@@ -131,6 +131,28 @@ continuing up the hierarchy until no more merges are possible.
131131
132132List of documents (could be a mix of different hierarchy levels)
133133
134+ <a id =" auto_merging_retriever.AutoMergingRetriever.run_async " ></a >
135+
136+ #### AutoMergingRetriever.run\_ async
137+
138+ ``` python
139+ @component.output_types (documents = list[Document])
140+ async def run_async (documents : list[Document])
141+ ```
142+
143+ Asynchronously run the AutoMergingRetriever.
144+
145+ Recursively groups documents by their parents and merges them if they meet the threshold,
146+ continuing up the hierarchy until no more merges are possible.
147+
148+ ** Arguments** :
149+
150+ - ` documents ` : List of leaf documents that were matched by a retriever
151+
152+ ** Returns** :
153+
154+ List of documents (could be a mix of different hierarchy levels)
155+
134156<a id =" filter_retriever " ></a >
135157
136158## Module filter\_ retriever
@@ -232,6 +254,26 @@ If not specified, the FilterRetriever uses the values provided at initialization
232254
233255A list of retrieved documents.
234256
257+ <a id =" filter_retriever.FilterRetriever.run_async " ></a >
258+
259+ #### FilterRetriever.run\_ async
260+
261+ ``` python
262+ @component.output_types (documents = list[Document])
263+ async def run_async (filters : Optional[dict[str , Any]] = None )
264+ ```
265+
266+ Asynchronously run the FilterRetriever on the given input data.
267+
268+ ** Arguments** :
269+
270+ - ` filters ` : A dictionary with filters to narrow down the search space.
271+ If not specified, the FilterRetriever uses the values provided at initialization.
272+
273+ ** Returns** :
274+
275+ A list of retrieved documents.
276+
235277<a id =" in_memory/bm25_retriever " ></a >
236278
237279## Module in\_ memory/bm25\_ retriever
0 commit comments