Text-Embedding-3-Small API 教程 - OpenAI 向量嵌入模型指南

from openai import OpenAI

client = OpenAI(
    api_key="your-crazyrouter-api-key",
    base_url="https://crazyrouter.com/v1"
)

# 为单条文本生成向量
response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Machine learning is transforming industries worldwide."
)

embedding = response.data[0].embedding
print(f"Dimensions: {len(embedding)}")  # Output: 1536
print(f"First 5 values: {embedding[:5]}")

import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: 'your-crazyrouter-api-key',
    baseURL: 'https://crazyrouter.com/v1'
});

async function getEmbedding(text) {
    const response = await client.embeddings.create({
        model: 'text-embedding-3-small',
        input: text
    });

    return response.data[0].embedding;
}

// Usage
const embedding = await getEmbedding('Machine learning is amazing');
console.log(`Dimensions: ${embedding.length}`);  // Output: 1536

curl -X POST https://crazyrouter.com/v1/embeddings \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "Hello world"
  }'

{
  "object": "list",
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 2,
    "total_tokens": 2
  },
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [-0.0020785425, -0.049085874, 0.02094679, ...]
    }
  ]
}

from openai import OpenAI

client = OpenAI(
    api_key="your-crazyrouter-api-key",
    base_url="https://crazyrouter.com/v1"
)

# 批量生成向量 - 一次处理多条文本
texts = [
    "Python is a programming language",
    "JavaScript runs in browsers",
    "Machine learning uses neural networks"
]

response = client.embeddings.create(
    model="text-embedding-3-small",
    input=texts
)

# 访问每一条向量
for i, data in enumerate(response.data):
    print(f"Text {i}: {len(data.embedding)} dimensions")

# Output:
# Text 0: 1536 dimensions
# Text 1: 1536 dimensions
# Text 2: 1536 dimensions

# 使用 512 维向量替代默认的 1536 维
response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Your text here",
    dimensions=512  # Options: 256, 512, 1024, 1536
)

embedding = response.data[0].embedding
print(f"Dimensions: {len(embedding)}")  # Output: 512

import numpy as np
from openai import OpenAI

client = OpenAI(
    api_key="your-crazyrouter-api-key",
    base_url="https://crazyrouter.com/v1"
)

def get_embedding(text):
    """Get embedding for a single text"""
    response = client.embeddings.create(
        model="text-embedding-3-small",
        input=text
    )
    return response.data[0].embedding

def cosine_similarity(a, b):
    """Calculate cosine similarity between two vectors"""
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# 文档库
documents = [
    "Python is great for data science and machine learning",
    "JavaScript is essential for web development",
    "Docker containers simplify deployment",
    "Kubernetes orchestrates container workloads",
    "PostgreSQL is a powerful relational database"
]

# 为所有文档预先计算向量
doc_embeddings = [get_embedding(doc) for doc in documents]

# 搜索函数
def search(query, top_k=3):
    query_embedding = get_embedding(query)

    # 计算相似度
    similarities = [
        cosine_similarity(query_embedding, doc_emb)
        for doc_emb in doc_embeddings
    ]

    # 获取 Top 结果
    results = sorted(
        zip(documents, similarities),
        key=lambda x: x[1],
        reverse=True
    )[:top_k]

    return results

# 示例搜索
results = search("How to deploy applications?")
for doc, score in results:
    print(f"Score: {score:.4f} - {doc}")

# Output:
# Score: 0.8234 - Docker containers simplify deployment
# Score: 0.7891 - Kubernetes orchestrates container workloads
# Score: 0.6543 - PostgreSQL is a powerful relational database

import pinecone
from openai import OpenAI

# 初始化客户端
client = OpenAI(
    api_key="your-crazyrouter-api-key",
    base_url="https://crazyrouter.com/v1"
)

pinecone.init(api_key="your-pinecone-key")
index = pinecone.Index("your-index")

def embed_and_upsert(texts, ids):
    """Embed texts and store in Pinecone"""
    response = client.embeddings.create(
        model="text-embedding-3-small",
        input=texts
    )

    vectors = [
        (id, data.embedding)
        for id, data in zip(ids, response.data)
    ]

    index.upsert(vectors=vectors)

def search_pinecone(query, top_k=5):
    """Search Pinecone with query embedding"""
    response = client.embeddings.create(
        model="text-embedding-3-small",
        input=query
    )

    results = index.query(
        vector=response.data[0].embedding,
        top_k=top_k
    )

    return results

import chromadb
from openai import OpenAI

client = OpenAI(
    api_key="your-crazyrouter-api-key",
    base_url="https://crazyrouter.com/v1"
)

# 初始化 ChromaDB
chroma_client = chromadb.Client()
collection = chroma_client.create_collection("documents")

def get_embeddings(texts):
    """Get embeddings for multiple texts"""
    response = client.embeddings.create(
        model="text-embedding-3-small",
        input=texts
    )
    return [data.embedding for data in response.data]

# 添加文档
documents = ["doc1 content", "doc2 content", "doc3 content"]
embeddings = get_embeddings(documents)

collection.add(
    embeddings=embeddings,
    documents=documents,
    ids=["doc1", "doc2", "doc3"]
)

# 查询
query_embedding = get_embeddings(["search query"])[0]
results = collection.query(
    query_embeddings=[query_embedding],
    n_results=3
)

# 推荐写法 - 一次 API 调用处理多条文本
response = client.embeddings.create(
    model="text-embedding-3-small",
    input=["text1", "text2", "text3"]  # 一次最多 2048 条
)

# 不推荐 - 多次 API 调用
for text in texts:
    response = client.embeddings.create(
        model="text-embedding-3-small",
        input=text
    )

import hashlib
import json

embedding_cache = {}

def get_embedding_cached(text):
    # 为文本创建缓存键
    cache_key = hashlib.md5(text.encode()).hexdigest()

    if cache_key in embedding_cache:
        return embedding_cache[cache_key]

    response = client.embeddings.create(
        model="text-embedding-3-small",
        input=text
    )

    embedding = response.data[0].embedding
    embedding_cache[cache_key] = embedding

    return embedding