설정
pip install langchain langchain-openai openai
Chat 모델
Venice의 base URL과 함께ChatOpenAI를 사용하세요:
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
model="venice-uncensored-1-2",
api_key="your-venice-api-key",
base_url="https://api.venice.ai/api/v1",
temperature=0.7,
)
response = llm.invoke("Explain privacy-preserving AI in 2 sentences.")
print(response.content)
스트리밍
for chunk in llm.stream("Write a haiku about decentralization."):
print(chunk.content, end="", flush=True)
임베딩(Embeddings)
Venice는 텍스트만 임베딩합니다. LangChain의OpenAIEmbeddings는 기본적으로 check_embedding_ctx_length=True로 설정되어 있어 tiktoken으로 토큰화하고 정수 토큰 배열을 전송할 수 있습니다. Venice는 이를 HTTP 400으로 거부하므로 반드시 check_embedding_ctx_length=False로 설정하세요.
from langchain_openai import OpenAIEmbeddings
embeddings = OpenAIEmbeddings(
model="text-embedding-bge-m3",
api_key="your-venice-api-key",
base_url="https://api.venice.ai/api/v1",
check_embedding_ctx_length=False, # Required: send text, not token IDs
)
vectors = embeddings.embed_documents([
"Venice AI provides private inference.",
"No data is retained after processing.",
])
print(f"Embedding dimension: {len(vectors[0])}")
체인(Chains)
Prompt 템플릿이 있는 단순 체인
from langchain_core.prompts import ChatPromptTemplate
prompt = ChatPromptTemplate.from_messages([
("system", "You are a {role}. Answer concisely."),
("user", "{question}"),
])
chain = prompt | llm
response = chain.invoke({"role": "privacy expert", "question": "Why does zero data retention matter?"})
print(response.content)
순차 체인
from langchain_core.output_parsers import StrOutputParser
# 체인 1: 주제 요약 생성
summarizer = ChatPromptTemplate.from_messages([
("user", "Summarize this topic in 3 bullet points: {topic}")
]) | llm | StrOutputParser()
# 체인 2: 요약으로부터 질문 생성
questioner = ChatPromptTemplate.from_messages([
("user", "Based on this summary, generate 3 thought-provoking questions:\n{summary}")
]) | llm | StrOutputParser()
# 구성
summary = summarizer.invoke({"topic": "decentralized AI inference"})
questions = questioner.invoke({"summary": summary})
print(questions)
RAG 파이프라인
Venice로 검색 기반 생성(RAG) 파이프라인을 만드세요:from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser
# Venice 모델 초기화
llm = ChatOpenAI(
model="zai-org-glm-5-1",
api_key="your-venice-api-key",
base_url="https://api.venice.ai/api/v1",
)
embeddings = OpenAIEmbeddings(
model="text-embedding-bge-m3",
api_key="your-venice-api-key",
base_url="https://api.venice.ai/api/v1",
check_embedding_ctx_length=False, # Required: send text, not token IDs
)
# 문서 로딩 및 분할
documents = [
"Venice AI provides private, uncensored AI inference with zero data retention.",
"The Venice API is OpenAI-compatible, supporting chat completions, images, audio, video, and embeddings.",
"Venice supports function calling, structured outputs, web search, and reasoning models.",
"Privacy levels include Private (zero retention) and Anonymized (third-party processed).",
]
# 벡터 스토어 생성
vectorstore = FAISS.from_texts(documents, embeddings)
retriever = vectorstore.as_retriever(search_kwargs={"k": 2})
# RAG prompt
rag_prompt = ChatPromptTemplate.from_messages([
("system", "Answer the question based only on the following context:\n\n{context}"),
("user", "{question}"),
])
# RAG 체인
def format_docs(docs):
return "\n\n".join(doc.page_content for doc in docs)
rag_chain = (
{"context": retriever | format_docs, "question": RunnablePassthrough()}
| rag_prompt
| llm
| StrOutputParser()
)
answer = rag_chain.invoke("What privacy levels does Venice offer?")
print(answer)
에이전트를 통한 함수 호출
from langchain_core.tools import tool
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate
# 함수 호출이 가능한 모델 사용
llm = ChatOpenAI(
model="zai-org-glm-5-1",
api_key="your-venice-api-key",
base_url="https://api.venice.ai/api/v1",
)
@tool
def get_venice_model_price(model_id: str) -> str:
"""Get the pricing for a Venice AI model."""
prices = {
"venice-uncensored-1-2": "Input: $0.20/1M, Output: $0.90/1M",
"zai-org-glm-5-1": "Input: $1.75/1M, Output: $5.50/1M",
"qwen3-5-9b": "Input: $0.10/1M, Output: $0.15/1M",
}
return prices.get(model_id, f"Model {model_id} not found in price list.")
prompt = ChatPromptTemplate.from_messages([
("system", "You help users find the right Venice AI model. Use tools when needed."),
("placeholder", "{chat_history}"),
("user", "{input}"),
("placeholder", "{agent_scratchpad}"),
])
agent = create_tool_calling_agent(llm, [get_venice_model_price], prompt)
executor = AgentExecutor(agent=agent, tools=[get_venice_model_price], verbose=True)
result = executor.invoke({"input": "What's the cheapest Venice text model?", "chat_history": []})
print(result["output"])
구조화된 출력
from pydantic import BaseModel, Field
class MovieReview(BaseModel):
title: str = Field(description="Movie title")
rating: float = Field(description="Rating out of 10")
summary: str = Field(description="One-sentence summary")
structured_llm = llm.with_structured_output(MovieReview)
review = structured_llm.invoke("Review the movie Inception")
print(f"{review.title}: {review.rating}/10 — {review.summary}")
웹 검색 통합
venice_parameters를 통해 Venice의 내장 웹 검색을 사용하세요:
from langchain_openai import ChatOpenAI
llm_with_search = ChatOpenAI(
model="venice-uncensored",
api_key="your-venice-api-key",
base_url="https://api.venice.ai/api/v1",
extra_body={
"venice_parameters": {
"enable_web_search": "auto"
}
}
)
response = llm_with_search.invoke("What are the latest developments in AI this week?")
print(response.content)
response = llm.invoke(
"What are the latest developments in AI this week?",
extra_body={"venice_parameters": {"enable_web_search": "auto"}}
)
LangChain에 권장되는 모델
| Use Case | Model | Why |
|---|---|---|
| 일반 체인 | venice-uncensored | 빠르고, 저렴하고, 비검열 |
| 복잡한 추론 | zai-org-glm-5-1 | 최고의 프라이빗 플래그십 모델 |
| 함수 호출 | zai-org-glm-5-1 | 신뢰성 있는 도구 사용 |
| 비전 + 텍스트 | qwen3-vl-235b-a22b | 고급 비전 이해 |
| 코드 생성 | qwen3-coder-480b-a35b-instruct | 코드에 최적화 |
| 임베딩(RAG) | text-embedding-bge-m3 | 프라이빗 임베딩 |
| 예산 / 대량 | qwen3-5-9b | 100만 input 토큰당 $0.10 |
모든 모델 보기
가격과 기능과 함께 모든 Venice 모델을 둘러보세요