You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/docs/examples/memory/custom_multi_turn_memory.ipynb
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@
6
6
"source": [
7
7
"# Reducing Multi-Turn Confusion with LlamaIndex Memory\n",
8
8
"\n",
9
-
"[Recent research](https://arxiv.org/abs/2505.06120) has shown that the past two turns of a converstation, performance of that LLM can start to greatly degrade.\n",
9
+
"[Recent research](https://arxiv.org/abs/2505.06120) has shown the performance of an LLM significantly degrades given multi-turn conversations.\n",
10
10
"\n",
11
11
"To help avoid this, we can implement a custom short-term and long-term memory in LlamaIndex to ensure that the conversation turns never get too long, and condense the memory as we go.\n",
0 commit comments