diff --git a/authors.yaml b/authors.yaml
index 65df76987d..c9f1a2052f 100644
--- a/authors.yaml
+++ b/authors.yaml
@@ -370,4 +370,9 @@ joshbickett:
 lupie:
   name: "Lucie Lozinski"
   website: "https://twitter.com/thisloops"
-  avatar: "https://avatars.githubusercontent.com/u/6293148"
\ No newline at end of file
+  avatar: "https://avatars.githubusercontent.com/u/6293148"
+
+crayon:
+  name: "Crayon"
+  website: "https://github.com/ZhuoZhuoCrayon"
+  avatar: "https://avatars.githubusercontent.com/u/42019787"
diff --git a/examples/How_to_handle_rate_limits.ipynb b/examples/How_to_handle_rate_limits.ipynb
index 9b65287eb2..fc0dc91a23 100644
--- a/examples/How_to_handle_rate_limits.ipynb
+++ b/examples/How_to_handle_rate_limits.ipynb
@@ -83,19 +83,19 @@
      "evalue": "Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}",
      "output_type": "error",
      "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mRateLimitError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[2], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# request a bunch of completions in a loop\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m _ \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;241m100\u001b[39m):\n\u001b[0;32m----> 3\u001b[0m     \u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mchat\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompletions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      4\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mgpt-4o-mini\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      5\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmessages\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrole\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcontent\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mHello\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m}\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m      6\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m10\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      7\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_utils/_utils.py:279\u001b[0m, in \u001b[0;36mrequired_args.<locals>.inner.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    277\u001b[0m             msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMissing required argument: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mquote(missing[\u001b[38;5;241m0\u001b[39m])\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    278\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[0;32m--> 279\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/resources/chat/completions.py:859\u001b[0m, in \u001b[0;36mCompletions.create\u001b[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, reasoning_effort, response_format, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m    817\u001b[0m \u001b[38;5;129m@required_args\u001b[39m([\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m], [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[1;32m    818\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m    819\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    856\u001b[0m     timeout: \u001b[38;5;28mfloat\u001b[39m \u001b[38;5;241m|\u001b[39m httpx\u001b[38;5;241m.\u001b[39mTimeout \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m|\u001b[39m NotGiven \u001b[38;5;241m=\u001b[39m NOT_GIVEN,\n\u001b[1;32m    857\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ChatCompletion \u001b[38;5;241m|\u001b[39m Stream[ChatCompletionChunk]:\n\u001b[1;32m    858\u001b[0m     validate_response_format(response_format)\n\u001b[0;32m--> 859\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    860\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/chat/completions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    861\u001b[0m \u001b[43m        \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    862\u001b[0m \u001b[43m            \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m    863\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmessages\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    864\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    865\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43maudio\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43maudio\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    866\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfrequency_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    867\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunction_call\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunction_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    868\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunctions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    869\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogit_bias\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    870\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    871\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_completion_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_completion_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    872\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    873\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    874\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodalities\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodalities\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    875\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mn\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    876\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mparallel_tool_calls\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mparallel_tool_calls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    877\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mprediction\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mprediction\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    878\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpresence_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    879\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mreasoning_effort\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mreasoning_effort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    880\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mresponse_format\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    881\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseed\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    882\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mservice_tier\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mservice_tier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    883\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstop\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    884\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstore\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstore\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    885\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    886\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    887\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtemperature\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    888\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtool_choice\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtool_choice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    889\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtools\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    890\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_logprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_logprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    891\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_p\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    892\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    893\u001b[0m \u001b[43m            \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    894\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mCompletionCreateParams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    895\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    896\u001b[0m \u001b[43m        \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    897\u001b[0m \u001b[43m            \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[1;32m    898\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    899\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mChatCompletion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    900\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    901\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mStream\u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatCompletionChunk\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    902\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1283\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1269\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m   1270\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1271\u001b[0m     path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1278\u001b[0m     stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1279\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m   1280\u001b[0m     opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m   1281\u001b[0m         method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m   1282\u001b[0m     )\n\u001b[0;32m-> 1283\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:960\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m    957\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    958\u001b[0m     retries_taken \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n\u001b[0;32m--> 960\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    961\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    962\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    963\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    964\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    965\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    966\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1049\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1047\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m   1048\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1049\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1050\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1051\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1052\u001b[0m \u001b[43m        \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1053\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1054\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1055\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1056\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1058\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m   1059\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m   1060\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1098\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1094\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m   1095\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m   1096\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1098\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1099\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1100\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1101\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1102\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1103\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1104\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1049\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1047\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m   1048\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1049\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1050\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1051\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1052\u001b[0m \u001b[43m        \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1053\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1054\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1055\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1056\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1058\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m   1059\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m   1060\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1098\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1094\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m   1095\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m   1096\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1098\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1099\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1100\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1101\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1102\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1103\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1104\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1064\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1061\u001b[0m         err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m   1063\u001b[0m     log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1064\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1066\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m   1067\u001b[0m     cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m   1068\u001b[0m     options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1072\u001b[0m     retries_taken\u001b[38;5;241m=\u001b[39mretries_taken,\n\u001b[1;32m   1073\u001b[0m )\n",
-      "\u001b[0;31mRateLimitError\u001b[0m: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}"
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mRateLimitError\u001B[0m                            Traceback (most recent call last)",
+      "Cell \u001B[0;32mIn[2], line 3\u001B[0m\n\u001B[1;32m      1\u001B[0m \u001B[38;5;66;03m# request a bunch of completions in a loop\u001B[39;00m\n\u001B[1;32m      2\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m _ \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mrange\u001B[39m(\u001B[38;5;241m100\u001B[39m):\n\u001B[0;32m----> 3\u001B[0m     \u001B[43mclient\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mchat\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcompletions\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcreate\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m      4\u001B[0m \u001B[43m        \u001B[49m\u001B[43mmodel\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mgpt-4o-mini\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m      5\u001B[0m \u001B[43m        \u001B[49m\u001B[43mmessages\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m[\u001B[49m\u001B[43m{\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mrole\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43muser\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mcontent\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mHello\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m}\u001B[49m\u001B[43m]\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m      6\u001B[0m \u001B[43m        \u001B[49m\u001B[43mmax_tokens\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;241;43m10\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m      7\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_utils/_utils.py:279\u001B[0m, in \u001B[0;36mrequired_args.<locals>.inner.<locals>.wrapper\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m    277\u001B[0m             msg \u001B[38;5;241m=\u001B[39m \u001B[38;5;124mf\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mMissing required argument: \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mquote(missing[\u001B[38;5;241m0\u001B[39m])\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m    278\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mTypeError\u001B[39;00m(msg)\n\u001B[0;32m--> 279\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mfunc\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/resources/chat/completions.py:859\u001B[0m, in \u001B[0;36mCompletions.create\u001B[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, reasoning_effort, response_format, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001B[0m\n\u001B[1;32m    817\u001B[0m \u001B[38;5;129m@required_args\u001B[39m([\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mmessages\u001B[39m\u001B[38;5;124m\"\u001B[39m, \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mmodel\u001B[39m\u001B[38;5;124m\"\u001B[39m], [\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mmessages\u001B[39m\u001B[38;5;124m\"\u001B[39m, \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mmodel\u001B[39m\u001B[38;5;124m\"\u001B[39m, \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mstream\u001B[39m\u001B[38;5;124m\"\u001B[39m])\n\u001B[1;32m    818\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[38;5;21mcreate\u001B[39m(\n\u001B[1;32m    819\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m    856\u001B[0m     timeout: \u001B[38;5;28mfloat\u001B[39m \u001B[38;5;241m|\u001B[39m httpx\u001B[38;5;241m.\u001B[39mTimeout \u001B[38;5;241m|\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m \u001B[38;5;241m|\u001B[39m NotGiven \u001B[38;5;241m=\u001B[39m NOT_GIVEN,\n\u001B[1;32m    857\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m ChatCompletion \u001B[38;5;241m|\u001B[39m Stream[ChatCompletionChunk]:\n\u001B[1;32m    858\u001B[0m     validate_response_format(response_format)\n\u001B[0;32m--> 859\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_post\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    860\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43m/chat/completions\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m    861\u001B[0m \u001B[43m        \u001B[49m\u001B[43mbody\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mmaybe_transform\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    862\u001B[0m \u001B[43m            \u001B[49m\u001B[43m{\u001B[49m\n\u001B[1;32m    863\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mmessages\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mmessages\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    864\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mmodel\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mmodel\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    865\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43maudio\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43maudio\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    866\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mfrequency_penalty\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mfrequency_penalty\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    867\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mfunction_call\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mfunction_call\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    868\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mfunctions\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mfunctions\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    869\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mlogit_bias\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mlogit_bias\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    870\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mlogprobs\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mlogprobs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    871\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mmax_completion_tokens\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mmax_completion_tokens\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    872\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mmax_tokens\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mmax_tokens\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    873\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mmetadata\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mmetadata\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    874\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mmodalities\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mmodalities\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    875\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mn\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mn\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    876\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mparallel_tool_calls\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mparallel_tool_calls\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    877\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mprediction\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mprediction\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    878\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mpresence_penalty\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mpresence_penalty\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    879\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mreasoning_effort\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mreasoning_effort\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    880\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mresponse_format\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mresponse_format\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    881\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mseed\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mseed\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    882\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mservice_tier\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mservice_tier\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    883\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mstop\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mstop\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    884\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mstore\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mstore\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    885\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mstream\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mstream\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    886\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mstream_options\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mstream_options\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    887\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mtemperature\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mtemperature\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    888\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mtool_choice\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mtool_choice\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    889\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mtools\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mtools\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    890\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mtop_logprobs\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mtop_logprobs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    891\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mtop_p\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mtop_p\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    892\u001B[0m \u001B[43m                \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43muser\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43muser\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    893\u001B[0m \u001B[43m            \u001B[49m\u001B[43m}\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    894\u001B[0m \u001B[43m            \u001B[49m\u001B[43mcompletion_create_params\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mCompletionCreateParams\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    895\u001B[0m \u001B[43m        \u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    896\u001B[0m \u001B[43m        \u001B[49m\u001B[43moptions\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mmake_request_options\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    897\u001B[0m \u001B[43m            \u001B[49m\u001B[43mextra_headers\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mextra_headers\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mextra_query\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mextra_query\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mextra_body\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mextra_body\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mtimeout\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mtimeout\u001B[49m\n\u001B[1;32m    898\u001B[0m \u001B[43m        \u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    899\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcast_to\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mChatCompletion\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    900\u001B[0m \u001B[43m        \u001B[49m\u001B[43mstream\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;129;43;01mor\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mFalse\u001B[39;49;00m\u001B[43m,\u001B[49m\n\u001B[1;32m    901\u001B[0m \u001B[43m        \u001B[49m\u001B[43mstream_cls\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mStream\u001B[49m\u001B[43m[\u001B[49m\u001B[43mChatCompletionChunk\u001B[49m\u001B[43m]\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    902\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1283\u001B[0m, in \u001B[0;36mSyncAPIClient.post\u001B[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001B[0m\n\u001B[1;32m   1269\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[38;5;21mpost\u001B[39m(\n\u001B[1;32m   1270\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1271\u001B[0m     path: \u001B[38;5;28mstr\u001B[39m,\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1278\u001B[0m     stream_cls: \u001B[38;5;28mtype\u001B[39m[_StreamT] \u001B[38;5;241m|\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1279\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m ResponseT \u001B[38;5;241m|\u001B[39m _StreamT:\n\u001B[1;32m   1280\u001B[0m     opts \u001B[38;5;241m=\u001B[39m FinalRequestOptions\u001B[38;5;241m.\u001B[39mconstruct(\n\u001B[1;32m   1281\u001B[0m         method\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mpost\u001B[39m\u001B[38;5;124m\"\u001B[39m, url\u001B[38;5;241m=\u001B[39mpath, json_data\u001B[38;5;241m=\u001B[39mbody, files\u001B[38;5;241m=\u001B[39mto_httpx_files(files), \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39moptions\n\u001B[1;32m   1282\u001B[0m     )\n\u001B[0;32m-> 1283\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m cast(ResponseT, \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrequest\u001B[49m\u001B[43m(\u001B[49m\u001B[43mcast_to\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mopts\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mstream\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mstream_cls\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream_cls\u001B[49m\u001B[43m)\u001B[49m)\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:960\u001B[0m, in \u001B[0;36mSyncAPIClient.request\u001B[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001B[0m\n\u001B[1;32m    957\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m    958\u001B[0m     retries_taken \u001B[38;5;241m=\u001B[39m \u001B[38;5;241m0\u001B[39m\n\u001B[0;32m--> 960\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    961\u001B[0m \u001B[43m    \u001B[49m\u001B[43mcast_to\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mcast_to\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    962\u001B[0m \u001B[43m    \u001B[49m\u001B[43moptions\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43moptions\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    963\u001B[0m \u001B[43m    \u001B[49m\u001B[43mstream\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    964\u001B[0m \u001B[43m    \u001B[49m\u001B[43mstream_cls\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream_cls\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    965\u001B[0m \u001B[43m    \u001B[49m\u001B[43mretries_taken\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mretries_taken\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    966\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1049\u001B[0m, in \u001B[0;36mSyncAPIClient._request\u001B[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001B[0m\n\u001B[1;32m   1047\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m remaining_retries \u001B[38;5;241m>\u001B[39m \u001B[38;5;241m0\u001B[39m \u001B[38;5;129;01mand\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_should_retry(err\u001B[38;5;241m.\u001B[39mresponse):\n\u001B[1;32m   1048\u001B[0m     err\u001B[38;5;241m.\u001B[39mresponse\u001B[38;5;241m.\u001B[39mclose()\n\u001B[0;32m-> 1049\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_retry_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1050\u001B[0m \u001B[43m        \u001B[49m\u001B[43minput_options\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1051\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcast_to\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1052\u001B[0m \u001B[43m        \u001B[49m\u001B[43mretries_taken\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mretries_taken\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1053\u001B[0m \u001B[43m        \u001B[49m\u001B[43mresponse_headers\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43merr\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mresponse\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1054\u001B[0m \u001B[43m        \u001B[49m\u001B[43mstream\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1055\u001B[0m \u001B[43m        \u001B[49m\u001B[43mstream_cls\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream_cls\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1056\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1058\u001B[0m \u001B[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001B[39;00m\n\u001B[1;32m   1059\u001B[0m \u001B[38;5;66;03m# to completion before attempting to access the response text.\u001B[39;00m\n\u001B[1;32m   1060\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m err\u001B[38;5;241m.\u001B[39mresponse\u001B[38;5;241m.\u001B[39mis_closed:\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1098\u001B[0m, in \u001B[0;36mSyncAPIClient._retry_request\u001B[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001B[0m\n\u001B[1;32m   1094\u001B[0m \u001B[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001B[39;00m\n\u001B[1;32m   1095\u001B[0m \u001B[38;5;66;03m# different thread if necessary.\u001B[39;00m\n\u001B[1;32m   1096\u001B[0m time\u001B[38;5;241m.\u001B[39msleep(timeout)\n\u001B[0;32m-> 1098\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1099\u001B[0m \u001B[43m    \u001B[49m\u001B[43moptions\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43moptions\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1100\u001B[0m \u001B[43m    \u001B[49m\u001B[43mcast_to\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mcast_to\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1101\u001B[0m \u001B[43m    \u001B[49m\u001B[43mretries_taken\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mretries_taken\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m+\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;241;43m1\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1102\u001B[0m \u001B[43m    \u001B[49m\u001B[43mstream\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1103\u001B[0m \u001B[43m    \u001B[49m\u001B[43mstream_cls\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream_cls\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1104\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1049\u001B[0m, in \u001B[0;36mSyncAPIClient._request\u001B[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001B[0m\n\u001B[1;32m   1047\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m remaining_retries \u001B[38;5;241m>\u001B[39m \u001B[38;5;241m0\u001B[39m \u001B[38;5;129;01mand\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_should_retry(err\u001B[38;5;241m.\u001B[39mresponse):\n\u001B[1;32m   1048\u001B[0m     err\u001B[38;5;241m.\u001B[39mresponse\u001B[38;5;241m.\u001B[39mclose()\n\u001B[0;32m-> 1049\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_retry_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1050\u001B[0m \u001B[43m        \u001B[49m\u001B[43minput_options\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1051\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcast_to\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1052\u001B[0m \u001B[43m        \u001B[49m\u001B[43mretries_taken\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mretries_taken\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1053\u001B[0m \u001B[43m        \u001B[49m\u001B[43mresponse_headers\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43merr\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mresponse\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1054\u001B[0m \u001B[43m        \u001B[49m\u001B[43mstream\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1055\u001B[0m \u001B[43m        \u001B[49m\u001B[43mstream_cls\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream_cls\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1056\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1058\u001B[0m \u001B[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001B[39;00m\n\u001B[1;32m   1059\u001B[0m \u001B[38;5;66;03m# to completion before attempting to access the response text.\u001B[39;00m\n\u001B[1;32m   1060\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m err\u001B[38;5;241m.\u001B[39mresponse\u001B[38;5;241m.\u001B[39mis_closed:\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1098\u001B[0m, in \u001B[0;36mSyncAPIClient._retry_request\u001B[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001B[0m\n\u001B[1;32m   1094\u001B[0m \u001B[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001B[39;00m\n\u001B[1;32m   1095\u001B[0m \u001B[38;5;66;03m# different thread if necessary.\u001B[39;00m\n\u001B[1;32m   1096\u001B[0m time\u001B[38;5;241m.\u001B[39msleep(timeout)\n\u001B[0;32m-> 1098\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1099\u001B[0m \u001B[43m    \u001B[49m\u001B[43moptions\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43moptions\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1100\u001B[0m \u001B[43m    \u001B[49m\u001B[43mcast_to\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mcast_to\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1101\u001B[0m \u001B[43m    \u001B[49m\u001B[43mretries_taken\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mretries_taken\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m+\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;241;43m1\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1102\u001B[0m \u001B[43m    \u001B[49m\u001B[43mstream\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1103\u001B[0m \u001B[43m    \u001B[49m\u001B[43mstream_cls\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mstream_cls\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1104\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/openai-cookbook/.venv/lib/python3.9/site-packages/openai/_base_client.py:1064\u001B[0m, in \u001B[0;36mSyncAPIClient._request\u001B[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001B[0m\n\u001B[1;32m   1061\u001B[0m         err\u001B[38;5;241m.\u001B[39mresponse\u001B[38;5;241m.\u001B[39mread()\n\u001B[1;32m   1063\u001B[0m     log\u001B[38;5;241m.\u001B[39mdebug(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mRe-raising status error\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[0;32m-> 1064\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_make_status_error_from_response(err\u001B[38;5;241m.\u001B[39mresponse) \u001B[38;5;28;01mfrom\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[1;32m   1066\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_process_response(\n\u001B[1;32m   1067\u001B[0m     cast_to\u001B[38;5;241m=\u001B[39mcast_to,\n\u001B[1;32m   1068\u001B[0m     options\u001B[38;5;241m=\u001B[39moptions,\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1072\u001B[0m     retries_taken\u001B[38;5;241m=\u001B[39mretries_taken,\n\u001B[1;32m   1073\u001B[0m )\n",
+      "\u001B[0;31mRateLimitError\u001B[0m: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}"
      ]
     }
    ],
@@ -134,13 +134,21 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Example #1: Using the Tenacity library\n",
+    "#### Example #1: Using the Tenacity library and the throttled-py library\n",
     "\n",
     "[Tenacity](https://tenacity.readthedocs.io/en/latest/) is an Apache 2.0 licensed general-purpose retrying library, written in Python, to simplify the task of adding retry behavior to just about anything.\n",
     "\n",
+    "[throttled-py](https://github.com/ZhuoZhuoCrayon/throttled-py) is a Python rate limiting library with multiple algorithms (Fixed Window, Sliding Window, Token Bucket, Leaky Bucket & GCRA) and storage backends (Redis, In-Memory).\n",
+    "\n",
+    "Simply backing off and retrying will waste part of the request budget on unnecessary retries.\n",
+    "\n",
+    "By using the [GCRA](https://en.wikipedia.org/wiki/Generic_cell_rate_algorithm) rate limiting strategy provided by throttled-py in [Wait & Retry mode](https://github.com/ZhuoZhuoCrayon/throttled-py?tab=readme-ov-file#wait--retry), the API call process can smoothly adhere to OpenAI API rate limiting rules.\n",
+    "\n",
+    "This approach reduces invalid API request budget consumption and integrates tenacity to handle exceptions, thereby improving call success rates.\n",
+    "\n",
     "To add exponential backoff to your requests, you can use the `tenacity.retry` [decorator](https://peps.python.org/pep-0318/). The following example uses the `tenacity.wait_random_exponential` function to add random exponential backoff to a request.\n",
     "\n",
-    "Note that the Tenacity library is a third-party tool, and OpenAI makes no guarantees about its reliability or security."
+    "Note that Tenacity and throttled-py are third-party tools, and OpenAI does not guarantee these tools' reliability or security.\n"
    ]
   },
   {
@@ -165,8 +173,18 @@
     "    stop_after_attempt,\n",
     "    wait_random_exponential,\n",
     ")  # for exponential backoff\n",
+    "from throttled import Throttled, rate_limiter\n",
     "\n",
     "@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))\n",
+    "@Throttled(\n",
+    "    key=\"chat.completions.create\",\n",
+    "     # Adjust the rate limit as needed\n",
+    "    quota=rate_limiter.per_min(60, burst=20),\n",
+    "    # Use GCRA rate limiting strategy\n",
+    "    using=\"gcra\",\n",
+    "    # Set timeout=5 to enable wait-and-retry (max wait 5 second)\n",
+    "    timeout=5,\n",
+    ")\n",
     "def completion_with_backoff(**kwargs):\n",
     "    return client.chat.completions.create(**kwargs)\n",
     "\n",
diff --git a/registry.yaml b/registry.yaml
index d84d06caf0..2a398b330e 100644
--- a/registry.yaml
+++ b/registry.yaml
@@ -396,6 +396,7 @@
   authors:
     - ted-at-openai
     - dwigg-openai
+    - crayon
   tags:
     - completions
     - embeddings