46 lines
1.6 KiB
Python
46 lines
1.6 KiB
Python
import requests
|
|
|
|
def chunks_embedding(texts: list[str], api_key: str) -> list[list[float]]:
|
|
if not texts:
|
|
return []
|
|
|
|
MODEL_NAME = "text-embedding-v4"
|
|
url = "https://dashscope.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding"
|
|
headers = {
|
|
"Authorization": f"Bearer {api_key}",
|
|
"Content-Type": "application/json"
|
|
}
|
|
payload = {
|
|
"model": MODEL_NAME,
|
|
"input": {"texts": texts},
|
|
"parameters": {"text_type": "document", "dimension": 1536}
|
|
}
|
|
|
|
try:
|
|
response = requests.post(url, headers=headers, json=payload, timeout=60)
|
|
response.raise_for_status()
|
|
result = response.json()
|
|
|
|
if "output" in result and "embeddings" in result["output"]:
|
|
embeddings_list = result["output"]["embeddings"]
|
|
embeddings_list.sort(key=lambda x: x["text_index"])
|
|
|
|
# --- 核心修复：对每个浮点数保留 8 位小数，解决精度过高报错 ---
|
|
final_vectors = []
|
|
for item in embeddings_list:
|
|
# 将每个 float 限制在 8 位精度以内
|
|
rounded_vector = [round(float(val), 8) for val in item["embedding"]]
|
|
final_vectors.append(rounded_vector)
|
|
return final_vectors
|
|
else:
|
|
return [None] * len(texts)
|
|
except Exception as e:
|
|
print(f"Alibaba Embedding Error: {e}")
|
|
return [None] * len(texts)
|
|
|
|
def main(text: str, api_key: str):
|
|
|
|
vector = chunks_embedding([text], api_key)[0]
|
|
return {
|
|
'vector': vector
|
|
} |