Skip to main content

Fireworks AI

https://fireworks.ai/

info

我们支持所有Fireworks AI模型，只需在发送完成请求时设置 fireworks_ai/ 作为前缀

API密钥​

# 环境变量
os.environ['FIREWORKS_AI_API_KEY']

示例用法​

from litellm import completion
import os

os.environ['FIREWORKS_AI_API_KEY'] = ""
response = completion(
    model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
)
print(response)

示例用法 - 流式传输​

from litellm import completion
import os

os.environ['FIREWORKS_AI_API_KEY'] = ""
response = completion(
    model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
    stream=True
)

for chunk in response:
    print(chunk)

与LiteLLM代理一起使用​

1. 在config.yaml上设置Fireworks AI模型​

model_list:
  - model_name: fireworks-llama-v3-70b-instruct
    litellm_params:
      model: fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct
      api_key: "os.environ/FIREWORKS_AI_API_KEY"

2. 启动代理​

litellm --config config.yaml

3. 测试它​

curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
      "model": "fireworks-llama-v3-70b-instruct",
      "messages": [
        {
          "role": "user",
          "content": "what llm are you"
        }
      ]
    }
'
import openai
client = openai.OpenAI(
    api_key="anything",
    base_url="http://0.0.0.0:4000"
)

# 请求发送到在litellm代理上设置的模型，`litellm --model`
response = client.chat.completions.create(model="fireworks-llama-v3-70b-instruct", messages = [
    {
        "role": "user",
        "content": "this is a test request, write a short poem"
    }
])

print(response)

from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
    ChatPromptTemplate,
    HumanMessagePromptTemplate,
    SystemMessagePromptTemplate,
)
from langchain.schema import HumanMessage, SystemMessage

chat = ChatOpenAI(
    openai_api_base="http://0.0.0.0:4000", # 将openai_api_base设置为LiteLLM代理
    model = "fireworks-llama-v3-70b-instruct",
    temperature=0.1
)

messages = [
    SystemMessage(
        content="You are a helpful assistant that im using to make a test request to."
    ),
    HumanMessage(
        content="test from litellm. tell me why it's amazing in 1 sentence"
    ),
]
response = chat(messages)

print(response)

支持的模型 - 所有Fireworks AI模型都支持！​

info

我们支持所有Fireworks AI模型，只需在发送完成请求时设置 fireworks_ai/ 作为前缀

模型名称函数调用
llama-v3p2-1b-instructcompletion(model="fireworks_ai/llama-v3p2-1b-instruct", messages)
llama-v3p2-3b-instructcompletion(model="fireworks_ai/llama-v3p2-3b-instruct", messages)
llama-v3p2-11b-vision-instructcompletion(model="fireworks_ai/llama-v3p2-11b-vision-instruct", messages)
llama-v3p2-90b-vision-instructcompletion(model="fireworks_ai/llama-v3p2-90b-vision-instruct", messages)
mixtral-8x7b-instructcompletion(model="fireworks_ai/mixtral-8x7b-instruct", messages)
firefunction-v1completion(model="fireworks_ai/firefunction-v1", messages)
llama-v2-70b-chatcompletion(model="fireworks_ai/llama-v2-70b-chat", messages)

支持的嵌入模型​

info

我们支持所有Fireworks AI模型，只需在发送嵌入请求时设置 fireworks_ai/ 作为前缀

模型名称函数调用
fireworks_ai/nomic-ai/nomic-embed-text-v1.5response = litellm.embedding(model="fireworks_ai/nomic-ai/nomic-embed-text-v1.5", input=input_text)
fireworks_ai/nomic-ai/nomic-embed-text-v1response = litellm.embedding(model="fireworks_ai/nomic-ai/nomic-embed-text-v1", input=input_text)
fireworks_ai/WhereIsAI/UAE-Large-V1response = litellm.embedding(model="fireworks_ai/WhereIsAI/UAE-Large-V1", input=input_text)
fireworks_ai/thenlper/gte-largeresponse = litellm.embedding(model="fireworks_ai/thenlper/gte-large", input=input_text)
fireworks_ai/thenlper/gte-baseresponse = litellm.embedding(model="fireworks_ai/thenlper/gte-base", input=input_text)
优云智算