removed unnecessary files

docs/source/inference-loop-history.py

@@ -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())

docs/source/inference-loop.py

@@ -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())

docs/source/inference-streaming.py

@@ -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())

docs/source/inference.py

@@ -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")