diff --git a/docs/docs/how_to/qa_sources.ipynb b/docs/docs/how_to/qa_sources.ipynb
index 57104ea64d8c3..e7833ce6001a3 100644
--- a/docs/docs/how_to/qa_sources.ipynb
+++ b/docs/docs/how_to/qa_sources.ipynb
@@ -417,7 +417,7 @@
    "id": "82c8e1ec-6f77-468b-a06d-f032a9fe3488",
    "metadata": {},
    "source": [
-    "[Part 2](/docs/tutorial/qa_chat_history) of the RAG tutorial implements a different architecture, in which steps in the RAG flow are represented via successive [message](/docs/concepts/messages/) objects. This leverages additional [tool-calling](/docs/concepts/tool_calling/) features of chat models, and more naturally accommodates a \"back-and-forth\" conversational user experience.\n",
+    "[Part 2](/docs/tutorials/qa_chat_history) of the RAG tutorial implements a different architecture, in which steps in the RAG flow are represented via successive [message](/docs/concepts/messages/) objects. This leverages additional [tool-calling](/docs/concepts/tool_calling/) features of chat models, and more naturally accommodates a \"back-and-forth\" conversational user experience.\n",
     "\n",
     "In that tutorial (and below), we propagate the retrieved documents as [artifacts](/docs/how_to/tool_artifacts/) on the tool messages. That makes it easy to pluck out the retrieved documents. Below, we add them as an additional key in the state, for convenience.\n",
     "\n",
@@ -450,7 +450,7 @@
    "id": "f0e4859f-efad-41d0-aca3-2a6f314464e1",
    "metadata": {},
    "source": [
-    "We can now build and compile the exact same application as in [Part 2](/docs/tutorial/qa_chat_history) of the RAG tutorial, with two changes:\n",
+    "We can now build and compile the exact same application as in [Part 2](/docs/tutorials/qa_chat_history) of the RAG tutorial, with two changes:\n",
     "\n",
     "1. We add a `context` key of the state to store retrieved documents;\n",
     "2. In the `generate` step, we pluck out the retrieved documents and populate them in the state.\n",