Passer au contenu principal

​
Aperçu

LangChain est un framework populaire pour la création d’applications LLM. LemonData fonctionne parfaitement avec l’intégration OpenAI de LangChain.

​
Installation

pip install langchain langchain-openai

​
Configuration de base

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4o",
    api_key="sk-your-lemondata-key",
    base_url="https://api.lemondata.cc/v1"
)

response = llm.invoke("Hello, how are you?")
print(response.content)

​
Utilisation de différents modèles

Accédez à n’importe quel modèle LemonData : 
# OpenAI GPT-4o
gpt4 = ChatOpenAI(
    model="gpt-4o",
    api_key="sk-your-key",
    base_url="https://api.lemondata.cc/v1"
)

# Anthropic Claude
claude = ChatOpenAI(
    model="claude-sonnet-4-5",
    api_key="sk-your-key",
    base_url="https://api.lemondata.cc/v1"
)

# Google Gemini
gemini = ChatOpenAI(
    model="gemini-2.5-flash",
    api_key="sk-your-key",
    base_url="https://api.lemondata.cc/v1"
)

# DeepSeek
deepseek = ChatOpenAI(
    model="deepseek-r1",
    api_key="sk-your-key",
    base_url="https://api.lemondata.cc/v1"
)

​
Chat avec historique des messages

from langchain_core.messages import HumanMessage, SystemMessage

messages = [
    SystemMessage(content="You are a helpful assistant."),
    HumanMessage(content="What is the capital of France?")
]

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

​
Streaming

for chunk in llm.stream("Write a poem about coding"):
    print(chunk.content, end="", flush=True)

​
Utilisation asynchrone

import asyncio

async def main():
    response = await llm.ainvoke("Hello!")
    print(response.content)

asyncio.run(main())

​
Chaînes

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant that translates {input_language} to {output_language}."),
    ("human", "{text}")
])

chain = prompt | llm | StrOutputParser()

result = chain.invoke({
    "input_language": "English",
    "output_language": "French",
    "text": "Hello, how are you?"
})
print(result)

​
RAG (Retrieval Augmented Generation)

from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough

# Embeddings
embeddings = OpenAIEmbeddings(
    model="text-embedding-3-small",
    api_key="sk-your-key",
    base_url="https://api.lemondata.cc/v1"
)

# Create vector store
texts = ["LemonData supports 300+ AI models", "API is OpenAI compatible"]
vectorstore = FAISS.from_texts(texts, embeddings)
retriever = vectorstore.as_retriever()

# RAG chain
template = """Answer based on context:
{context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)

rag_chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
    | llm
)

response = rag_chain.invoke("How many models does LemonData support?")
print(response.content)

​
Agents

Les API d’agent dans LangChain évoluent. Pour les nouveaux projets, envisagez d’utiliser LangGraph pour des architectures d’agent plus flexibles.
from langchain.agents import create_openai_tools_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.tools import tool

@tool
def search(query: str) -> str:
    """Search for information."""
    return f"Search results for: {query}"

tools = [search]

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant with access to tools."),
    ("human", "{input}"),
    ("placeholder", "{agent_scratchpad}")
])

agent = create_openai_tools_agent(llm, tools, prompt)
executor = AgentExecutor(agent=agent, tools=tools)

result = executor.invoke({"input": "Search for LemonData pricing"})
print(result["output"])

​
Variables d’environnement

Pour un code plus propre, utilisez des variables d’environnement : 
export OPENAI_API_KEY="sk-your-lemondata-key"
export OPENAI_API_BASE="https://api.lemondata.cc/v1"

from langchain_openai import ChatOpenAI

# Utilisera automatiquement les variables d'environnement
llm = ChatOpenAI(model="gpt-4o")

​
Callbacks et traçage

from langchain_core.callbacks import StdOutCallbackHandler

llm = ChatOpenAI(
    model="gpt-4o",
    api_key="sk-your-key",
    base_url="https://api.lemondata.cc/v1",
    callbacks=[StdOutCallbackHandler()]
)

​
Bonnes pratiques

Utilisez des modèles moins chers (GPT-4o-mini) pour les tâches simples dans les chaînes.
LangChain dispose d’une logique de retry intégrée pour les erreurs transitoires.
Utilisez des callbacks pour suivre la consommation de tokens.