phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: unpublish /inference/chat-completion

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 09:27:23 -04:00
parent 6cce553c93
commit b0e161d3db
23 changed files with 1448 additions and 2137 deletions
Download patch file Download diff file Expand all files Collapse all files

32
docs/getting_started_llama4.ipynb
View file

@ -577,15 +577,15 @@
}
],
"source": [
"response = client.inference.chat_completion(\n",
" model_id=model_id,\n",
"response = client.chat.completions.create(\n",
" model=model_id,\n",
" messages=[\n",
" {\"role\": \"system\", \"content\": \"You are a friendly assistant.\"},\n",
" {\"role\": \"user\", \"content\": \"Write a two-sentence poem about llama.\"},\n",
" ],\n",
")\n",
"\n",
"print(response.completion_message.content)\n"
"print(response.choices[0].message.content)\n"
]
},
{
@ -673,7 +673,7 @@
}
],
"source": [
"response = client.inference.chat_completion(\n",
"response = client.chat.completions.create(\n",
" messages=[\n",
" {\n",
" \"role\": \"user\",\n",
@ -693,11 +693,11 @@
" ]\n",
" }\n",
" ],\n",
" model_id=model_id,\n",
" model=model_id,\n",
" stream=False,\n",
")\n",
"\n",
"print(response.completion_message.content)"
"print(response.choices[0].message.content)"
]
},
{
@ -767,16 +767,16 @@
" user_message = {\"role\": \"user\", \"content\": user_input}\n",
" conversation_history.append(user_message)\n",
"\n",
" response = client.inference.chat_completion(\n",
" response = client.chat.completions.create(\n",
" messages=conversation_history,\n",
" model_id=model_id,\n",
" model=model_id,\n",
" )\n",
" cprint(f\"> Response: {response.completion_message.content}\", \"cyan\")\n",
" cprint(f\"> Response: {response.choices[0].message.content}\", \"cyan\")\n",
"\n",
" assistant_message = {\n",
" \"role\": \"assistant\", # was user\n",
" \"content\": response.completion_message.content,\n",
" \"stop_reason\": response.completion_message.stop_reason,\n",
" \"content\": response.choices[0].message.content,\n",
" \"stop_reason\": response.choices[0].finish_reason,\n",
" }\n",
" conversation_history.append(assistant_message)\n",
"\n",
@ -831,16 +831,16 @@
" user_message = {\"role\": \"user\", \"content\": user_input}\n",
" conversation_history.append(user_message)\n",
"\n",
" response = client.inference.chat_completion(\n",
" response = client.chat.completions.create(\n",
" messages=conversation_history,\n",
" model_id=model_id,\n",
" model=model_id,\n",
" )\n",
" cprint(f\"> Response: {response.completion_message.content}\", \"cyan\")\n",
" cprint(f\"> Response: {response.choices[0].message.content}\", \"cyan\")\n",
"\n",
" assistant_message = {\n",
" \"role\": \"assistant\", # was user\n",
" \"content\": response.completion_message.content,\n",
" \"stop_reason\": response.completion_message.stop_reason,\n",
" \"content\": response.choices[0].message.content,\n",
" \"stop_reason\": response.choices[0].finish_reason,\n",
" }\n",
" conversation_history.append(assistant_message)\n",
"\n",