fix: sort SentenceWindowRetriever context before merging text

haystack/components/retrievers/sentence_window_retriever.py

@@ -322,8 +322,9 @@ def _assemble_context(
                 for fetched in fetched_documents
                 if self._is_in_window(fetched, source_ids, split_id - window_size, split_id + window_size)
             ]
-            context_text.append(self.merge_documents_text(context_docs))
-            context_documents.extend(sorted(context_docs, key=lambda d: d.meta[self.split_id_meta_field]))
+            context_docs_sorted = sorted(context_docs, key=lambda d: d.meta[self.split_id_meta_field])
+            context_text.append(self.merge_documents_text(context_docs_sorted))
+            context_documents.extend(context_docs_sorted)
 
         return {"context_windows": context_text, "context_documents": context_documents}
 

releasenotes/notes/fix-sentence-window-retriever-context-order-a1267b171dea93bb.yaml

@@ -0,0 +1,8 @@
+---
+fixes:
+  - |
+    Fixed ``SentenceWindowRetriever`` returning ``context_windows`` with the chunks in the wrong order when the
+    documents have no ``split_idx_start`` meta field, for example chunks produced by ``MarkdownHeaderSplitter``.
+    The chunks were concatenated in the order returned by the Document Store instead of by ``split_id``, so the
+    context passed to an LLM could be scrambled while ``context_documents`` was correctly sorted. The chunks are now
+    sorted by ``split_id`` before being merged, in both ``run`` and ``run_async``.

test/components/retrievers/test_sentence_window_retriever.py

@@ -284,6 +284,10 @@ def test_run_custom_fields(self, in_memory_doc_store):
         # run the retriever with a document whose content = "Sentence 4."
         result = retriever.run(retrieved_documents=[doc for doc in docs if doc.content == "Sentence 4."])
         assert len(result["context_documents"]) == 7
+        assert [doc.meta["split_id_test"] for doc in result["context_documents"]] == [1, 2, 3, 4, 5, 6, 7]
+        assert result["context_windows"] == [
+            "Sentence 1.Sentence 2.Sentence 3.Sentence 4.Sentence 5.Sentence 6.Sentence 7."
+        ]
 
     def test_run_with_multiple_source_ids(self, in_memory_doc_store):
         docs = [

test/components/retrievers/test_sentence_window_retriever_async.py

@@ -176,6 +176,10 @@ async def test_run_async_custom_fields(self, in_memory_doc_store):
         # run the retriever with a document whose content = "Sentence 4."
         result = await retriever.run_async(retrieved_documents=[doc for doc in docs if doc.content == "Sentence 4."])
         assert len(result["context_documents"]) == 7
+        assert [doc.meta["split_id_test"] for doc in result["context_documents"]] == [1, 2, 3, 4, 5, 6, 7]
+        assert result["context_windows"] == [
+            "Sentence 1.Sentence 2.Sentence 3.Sentence 4.Sentence 5.Sentence 6.Sentence 7."
+        ]
 
     @pytest.mark.asyncio
     async def test_run_async_with_multiple_source_ids(self, in_memory_doc_store):