Gemini Embedding 2 Preview 上线：首个原生多模态嵌入模型

from openai import OpenAI

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

response = client.embeddings.create(
    model="gemini-embedding-2-preview",
    input="谷歌最新的多模态嵌入模型有哪些特点？",
    dimensions=768  # 可选：128～3072
)

embedding = response.data[0].embedding
print(f"维度: {len(embedding)}")

texts = [
    "人工智能的最新发展趋势",
    "机器学习在医疗领域的应用",
    "大语言模型的工作原理"
]

response = client.embeddings.create(
    model="gemini-embedding-2-preview",
    input=texts,
    dimensions=1536
)

for i, data in enumerate(response.data):
    print(f"文本 {i}: 维度 {len(data.embedding)}")

import numpy as np

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# 构建文档库嵌入
docs = ["量子计算原理", "深度学习入门", "区块链技术概述"]
doc_resp = client.embeddings.create(
    model="gemini-embedding-2-preview",
    input=docs,
    dimensions=768
)
doc_embeddings = [d.embedding for d in doc_resp.data]

# 查询
query_resp = client.embeddings.create(
    model="gemini-embedding-2-preview",
    input="神经网络是怎么工作的？",
    dimensions=768
)
query_embedding = query_resp.data[0].embedding

# 计算相似度
for i, doc_emb in enumerate(doc_embeddings):
    sim = cosine_similarity(query_embedding, doc_emb)
    print(f"{docs[i]}: {sim:.4f}")