嵌入
POST /v1/embeddings 通过 CometAPI 使用所选模型生成文本嵌入，用于语义搜索、聚类和检索工作流。
from openai import OpenAI
client = OpenAI(
base_url="https://api.cometapi.com/v1",
api_key="<COMETAPI_KEY>",
)
response = client.embeddings.create(
model="text-embedding-3-small",
input="The food was delicious and the waiter was friendly.",
)
print(response.data[0].embedding[:5]) # First 5 dimensions
print(f"Dimensions: {len(response.data[0].embedding)}"){
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
-0.0021,
-0.0491,
0.0209,
0.0314,
-0.0453
]
}
],
"model": "text-embedding-3-small",
"usage": {
"prompt_tokens": 2,
"total_tokens": 2
}
}概述
Embeddings API 会生成能够捕捉语义含义的文本向量表示。这些向量可用于语义搜索、聚类、分类、异常检测和检索增强生成（RAG）。 CometAPI 支持来自多个提供商的嵌入模型。传入一个或多个文本字符串后，会返回数值向量，你可以将其存储到向量数据库中，或直接用于相似度计算。可用模型
| 模型 | 维度 | 最大 Token 数 | 最适合 |
|---|---|---|---|
text-embedding-3-large | 3,072（可调） | 8,191 | 质量最高的嵌入 |
text-embedding-3-small | 1,536（可调） | 8,191 | 性价比高、速度快 |
text-embedding-ada-002 | 1,536（固定） | 8,191 | 兼容旧版 |
重要说明
text-embedding-3-* 模型支持 dimensions 参数，允许你在不显著损失准确率的情况下缩短嵌入向量。这最多可将存储成本降低 75%，同时保留大部分语义信息。input 参数传入字符串数组，在一次请求中为多个文本生成嵌入。与为每段文本分别发起请求相比，这样的效率会高得多。授权
Bearer token authentication. Use your CometAPI key.
请求体
The embedding model to use. See the Models page for current embedding model IDs.
"text-embedding-3-small"
The text to embed. Can be a single string, an array of strings, or an array of token arrays. Each input must not exceed the model's maximum token limit (8,191 tokens for text-embedding-3-* models).
The format of the returned embedding vectors. float returns an array of floating-point numbers. base64 returns a base64-encoded string representation, which can reduce response size for large batches.
float, base64 The number of dimensions for the output embedding vector. Only supported by text-embedding-3-* models. Reducing dimensions can lower storage costs while maintaining most of the embedding's utility.
x >= 1A unique identifier for your end-user, which can help monitor and detect abuse.
响应
A list of embedding vectors for the input text(s).
The object type, always list.
list "list"
An array of embedding objects, one per input text. When multiple inputs are provided, results are returned in the same order as the input.
Show child attributes
Show child attributes
The model used to generate the embeddings.
"text-embedding-3-small"
Token usage statistics for this request.
Show child attributes
Show child attributes
from openai import OpenAI
client = OpenAI(
base_url="https://api.cometapi.com/v1",
api_key="<COMETAPI_KEY>",
)
response = client.embeddings.create(
model="text-embedding-3-small",
input="The food was delicious and the waiter was friendly.",
)
print(response.data[0].embedding[:5]) # First 5 dimensions
print(f"Dimensions: {len(response.data[0].embedding)}"){
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
-0.0021,
-0.0491,
0.0209,
0.0314,
-0.0453
]
}
],
"model": "text-embedding-3-small",
"usage": {
"prompt_tokens": 2,
"total_tokens": 2
}
}