Together AI | liteLLM (original) (raw)

LiteLLM supports all models on Together AI.

API Keys​

import os 
os.environ["TOGETHERAI_API_KEY"] = "your-api-key"

Sample Usage​

from litellm import completion 

os.environ["TOGETHERAI_API_KEY"] = "your-api-key"

messages = [{"role": "user", "content": "Write me a poem about the blue sky"}]

completion(model="together_ai/togethercomputer/Llama-2-7B-32K-Instruct", messages=messages)

Together AI Models​

liteLLM supports non-streaming and streaming requests to all models on https://api.together.xyz/

Example TogetherAI Usage - Note: liteLLM supports all models deployed on TogetherAI

Llama LLMs - Chat​

Llama LLMs - Language / Instruct​

Falcon LLMs​

Alpaca LLMs​

Other Chat LLMs​

Code LLMs​

Language LLMs​

Prompt Templates​

Using a chat model on Together AI with it's own prompt format?

Using Llama2 Instruct models​

If you're using Together AI's Llama2 variants( model=togethercomputer/llama-2..-instruct), LiteLLM can automatically translate between the OpenAI prompt format and the TogetherAI Llama2 one ([INST]..[/INST]).

from litellm import completion 

# set env variable 
os.environ["TOGETHERAI_API_KEY"] = ""

messages = [{"role": "user", "content": "Write me a poem about the blue sky"}]

completion(model="together_ai/togethercomputer/Llama-2-7B-32K-Instruct", messages=messages)

Using another model​

You can create a custom prompt template on LiteLLM (and we welcome PRs to add them to the main repo 🤗)

Let's make one for OpenAssistant/llama2-70b-oasst-sft-v10!

The accepted template format is: Reference

"""
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""

Let's register our custom prompt template: Implementation Code

import litellm 

litellm.register_prompt_template(
        model="OpenAssistant/llama2-70b-oasst-sft-v10",
        roles={
            "system": {
                "pre_message": "[<|im_start|>system",
                "post_message": "\n"
            },
            "user": {
                "pre_message": "<|im_start|>user",
                "post_message": "\n"
            }, 
            "assistant": {
                "pre_message": "<|im_start|>assistant",
                "post_message": "\n"
            }
        }
    )

Let's use it!

from litellm import completion 

# set env variable 
os.environ["TOGETHERAI_API_KEY"] = ""

messages=[{"role":"user", "content": "Write me a poem about the blue sky"}]

completion(model="together_ai/OpenAssistant/llama2-70b-oasst-sft-v10", messages=messages)

Complete Code

import litellm 
from litellm import completion

# set env variable 
os.environ["TOGETHERAI_API_KEY"] = ""

litellm.register_prompt_template(
        model="OpenAssistant/llama2-70b-oasst-sft-v10",
        roles={
            "system": {
                "pre_message": "[<|im_start|>system",
                "post_message": "\n"
            },
            "user": {
                "pre_message": "<|im_start|>user",
                "post_message": "\n"
            }, 
            "assistant": {
                "pre_message": "<|im_start|>assistant",
                "post_message": "\n"
            }
        }
    )

messages=[{"role":"user", "content": "Write me a poem about the blue sky"}]

response = completion(model="together_ai/OpenAssistant/llama2-70b-oasst-sft-v10", messages=messages)

print(response)

Output

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": ".\n\nThe sky is a canvas of blue,\nWith clouds that drift and move,",
        "role": "assistant",
        "logprobs": null
      }
    }
  ],
  "created": 1693941410.482018,
  "model": "OpenAssistant/llama2-70b-oasst-sft-v10",
  "usage": {
    "prompt_tokens": 7,
    "completion_tokens": 16,
    "total_tokens": 23
  },
  "litellm_call_id": "f21315db-afd6-4c1e-b43a-0b5682de4b06"
}

Rerank​

Usage​

• LiteLLM SDK Usage
• LiteLLM Proxy Usage

from litellm import rerank
import os

os.environ["TOGETHERAI_API_KEY"] = "sk-.."

query = "What is the capital of the United States?"
documents = [
    "Carson City is the capital city of the American state of Nevada.",
    "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
    "Washington, D.C. is the capital of the United States.",
    "Capital punishment has existed in the United States since before it was a country.",
]

response = rerank(
    model="together_ai/rerank-english-v3.0",
    query=query,
    documents=documents,
    top_n=3,
)
print(response)