LangChain

pip install langchain langchain-openai

import os
from langchain_openai import ChatOpenAI

os.environ["OPENAI_API_KEY"] = "your-UToken-api-key"
os.environ["OPENAI_BASE_URL"] = "https://utoken.yoostudio.ai/v1"

llm = ChatOpenAI(
    model="gpt-3.5-turbo",
    temperature=0.7
)

from langchain.schema import HumanMessage, SystemMessage

messages = [
    SystemMessage(content="You are a helpful assistant"),
    HumanMessage(content="Describe the main features of Python")
]

response = llm.invoke(messages)
print(response.content)

from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationChain

memory = ConversationBufferMemory()
conversation = ConversationChain(llm=llm, memory=memory, verbose=True)

conversation.predict(input="I want to learn machine learning")
conversation.predict(input="Recommend some beginner resources")

from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA

embeddings = OpenAIEmbeddings(
    api_key="your-UToken-api-key",
    base_url="https://utoken.yoostudio.ai/v1"
)

loader = TextLoader("document.txt")
documents = loader.load()

text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)

vectorstore = FAISS.from_documents(texts, embeddings)

qa = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever()
)

result = qa.run("What are the key concepts in the document?")

gpt4 = ChatOpenAI(
    model="gpt-4",
    api_key="your-UToken-api-key",
    base_url="https://utoken.yoostudio.ai/v1"
)

claude = ChatOpenAI(
    model="claude-opus-4-5-20251101",
    api_key="your-UToken-api-key",
    base_url="https://utoken.yoostudio.ai/v1"
)

from langchain.agents import create_openai_functions_agent, AgentExecutor
from langchain.tools import Tool
from langchain import hub

def get_weather(location: str) -> str:
    return f"The weather in {location} is sunny, 25°C"

weather_tool = Tool(
    name="Weather",
    func=get_weather,
    description="Retrieve weather information for a specified location"
)

prompt = hub.pull("hwchase17/openai-functions-agent")
agent = create_openai_functions_agent(llm, [weather_tool], prompt)
agent_executor = AgentExecutor(agent=agent, tools=[weather_tool])

result = agent_executor.invoke({"input": "What is the weather like in Beijing today?"})

prompts = ["Explain artificial intelligence", "What is machine learning", "Applications of deep learning"]

responses = llm.batch([HumanMessage(content=p) for p in prompts])

for response in responses:
    print(response.content)

from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler

streaming_llm = ChatOpenAI(
    model="gpt-3.5-turbo",
    streaming=True,
    callbacks=[StreamingStdOutCallbackHandler()]
)

streaming_llm.invoke("Write a poem about spring")

from langchain.callbacks import get_openai_callback

with get_openai_callback() as cb:
    response = llm.invoke("Hello, introduce LangChain")
    print(f"Token count: {cb.total_tokens}")
    print(f"Cost: ${cb.total_cost:.6f}")

class CostOptimizedLLM:
    def __init__(self):
        self.cheap_model = ChatOpenAI(model="gpt-3.5-turbo")
        self.premium_model = ChatOpenAI(model="gpt-4")
    
    def smart_invoke(self, message, complexity="low"):
        model = self.premium_model if complexity == "high" else self.cheap_model
        return model.invoke(message)

from langchain.cache import InMemoryCache
from langchain.globals import set_llm_cache

set_llm_cache(InMemoryCache())

response1 = llm.invoke("What is artificial intelligence?")
response2 = llm.invoke("What is artificial intelligence?")  # served from cache

import asyncio
from langchain_openai import AsyncChatOpenAI

async def async_chat():
    async_llm = AsyncChatOpenAI(
        model="gpt-3.5-turbo",
        api_key="your-UToken-api-key",
        base_url="https://utoken.yoostudio.ai/v1"
    )
    response = await async_llm.ainvoke("Asynchronously generated content")
    return response.content

result = asyncio.run(async_chat())

import os
from langchain_openai import ChatOpenAI

class ProductionLLM:
    def __init__(self):
        self.llm = ChatOpenAI(
            model=os.getenv("LLM_MODEL", "gpt-3.5-turbo"),
            temperature=float(os.getenv("LLM_TEMPERATURE", "0.7")),
            max_tokens=int(os.getenv("LLM_MAX_TOKENS", "1000")),
            request_timeout=int(os.getenv("LLM_REQUEST_TIMEOUT", "60"))
        )
    
    def chat(self, message):
        try:
            return self.llm.invoke(message)
        except Exception as e:
            return "Sorry, the service is temporarily unavailable"

import time
from functools import wraps

def retry_llm_call(max_retries=3, delay=1):
    def decorator(func):
        @wraps(func)
        def wrapper(*args, **kwargs):
            for attempt in range(max_retries):
                try:
                    return func(*args, **kwargs)
                except Exception as e:
                    if attempt == max_retries - 1:
                        raise e
                    time.sleep(delay * (2 ** attempt))
            return None
        return wrapper
    return decorator

@retry_llm_call(max_retries=3)
def robust_llm_call(llm, message):
    return llm.invoke(message)