财富正在向 AI 集中——开发者如何看清局势并找到位置

# rag_minimal.py — 最小 RAG 示例，可直接运行
# 依赖：pip install langchain langchain-openai langchain-community faiss-cpu tiktoken

import os
from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain_community.vectorstores import FAISS
from langchain.chains import RetrievalQA

# 1. 设置 API Key（也可写入环境变量）
os.environ["OPENAI_API_KEY"] = "sk-你的key"

# 2. 加载业务文档并切片
loader = TextLoader("your_doc.txt")  # 替换为你的文档路径
docs = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(docs)

# 3. 构建向量索引
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
vectorstore = FAISS.from_documents(chunks, embeddings)

# 4. 组装问答链
llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever(search_kwargs={"k": 3}),
)

# 5. 提问
answer = qa_chain.invoke("文档中提到的核心流程是什么？")
print(answer["result"])

# cost_monitor.py — 统计 OpenAI API 近期用量（需安装 openai）
# pip install openai

from openai import OpenAI
import os

client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

# 获取最近 7 天的用量概览（OpenAI Dashboard API）
# 注：OpenAI 官方 API 目前不直接提供用量端点，以下为替代方案
# 实际项目中建议在每次调用后自行记录 token 数

# ---- 自记录方案（推荐） ----
import json, datetime

LOG_FILE = "api_usage_log.json"

def log_usage(model: str, prompt_tokens: int, completion_tokens: int, cost_usd: float):
    entry = {
        "timestamp": datetime.datetime.now().isoformat(),
        "model": model,
        "prompt_tokens": prompt_tokens,
        "completion_tokens": completion_tokens,
        "cost_usd": cost_usd,
    }
    records = []
    if os.path.exists(LOG_FILE):
        with open(LOG_FILE) as f:
            records = json.load(f)
    records.append(entry)
    with open(LOG_FILE, "w") as f:
        json.dump(records, f, indent=2)

def weekly_summary():
    if not os.path.exists(LOG_FILE):
        print("暂无用量记录")
        return
    with open(LOG_FILE) as f:
        records = json.load(f)
    cutoff = datetime.datetime.now() - datetime.timedelta(days=7)
    recent = [r for r in records if datetime.datetime.fromisoformat(r["timestamp"]) > cutoff]
    total_cost = sum(r["cost_usd"] for r in recent)
    total_tokens = sum(r["prompt_tokens"] + r["completion_tokens"] for r in recent)
    print(f"近 7 天：{len(recent)} 次调用，{total_tokens} tokens，总费用 ${total_cost:.2f}")

# 使用示例：每次 API 调用后记录
# resp = client.chat.completions.create(model="gpt-4o-mini", messages=[...])
# log_usage("gpt-4o-mini", resp.usage.prompt_tokens, resp.usage.completion_tokens, 0.15)

weekly_summary()