openai
diff --git a/‎examples/Context_summarization_with_realtime_api.ipynb‎
Lines changed: 3 additions & 1 deletion b/‎examples/Context_summarization_with_realtime_api.ipynb‎
Lines changed: 3 additions & 1 deletion
diff --git a/‎images/text-vs-audio-tokens.png‎
2.26 MB b/‎images/text-vs-audio-tokens.png‎
2.26 MB
@@ -98,7 +98,9 @@
     "\n",
     "* GPT-4o realtime accepts up to **128k tokens** and as the token size increases instruction adherence can drifts.\n",
     "* Every user/assistant turn consumes tokens → the window **only grows**.\n",
-    "* **Strategy**: Summarise older turns into a single assistant message, keep the last few verbatim turns, and continue.\n"
+    "* **Strategy**: Summarise older turns into a single assistant message, keep the last few verbatim turns, and continue.\n",
+    "\n",
+    "<img src=\"../images/text-vs-audio-tokens.png\" alt=\"drawing\" width=\"800\"/>"
    ]
   },
   {
Original file line number	Diff line number	Diff line change
`@@ -98,7 +98,9 @@`
`98`	`98`	`"\n",`
`99`	`99`	`"* GPT-4o realtime accepts up to 128k tokens and as the token size increases instruction adherence can drifts.\n",`
`100`	`100`	`"* Every user/assistant turn consumes tokens → the window only grows.\n",`
`101`		`- "* Strategy: Summarise older turns into a single assistant message, keep the last few verbatim turns, and continue.\n"`
	`101`	`+ "* Strategy: Summarise older turns into a single assistant message, keep the last few verbatim turns, and continue.\n",`
	`102`	`+ "\n",`
	`103`	`+ "<img src=\"../images/text-vs-audio-tokens.png\" alt=\"drawing\" width=\"800\"/>"`
`102`	`104`	`]`
`103`	`105`	`},`
`104`	`106`	`{`