phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-30 07:39:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

removed unnecessary files

Browse source
This commit is contained in:
Justin Lee 2024-11-01 13:56:54 -07:00
parent 43289c36e1
commit 78083c4e0a
4 changed files with 0 additions and 127 deletions
Download patch file Download diff file Expand all files Collapse all files

37
docs/source/inference-loop-history.py
View file

@ -1,37 +0,0 @@
import asyncio
from llama_stack_client import LlamaStackClient
from llama_stack_client.types import UserMessage
from termcolor import cprint
client = LlamaStackClient(
base_url="http://localhost:5000",
)
async def chat_loop():
conversation_history = []
while True:
user_input = input("User> ")
if user_input.lower() in ["exit", "quit", "bye"]:
cprint("Ending conversation. Goodbye!", "yellow")
break
user_message = UserMessage(content=user_input, role="user")
conversation_history.append(user_message)
response = client.inference.chat_completion(
messages=conversation_history,
model="Llama3.2-11B-Vision-Instruct",
)
cprint(f"> Response: {response.completion_message.content}", "cyan")
assistant_message = UserMessage(
content=response.completion_message.content, role="user"
)
conversation_history.append(assistant_message)
asyncio.run(chat_loop())

32
docs/source/inference-loop.py
View file

@ -1,32 +0,0 @@
import asyncio
from llama_stack_client import LlamaStackClient
from llama_stack_client.lib.inference.event_logger import EventLogger
from llama_stack_client.types import UserMessage
from termcolor import cprint
client = LlamaStackClient(
base_url="http://localhost:5000",
)
async def chat_loop():
while True:
user_input = input("User> ")
if user_input.lower() in ["exit", "quit", "bye"]:
cprint("Ending conversation. Goodbye!", "yellow")
break
message = UserMessage(content=user_input, role="user")
response = client.inference.chat_completion(
messages=[message],
model="Llama3.2-11B-Vision-Instruct",
)
cprint(f"> Response: {response.completion_message.content}", "cyan")
asyncio.run(chat_loop())

36
docs/source/inference-streaming.py
View file

@ -1,36 +0,0 @@
import asyncio
from llama_stack_client import LlamaStackClient
from llama_stack_client.lib.inference.event_logger import EventLogger
from llama_stack_client.types import UserMessage
from termcolor import cprint
async def run_main(stream: bool = True):
client = LlamaStackClient(
base_url=f"http://localhost:5000",
)
message = UserMessage(
content="hello world, write me a 2 sentence poem about the moon", role="user"
)
print(f"User>{message.content}", "green")
response = client.inference.chat_completion(
messages=[message],
model="Llama3.2-11B-Vision-Instruct",
stream=stream,
)
if not stream:
cprint(f"> Response: {response}", "cyan")
else:
async for log in EventLogger().log(response):
log.print()
models_response = client.models.list()
print(models_response)
if __name__ == "__main__":
asyncio.run(run_main())

22
docs/source/inference.py
View file

@ -1,22 +0,0 @@
import asyncio
from llama_stack_client import LlamaStackClient
from llama_stack_client.lib.inference.event_logger import EventLogger
from llama_stack_client.types import UserMessage
from termcolor import cprint
client = LlamaStackClient(
base_url=f"http://localhost:5000",
)
message = UserMessage(
content="hello world, write me a 2 sentence poem about the moon", role="user"
)
cprint(f"User>{message.content}", "green")
response = client.inference.chat_completion(
messages=[message],
model="Llama3.2-11B-Vision-Instruct",
)
cprint(f"> Response: {response.completion_message.content}", "cyan")