Skip to main content
Open on GitHub

MLflow AI Gateway for LLMs

MLflow AI Gateway for LLMs 是一个强大的工具,旨在简化组织内各种大型语言模型(LLM)提供商(如 OpenAI 和 Anthropic)的使用和管理。它提供了一个高级接口,通过提供统一的端点来处理特定于 LLM 的请求,从而简化了与这些服务的交互。

安装和设置​

使用 MLflow GenAI 依赖项安装 mlflow:

pip install 'mlflow[genai]'

将 OpenAI API 密钥设置为环境变量:

export OPENAI_API_KEY=...

创建一个配置文件:

endpoints:
- name: completions
endpoint_type: llm/v1/completions
model:
provider: openai
name: text-davinci-003
config:
openai_api_key: $OPENAI_API_KEY

- name: embeddings
endpoint_type: llm/v1/embeddings
model:
provider: openai
name: text-embedding-ada-002
config:
openai_api_key: $OPENAI_API_KEY

启动网关服务器:

mlflow gateway start --config-path /path/to/config.yaml

MLflow 提供的示例​

mlflow.langchain 模块提供了用于记录和加载 LangChain 模型的 API。此模块以 langchain flavor 的形式导出多元 LangChain 模型,以 pyfunc flavor 的形式导出单变量 LangChain 模型。

有关更多信息,请参阅API 文档和示例。

Completions 示例​

import mlflow
from langchain.chains import LLMChain, PromptTemplate
from langchain_community.llms import Mlflow

llm = Mlflow(
target_uri="http://127.0.0.1:5000",
endpoint="completions",
)

llm_chain = LLMChain(
llm=Mlflow,
prompt=PromptTemplate(
input_variables=["adjective"],
template="Tell me a {adjective} joke",
),
)
result = llm_chain.run(adjective="funny")
print(result)

with mlflow.start_run():
model_info = mlflow.langchain.log_model(chain, "model")

model = mlflow.pyfunc.load_model(model_info.model_uri)
print(model.predict([{"adjective": "funny"}]))
API Reference:LLMChain | Mlflow

Embeddings 示例​

from langchain_community.embeddings import MlflowEmbeddings

embeddings = MlflowEmbeddings(
target_uri="http://127.0.0.1:5000",
endpoint="embeddings",
)

print(embeddings.embed_query("hello"))
print(embeddings.embed_documents(["hello"]))
API Reference:MlflowEmbeddings

Chat 示例​

from langchain_community.chat_models import ChatMlflow
from langchain_core.messages import HumanMessage, SystemMessage

chat = ChatMlflow(
target_uri="http://127.0.0.1:5000",
endpoint="chat",
)

messages = [
SystemMessage(
content="You are a helpful assistant that translates English to French."
),
HumanMessage(
content="Translate this sentence from English to French: I love programming."
),
]
print(chat(messages))