mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 22:47:59 +00:00
pr review changes
This commit is contained in:
Justin Lee
parent
6dd5ea7631
commit
c79c8367b7
6 changed files with 152 additions and 209 deletions
|
|
@ -77,7 +77,6 @@
|
|||
"outputs": [],
|
||||
"source": [
|
||||
"from llama_stack_client import LlamaStackClient\n",
|
||||
"from llama_stack_client.types import SystemMessage, UserMessage\n",
|
||||
"\n",
|
||||
"client = LlamaStackClient(base_url=f'http://{HOST}:{PORT}')"
|
||||
]
|
||||
|
|
@ -102,18 +101,18 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"A gentle llama roams the land,\n",
|
||||
"With soft fur and a gentle hand.\n"
|
||||
"With soft fur and gentle eyes,\n",
|
||||
"The llama roams, a peaceful surprise.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"response = client.inference.chat_completion(\n",
|
||||
" messages=[\n",
|
||||
" SystemMessage(content='You are a friendly assistant.', role='system'),\n",
|
||||
" UserMessage(content='Write a two-sentence poem about llama.', role='user')\n",
|
||||
" {\"role\": \"system\", \"content\": \"You are a friendly assistant.\"},\n",
|
||||
" {\"role\": \"user\", \"content\": \"Write a two-sentence poem about llama.\"}\n",
|
||||
" ],\n",
|
||||
" model='Llama3.1-8B-Instruct',\n",
|
||||
" model='Llama3.2-11B-Vision-Instruct',\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print(response.completion_message.content)"
|
||||
|
|
@ -128,11 +127,6 @@
|
|||
"\n",
|
||||
"Effective prompt creation (often called 'prompt engineering') is essential for quality responses. Here are best practices for structuring your prompts to get the most out of the Llama Stack model:\n",
|
||||
"\n",
|
||||
"1. **System Messages**: Use `SystemMessage` to set the model's behavior. This is similar to providing top-level instructions for tone, format, or specific behavior.\n",
|
||||
" - **Example**: `SystemMessage(content='You are a friendly assistant that explains complex topics simply.')`\n",
|
||||
"2. **User Messages**: Define the task or question you want to ask the model with a `UserMessage`. The clearer and more direct you are, the better the response.\n",
|
||||
" - **Example**: `UserMessage(content='Explain recursion in programming in simple terms.')`\n",
|
||||
"\n",
|
||||
"### Sample Prompt"
|
||||
]
|
||||
},
|
||||
|
|
@ -154,10 +148,10 @@
|
|||
"source": [
|
||||
"response = client.inference.chat_completion(\n",
|
||||
" messages=[\n",
|
||||
" SystemMessage(content='You are shakespeare.', role='system'),\n",
|
||||
" UserMessage(content='Write a two-sentence poem about llama.', role='user')\n",
|
||||
" {\"role\": \"system\", \"content\": \"You are shakespeare.\"},\n",
|
||||
" {\"role\": \"user\", \"content\": \"Write a two-sentence poem about llama.\"}\n",
|
||||
" ],\n",
|
||||
" model='Llama3.1-8B-Instruct',\n",
|
||||
" model='Llama3.2-11B-Vision-Instruct',\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print(response.completion_message.content)"
|
||||
|
|
@ -175,45 +169,57 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": null,
|
||||
"id": "02211625",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"User> Write me a 3 sentence poem about alpaca\n"
|
||||
"User> 1+1\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[36m> Response: Softly grazing, gentle soul,\n",
|
||||
"Alpaca's fleece, a treasure whole,\n",
|
||||
"In Andean fields, they softly roll.\u001b[0m\n"
|
||||
"\u001b[36m> Response: 2\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"User> what is llama\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"User> exit\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[33mEnding conversation. Goodbye!\u001b[0m\n"
|
||||
"\u001b[36m> Response: A llama is a domesticated mammal native to South America, specifically the Andean region. It belongs to the camelid family, which also includes camels, alpacas, guanacos, and vicuñas.\n",
|
||||
"\n",
|
||||
"Here are some interesting facts about llamas:\n",
|
||||
"\n",
|
||||
"1. **Physical Characteristics**: Llamas are large, even-toed ungulates with a distinctive appearance. They have a long neck, a small head, and a soft, woolly coat that can be various colors, including white, brown, gray, and black.\n",
|
||||
"2. **Size**: Llamas typically grow to be between 5 and 6 feet (1.5 to 1.8 meters) tall at the shoulder and weigh between 280 and 450 pounds (127 to 204 kilograms).\n",
|
||||
"3. **Habitat**: Llamas are native to the Andean highlands, where they live in herds and roam freely. They are well adapted to the harsh, high-altitude climate of the Andes.\n",
|
||||
"4. **Diet**: Llamas are herbivores and feed on a variety of plants, including grasses, leaves, and shrubs. They are known for their ability to digest plant material that other animals cannot.\n",
|
||||
"5. **Behavior**: Llamas are social animals and live in herds. They are known for their intelligence, curiosity, and strong sense of self-preservation.\n",
|
||||
"6. **Purpose**: Llamas have been domesticated for thousands of years and have been used for a variety of purposes, including:\n",
|
||||
"\t* **Pack animals**: Llamas are often used as pack animals, carrying goods and supplies over long distances.\n",
|
||||
"\t* **Fiber production**: Llama wool is highly valued for its softness, warmth, and durability.\n",
|
||||
"\t* **Meat**: Llama meat is consumed in some parts of the world, particularly in South America.\n",
|
||||
"\t* **Companionship**: Llamas are often kept as pets or companions, due to their gentle nature and intelligence.\n",
|
||||
"\n",
|
||||
"Overall, llamas are fascinating animals that have been an integral part of Andean culture for thousands of years.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import asyncio\n",
|
||||
"from llama_stack_client import LlamaStackClient\n",
|
||||
"from llama_stack_client.types import UserMessage\n",
|
||||
"from termcolor import cprint\n",
|
||||
"\n",
|
||||
"client = LlamaStackClient(base_url=f'http://{HOST}:{PORT}')\n",
|
||||
|
|
@ -225,17 +231,17 @@
|
|||
" cprint('Ending conversation. Goodbye!', 'yellow')\n",
|
||||
" break\n",
|
||||
"\n",
|
||||
" message = UserMessage(content=user_input, role='user')\n",
|
||||
" message = {\"role\": \"user\", \"content\": user_input}\n",
|
||||
" response = client.inference.chat_completion(\n",
|
||||
" messages=[message],\n",
|
||||
" model='Llama3.1-8B-Instruct',\n",
|
||||
" model='Llama3.2-11B-Vision-Instruct',\n",
|
||||
" )\n",
|
||||
" cprint(f'> Response: {response.completion_message.content}', 'cyan')\n",
|
||||
"\n",
|
||||
"# Run the chat loop in a Jupyter Notebook cell using `await`\n",
|
||||
"# Run the chat loop in a Jupyter Notebook cell using await\n",
|
||||
"await chat_loop()\n",
|
||||
"# To run it in a python file, use this line instead\n",
|
||||
"# asyncio.run(chat_loop())"
|
||||
"# asyncio.run(chat_loop())\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -250,66 +256,15 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": null,
|
||||
"id": "9496f75c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"User> what is 1+1\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[36m> Response: 1 + 1 = 2\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"User> what is llama + alpaca\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[36m> Response: That's a creative and imaginative question. However, since llamas and alpacas are animals, not numbers, we can't perform a mathematical operation on them.\n",
|
||||
"\n",
|
||||
"But if we were to interpret this as a creative or humorous question, we could say that the result of \"llama + alpaca\" is a fun and fuzzy bundle of South American camelid cuteness!\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"User> what was the first question\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[36m> Response: The first question was \"what is 1+1\"\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"User> exit\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[33mEnding conversation. Goodbye!\u001b[0m\n"
|
||||
"User> 1+1\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -322,22 +277,27 @@
|
|||
" cprint('Ending conversation. Goodbye!', 'yellow')\n",
|
||||
" break\n",
|
||||
"\n",
|
||||
" user_message = UserMessage(content=user_input, role='user')\n",
|
||||
" user_message = {\"role\": \"user\", \"content\": user_input}\n",
|
||||
" conversation_history.append(user_message)\n",
|
||||
"\n",
|
||||
" response = client.inference.chat_completion(\n",
|
||||
" messages=conversation_history,\n",
|
||||
" model='Llama3.1-8B-Instruct',\n",
|
||||
" model='Llama3.2-11B-Vision-Instruct',\n",
|
||||
" )\n",
|
||||
" cprint(f'> Response: {response.completion_message.content}', 'cyan')\n",
|
||||
"\n",
|
||||
" assistant_message = UserMessage(content=response.completion_message.content, role='user')\n",
|
||||
" # Append the assistant message with all required fields\n",
|
||||
" assistant_message = {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": response.completion_message.content,\n",
|
||||
" # Add any additional required fields here if necessary\n",
|
||||
" }\n",
|
||||
" conversation_history.append(assistant_message)\n",
|
||||
"\n",
|
||||
"# Use `await` in the Jupyter Notebook cell to call the function\n",
|
||||
"await chat_loop()\n",
|
||||
"# To run it in a python file, use this line instead\n",
|
||||
"# asyncio.run(chat_loop())"
|
||||
"# asyncio.run(chat_loop())\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -354,39 +314,25 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": null,
|
||||
"id": "d119026e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[32mUser> Write me a 3 sentence poem about llama\u001b[0m\n",
|
||||
"\u001b[36mAssistant> \u001b[0m\u001b[33mSoft\u001b[0m\u001b[33mly\u001b[0m\u001b[33m padded\u001b[0m\u001b[33m feet\u001b[0m\u001b[33m on\u001b[0m\u001b[33m the\u001b[0m\u001b[33m ground\u001b[0m\u001b[33m,\n",
|
||||
"\u001b[0m\u001b[33mA\u001b[0m\u001b[33m gentle\u001b[0m\u001b[33m llama\u001b[0m\u001b[33m's\u001b[0m\u001b[33m peaceful\u001b[0m\u001b[33m sound\u001b[0m\u001b[33m,\n",
|
||||
"\u001b[0m\u001b[33mF\u001b[0m\u001b[33murry\u001b[0m\u001b[33m coat\u001b[0m\u001b[33m and\u001b[0m\u001b[33m calm\u001b[0m\u001b[33m,\u001b[0m\u001b[33m serene\u001b[0m\u001b[33m eyes\u001b[0m\u001b[33m all\u001b[0m\u001b[33m around\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import asyncio\n",
|
||||
"from llama_stack_client import LlamaStackClient\n",
|
||||
"from llama_stack_client.lib.inference.event_logger import EventLogger\n",
|
||||
"from llama_stack_client.types import UserMessage\n",
|
||||
"from termcolor import cprint\n",
|
||||
"\n",
|
||||
"async def run_main(stream: bool = True):\n",
|
||||
" client = LlamaStackClient(base_url=f'http://{HOST}:{PORT}')\n",
|
||||
"\n",
|
||||
" message = UserMessage(\n",
|
||||
" content='Write me a 3 sentence poem about llama', role='user'\n",
|
||||
" )\n",
|
||||
" cprint(f'User> {message.content}', 'green')\n",
|
||||
" message = {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": 'Write me a 3 sentence poem about llama'\n",
|
||||
" }\n",
|
||||
" cprint(f'User> {message[\"content\"]}', 'green')\n",
|
||||
"\n",
|
||||
" response = client.inference.chat_completion(\n",
|
||||
" messages=[message],\n",
|
||||
" model='Llama3.1-8B-Instruct',\n",
|
||||
" model='Llama3.2-11B-Vision-Instruct',\n",
|
||||
" stream=stream,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
|
|
@ -399,7 +345,7 @@
|
|||
"# In a Jupyter Notebook cell, use `await` to call the function\n",
|
||||
"await run_main()\n",
|
||||
"# To run it in a python file, use this line instead\n",
|
||||
"# asyncio.run(chat_loop())"
|
||||
"# asyncio.run(run_main())\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue