This document describes different aspects of text generation, including types of generation, model selection, creating prompts, and managing multi-turn conversations.

​

Types of generations

You can use various methods to generate text, including non-streaming, streaming, and asynchronous completions.

​

Simple generation (non-streaming)

Use the following code to perform text generation with the OpenAI Python client in a non-streaming manner.

from openai import OpenAI
client = OpenAI(
    base_url="https://api.sambanova.ai/v1", 
    api_key="<your-api-key>"
)
completion = client.chat.completions.create(
    model="Meta-Llama-3.1-8B-Instruct",
    messages = [  
        {"role": "system", "content": "Answer the question in a couple sentences."},
        {"role": "user", "content": "Share a happy story with me"}
    ]
)
print(completion.choices[0].message.content)

​

Asynchronous generation (non-streaming)

For asynchronous completions, use the AsyncOpenAI Python client, as shown below.

from openai import AsyncOpenAI
import asyncio
async def main():
    client = AsyncOpenAI(
        base_url="https://api.sambanova.ai/v1", 
        api_key="<your-api-key>"
    )
    completion = await client.chat.completions.create(
        model="Meta-Llama-3.1-8B-Instruct",
        messages = [
            {"role": "system", "content": "Answer the question in a couple sentences."},
            {"role": "user", "content": "Share a happy story with me"}
        ]
    )
    print(completion.choices[0].message.content)
asyncio.run(main())

​

Streaming response

For real-time streaming completions, use the following approach with the OpenAI Python client.

from openai import OpenAI
client = OpenAI(
    base_url="https://api.sambanova.ai/v1", 
    api_key="<your-api-key>"
)
completion = client.chat.completions.create(
    model="Meta-Llama-3.1-8B-Instruct",
    messages = [
        {"role": "system", "content": "Answer the question in a couple sentences."},
        {"role": "user", "content": "Share a happy story with me"}
    ],
    stream = True
)
for chunk in completion:
  print(chunk.choices[0].delta.content, end="")

​

Asynchronous streaming

You can leverage the AsyncOpenAI Python client to enable asynchronous streaming.

from openai import AsyncOpenAI
import asyncio
async def main():
    client = AsyncOpenAI(
        base_url="https://api.sambanova.ai/v1", 
        api_key="<your-api-key>"
    )
    completion = await client.chat.completions.create(
        model="Meta-Llama-3.1-8B-Instruct",
        messages = [
            {"role": "system", "content": "Answer the question in a couple sentences."},
            {"role": "user", "content": "Share a happy story with me"}
        ],
        stream = True
    )
    async for chunk in completion:
        print(chunk.choices[0].delta.content, end="")
asyncio.run(main())

​

Model selection

Models differ in their architecture, impacting their speed and response quality. Selecting a model depends on the factors shown below.

Experiment with various models to find the one that best fits your specific use case.

​

Creating effective prompts

Prompt engineering is the practice of designing and refining prompts to optimize responses from large language models (LLMs). This process is iterative and requires experimentation to achieve the best possible outcomes.

​

Building a prompt

A basic prompt can be as simple as a few words to elicit a response from the LLM. However, for more complex use cases, additional elements may be needed, as shown below.

​

Advanced prompting techniques

To improve response quality and reasoning, more advanced techniques can be used.

For more details about prompt engineering, see A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

​

Messages and roles

In chat-based interactions, messages are represented as dictionaries with specific roles and content.

​

Common roles

Roles are typically categorized as system, user, or assistant.

​

Multi-turn conversation

To maintain context across multiple exchanges, messages in a conversational AI system are typically stored as a list of dictionaries. Each dictionary contains keys that specify the sender’s role and the message content. This structure helps the system track context across multiple turns in a conversation.

Below is an example of how a multi-turn conversation is structured using the Meta-Llama-3.1-8B-Instruct model:

completion = client.chat.completions.create(
    model="Meta-Llama-3.1-8B-Instruct",
    messages = [
        {"role": "user", "content": "Hi! My name is Peter and I am 31 years old. What is 1+1?"},
        {"role": "assistant", "content": "Nice to meet you, Peter. 1 + 1 is equal to 2"},
        {"role": "user", "content": "What is my age?"}
    ],
    stream = True
)
for chunk in completion:
  print(chunk.choices[0].delta.content, end="")

After running the program, you should see an output similar to the following.

You told me earlier, Peter. You're 31 years old.

By structuring conversations this way, the model can maintain context, recall prior user inputs, and provide more coherent responses.

​

Considerations for long conversations

When engaging in long conversations with LLMs, certain factors such as token limits and memory constraints must be considered to ensure accuracy and coherence.

• Token limits - LLMs have a fixed context window, limiting the number of tokens they can process in a single request. If the input exceeds this limit, the system might truncate it, leading to incomplete or incoherent responses.

• Memory constraints - The model does not retain context beyond its input window. To preserve context, past messages should be re-included in prompts.

By structuring prompts effectively and managing conversation history, you can optimize interactions with LLMs for better accuracy and coherence.