Langchain初体验-GLM4使用

GLM4

智谱AI推出新一代基座模型 GLM-4

Langchain

LangChain是一个由大型语言模型( LLMs )驱动的应用开发框架。

依赖

pip install langchain langchain_community httpx httpx_sse PyJWT

Demo

import os
from langchain_community.chat_models import ChatZhipuAI
from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
from langchain_core.callbacks.manager import CallbackManager
from langchain_core.callbacks.streaming_stdout import StreamingStdOutCallbackHandler

os.environ["ZHIPUAI_API_KEY"] = ""

chat = ChatZhipuAI(
    model="glm-4",
    temperature=0.5,
    streaming=True,
    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),
)

message = [
    AIMessage(content="Hi"),
    SystemMessage(content="You are an automated operations engineer"),
    HumanMessage(content="give me a shell scripts for deploy java package"),
]


def main():
    response = chat.invoke(message)
    print(response.content)


if __name__ == "__main__":
    main()

响应结果

#!/bin/bash

# Define source and target directories
SOURCE_DIR="/path/to/source"
TARGET_DIR="/path/to/deployment"
JAR_FILE="MyApp.jar"
JAR_PATH="$SOURCE_DIR/$JAR_FILE"

# Define the Java application's PID file and log file
PID_FILE="/path/to/deployment/MyApp.pid"
LOG_FILE="/path/to/deployment/MyApp.log"

# Stop the currently running instance of the application, if any
if [[ -f $PID_FILE ]]; then
    PID=$(cat $PID_FILE)
    kill $PID
    rm $PID_FILE
    echo "Previous instance of the application stopped."
fi

# Copy the new JAR file to the deployment directory
cp "$JAR_PATH" "$TARGET_DIR"
if [[ $? -eq 0 ]]; then
    echo "JAR file successfully copied to deployment directory."
else
    echo "Error copying JAR file. Deployment failed."
    exit 1
fi

# Start the Java application
java -jar "$TARGET_DIR/$JAR_FILE" > "$LOG_FILE" 2>&1 &
echo $! > $PID_FILE

echo "Application started with PID $(cat $PID_FILE)."

Make sure to give execute permissions to the script:

chmod +x deploy.sh

To run the script:

./deploy.sh