|
@@ -96,7 +96,7 @@
|
|
"Streaming allows the generated tokens to be sent as data-only server-sent events whenever they become available. \n",
|
|
"Streaming allows the generated tokens to be sent as data-only server-sent events whenever they become available. \n",
|
|
"This is extremely important for interactive applications such as chatbots, so the user is always engaged. \n",
|
|
"This is extremely important for interactive applications such as chatbots, so the user is always engaged. \n",
|
|
"\n",
|
|
"\n",
|
|
- "To use streaming, simply set `\"stream\":\"True\"` as part of the request payload. \n",
|
|
|
|
|
|
+ "To use streaming, simply set `\"stream\":True` as part of the request payload. \n",
|
|
"In the streaming mode, the REST API response will be different from non-streaming mode.\n",
|
|
"In the streaming mode, the REST API response will be different from non-streaming mode.\n",
|
|
"\n",
|
|
"\n",
|
|
"Here is an example: "
|
|
"Here is an example: "
|
|
@@ -108,7 +108,7 @@
|
|
"metadata": {},
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"outputs": [],
|
|
"source": [
|
|
"source": [
|
|
- "!curl -X POST -L https://your-endpoint.inference.ai.azure.com/v1/chat/completions -H 'Content-Type: application/json' -H 'Authorization: your-auth-key' -d '{\"messages\":[{\"content\":\"You are a helpful assistant.\",\"role\":\"system\"},{\"content\":\"Who wrote the book Innovators dilemma?\",\"role\":\"user\"}], \"max_tokens\": 500, \"stream\": \"True\"}'"
|
|
|
|
|
|
+ "!curl -X POST -L https://your-endpoint.inference.ai.azure.com/v1/chat/completions -H 'Content-Type: application/json' -H 'Authorization: your-auth-key' -d '{\"messages\":[{\"content\":\"You are a helpful assistant.\",\"role\":\"system\"},{\"content\":\"Who wrote the book Innovators dilemma?\",\"role\":\"user\"}], \"max_tokens\": 500, \"stream\": True}'"
|
|
]
|
|
]
|
|
},
|
|
},
|
|
{
|
|
{
|
|
@@ -170,7 +170,7 @@
|
|
" {\"role\":\"user\", \"content\":\"Who wrote the book Innovators dilemma?\"}], \n",
|
|
" {\"role\":\"user\", \"content\":\"Who wrote the book Innovators dilemma?\"}], \n",
|
|
" \"max_tokens\": 500,\n",
|
|
" \"max_tokens\": 500,\n",
|
|
" \"temperature\": 0.9,\n",
|
|
" \"temperature\": 0.9,\n",
|
|
- " \"stream\": \"True\",\n",
|
|
|
|
|
|
+ " \"stream\": True,\n",
|
|
"}\n",
|
|
"}\n",
|
|
"\n",
|
|
"\n",
|
|
"body = str.encode(json.dumps(data))\n",
|
|
"body = str.encode(json.dumps(data))\n",
|
|
@@ -230,7 +230,7 @@
|
|
" {\"role\":\"user\", \"content\":\"Who wrote the book Innovators dilemma?\"}],\n",
|
|
" {\"role\":\"user\", \"content\":\"Who wrote the book Innovators dilemma?\"}],\n",
|
|
" \"max_tokens\": 500,\n",
|
|
" \"max_tokens\": 500,\n",
|
|
" \"temperature\": 0.9,\n",
|
|
" \"temperature\": 0.9,\n",
|
|
- " \"stream\": \"True\"\n",
|
|
|
|
|
|
+ " \"stream\": True\n",
|
|
"}\n",
|
|
"}\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|