cr

libs/langchain/langchain/retrievers/parent_document_retriever.py

@@ -89,18 +89,51 @@ def get_relevant_documents(
         return_docs = cast(List[Document], docs)
         return return_docs
 
-    def add_documents(self, documents: List[Document]) -> None:
+    def add_documents(
+        self,
+        documents: List[Document],
+        ids: Optional[List[str]],
+        add_to_docstore: bool = True,
+    ) -> None:
+        """Adds documents to the docstore and vectorstores.
+
+        Args:
+            documents: List of documents to add
+            ids: Optional list of ids for documents. If provided should be the same
+                length as the list of documents. Can provided if parent documents
+                are already in the document store and you don't want to re-add
+                to the docstore. If not provided, random UUIDs will be used as
+                ids.
+            add_to_docstore: Boolean of whether to add documents to docstore.
+                This can be false if and only if `ids` are provided. You may want
+                to set this to False if the documents are already in the docstore
+                and you don't want to re-add them.
+        """
         if self.parent_splitter is not None:
             documents = self.parent_splitter.split_documents(documents)
+        if ids is None:
+            doc_ids = [str(uuid.uuid4()) for _ in documents]
+            if not add_to_docstore:
+                raise ValueError(
+                    "If ids are not passed in, `add_to_docstore` MUST be True"
+                )
+        else:
+            if len(documents) != len(ids):
+                raise ValueError(
+                    "Got uneven list of documents and ids. "
+                    "If `ids` is provided, should be same length as `documents`."
+                )
+            doc_ids = ids
 
         docs = []
         full_docs = []
-        for doc in documents:
-            _id = str(uuid.uuid4())
+        for i, doc in enumerate(documents):
+            _id = doc_ids[i]
             sub_docs = self.child_splitter.split_documents([doc])
             for _doc in sub_docs:
                 _doc.metadata[self.id_key] = _id
             docs.extend(sub_docs)
             full_docs.append((_id, doc))
         self.vectorstore.add_documents(docs)
-        self.docstore.mset(full_docs)
+        if add_to_docstore:
+            self.docstore.mset(full_docs)