search(+ query=query, top_k=top_k, source_ids=source_ids, tags=tags+ )- def search_edges(self, query: str, top_k: int = 3) -> list[EdgeSchema]:+ def search_edges(+ self,+ query: str,+ top_k: int = 3,+ *,+ source_ids: list[str] | None = None,+ tags: list[str] | None = None,+ ) -> list[EdgeSchema]:"""Semantic search for hyperedges/relationships only."""- return self._edge_memory.search(query=query, top_k=top_k)+ return self._edge_memory.search(+ query=query, top_k=top_k, source_ids=source_ids, tags=tags+ )def chat(self,diff --git a/hyperextract/types/set.py b/hyperextract/types/set.pyindex 959a6ca..007ab85 100644--- a/hyperextract/types/set.py+++ b/hyperextract/types/set.py@@ -184,7 +184,8 @@ class AutoSet(BaseAutoType[AutoSetSchema[ItemSchema]], Generic[ItemSchema]):embedder=embedder,strategy_or_merger=self._merger,verbose=verbose,- fields_for_index=fields_for_index, # Pass field selection to OMem+ fields_for_index=fields_for_index,+ track_sources=True, # source ledger for per-document rollback (#84))# Store label extractor for visualizationself._item_label_extractor = item_label_extractor@@ -344,12 +345,21 @@ class AutoSet(BaseAutoType[AutoSetSchema[ItemSchema]], Generic[ItemSchema]):"""self._data_memory.build_index(force=force)- def search(self, query: str, top_k: int = 3) -> list[ItemSchema]:+ def search(+ self,+ query: str,+ top_k: int = 3,+ *,+ source_ids: list[str] | None = None,+ tags: list[str] | None = None,+ ) -> list[ItemSchema]:"""Searches items in the set using semantic similarity.Args:query: Search query string.top_k: Number of results to return.+ source_ids: Optional scope — only items contributed by these source documents.+ tags: Optional scope — only items from sources carrying any of these tags.Returns:List of relevant items.@@ -359,7 +369,9 @@ class AutoSet(BaseAutoType[AutoSetSchema[ItemSchema]], Generic[ItemSchema]):return []if not self._data_memory.has_index():raise ValueError("Index not built. Call build_index() first.")- return self._data_memory.search(query, top_k=top_k)+ return self._data_memory.search(+ query, top_k=top_k, source_ids=source_ids, tags=tags+ )# ==================== Index Storage ====================