嵌入向量(Embedding)
将文本转换为高维向量,用于语义搜索、相似度匹配、RAG 等场景。
Python 示例
Python
from openai import OpenAI
client = OpenAI(
api_key="am-your-api-key",
base_url="https://allmodel.top/v1"
)
# 单条文本
response = client.embeddings.create(
model="text-embedding-3-small",
input="The food was delicious and the waiter was friendly."
)
vector = response.data[0].embedding
print(f"向量维度: {len(vector)}")
print(f"前5个值: {vector[:5]}")
# 批量(节省 API 调用)
responses = client.embeddings.create(
model="text-embedding-3-small",
input=["第一段文本", "第二段文本", "第三段文本"]
)
for r in responses.data:
print(f"index={r.index}, embedding长度={len(r.embedding)}")
支持的模型
| 模型 | 维度 | 价格 |
text-embedding-3-small | 1536 | $0.02/M tokens |
text-embedding-3-large | 3072 | $0.13/M tokens |
allmodel.top