phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 09:02:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

.

Browse source
This commit is contained in:
Aidan Do 2024-11-26 10:49:48 +00:00
parent f6f3f3c792
commit 85ae899964
1 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
1.py
View file

@ -14,19 +14,21 @@ client = LlamaStackClient(base_url=f"http://localhost:{os.environ['LLAMA_STACK_P
class CompletionMessage(BaseModel): class CompletionMessage(BaseModel):
content: str recipe_name: str
additional_info: str ingredients: list[str]
steps: list[str]
response = client.inference.chat_completion( response = client.inference.chat_completion(
model_id=os.environ["INFERENCE_MODEL"], model_id=os.environ["INFERENCE_MODEL"],
messages=[ messages=[
{"role": "system", "content": "You are a helpful assistant."}, {"role": "system", "content": "You are a chef."},
{"role": "user", "content": "Write a haiku about coding"}, {"role": "user", "content": "Give me a recipe for spaghetti bolognaise"},
], ],
response_format={ response_format={
"type": "json_schema", "type": "json_schema",
"json_schema": CompletionMessage.model_json_schema(), "json_schema": CompletionMessage.model_json_schema(),
}, },
sampling_params={"max_tokens": 8000},
) )
print(response.completion_message.content) print(response.completion_message.content)