Skip to main content

MLflow AI Gateway

danger

MLflow AI Gateway 已被弃用。请改用MLflow Deployments for LLMs

MLflow AI Gateway服务是一个强大的工具,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的LLM相关请求,从而简化与这些服务的交互。

安装和设置

使用以下命令安装带有 MLflow AI Gateway 依赖项的 mlflow

pip install 'mlflow[gateway]'

将 OpenAI API 密钥设置为环境变量:

export OPENAI_API_KEY=...

创建一个配置文件:

routes:
- name: completions
route_type: llm/v1/completions
model:
provider: openai
name: text-davinci-003
config:
openai_api_key: $OPENAI_API_KEY
- name: embeddings
route_type: llm/v1/embeddings
model:
provider: openai
name: text-embedding-ada-002
config:
openai_api_key: $OPENAI_API_KEY

启动 Gateway 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。该模块以 langchain flavor 导出多变量 LangChain 模型,以 pyfunc flavor 导出单变量 LangChain 模型。

查看API 文档和示例

完成示例

import mlflow
from langchain.chains import LLMChain, PromptTemplate
from langchain_community.llms import MlflowAIGateway
gateway = MlflowAIGateway(
gateway_uri="http://127.0.0.1:5000",
route="completions",
params={
"temperature": 0.0,
"top_p": 0.1,
},
)
llm_chain = LLMChain(
llm=gateway,
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"}]))

嵌入示例

from langchain_community.embeddings import MlflowAIGatewayEmbeddings
embeddings = MlflowAIGatewayEmbeddings(
gateway_uri="http://127.0.0.1:5000",
route="embeddings",
)
print(embeddings.embed_query("hello"))
print(embeddings.embed_documents(["hello"]))

聊天示例

from langchain_community.chat_models import ChatMLflowAIGateway
from langchain_core.messages import HumanMessage, SystemMessage
chat = ChatMLflowAIGateway(
gateway_uri="http://127.0.0.1:5000",
route="chat",
params={
"temperature": 0.1
}
)
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))

Databricks MLflow AI Gateway

Databricks MLflow AI Gateway 处于私人预览阶段。

请联系 Databricks 代表以参加预览。

from langchain.chains import LLMChain
from langchain_core.prompts import PromptTemplate
from langchain_community.llms import MlflowAIGateway
gateway = MlflowAIGateway(
gateway_uri="databricks",
route="completions",
)
llm_chain = LLMChain(
llm=gateway,
prompt=PromptTemplate(
input_variables=["adjective"],
template="Tell me a {adjective} joke",
),
)
result = llm_chain.run(adjective="funny")
print(result)

Was this page helpful?


You can leave detailed feedback on GitHub.