# pip install chromadb openai python-dotenv
import chromadb
from openai import OpenAI
from dotenv import load_dotenv
import os

load_dotenv()
ai = OpenAI(api_key=os.getenv("DEEPSEEK_API_KEY"),
            base_url="https://api.deepseek.com")

def embed(text: str) -> list[float]:
    res = ai.embeddings.create(model="text-embedding-ada-002", input=text)
    return res.data[0].embedding

# 创建本地持久化 Chroma 数据库
db = chromadb.PersistentClient(path="./chroma_db")
col = db.get_or_create_collection("running_knowledge")

# ① 存入文档
docs = [
    "E 配速跑是有氧基础训练，强度低、时间长",
    "间歇跑提升最大摄氧量，强度高、休息短",
    "马拉松补给策略：每 5km 补水一次",
    "跑前热身 10 分钟可降低受伤风险",
    "心率区间二对应有氧耐力训练",
]
col.add(
    documents=docs,
    embeddings=[embed(d) for d in docs],
    ids=[f"doc_{i}" for i in range(len(docs))]
)
print(f"已存入 {col.count()} 个文档")

# ② 检索
results = col.query(
    query_embeddings=[embed("心肺训练怎么做")],
    n_results=2
)
for doc in results["documents"][0]:
    print(doc)