一个简单的rank模型的OPENAI兼容API服务的客户端访问工具。
Project description
openai-simple-rerank
一个简单的rank模型的OPENAI兼容API服务的客户端访问工具。
安装
pip install openai-simple-rerank
使用
建议使用xinference启动rerank模型
验证过的模型列表
- bge-reranker-v2-m3
配置变量设置
# OPENAI兼容API服务,可以xinference提供
# 使用OPENAI_RERANK_BASE_URL或RERANK_BASE_URL设置独立的服务地址
export OPENAI_BASE_URL="http://localhost/v1"
# OPENAI兼容API服务密钥,一般以sk-开头,共16位长
# 使用OPENAI_RERANK_API_KEY或RERANK_API_KEY设置独立的服务密码
export OPENAI_API_KEY=""
# 默认的文本重排序模型
export OPENAI_RERANK_MODEL="bge-reranker-v2-m3"
# 默认的最大字符串长度控制
export OPENAI_RERANK_MAX_SIZE=1024
获取文本向量
代码
from openai_simple_rerank.base import get_rerank_scores
s1, s2 = get_rerank_scores("hello", ["hi", "world"])
print(s1, s2)
输出
0.9953891038894653 0.40583446621894836
关于字符串长度控制
- 模型本身一般没有字符串长度控制。
- 但过长的字符串会导入模型占用内存的增长。
- 所以默认将字符串长度控制在:1024字。
- 通过
OPENAI_RERANK_MAX_SIZE设置默认最大字符串长度。 - 也可以函数调用中指定最大字符串长度。
- 注意:所有超过最大长度的字符串将被截断。
版本记录
v0.1.0
- 版本首发。
v0.1.1
- 允许rerank模型使用独立的服务地址及密码。
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file openai-simple-rerank-0.1.1.tar.gz.
File metadata
- Download URL: openai-simple-rerank-0.1.1.tar.gz
- Upload date:
- Size: 8.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ff4e0151d5d73a466dd41d3eb8368d7e9e3a02dd8117e1bd4a881dbd11cb6245
|
|
| MD5 |
deb0444ad8be79b6b40377baccd9cc83
|
|
| BLAKE2b-256 |
07c1fb673ce9e245d447429dafae1f2c95594ba8f283c050ac9e93828fe4f746
|
File details
Details for the file openai_simple_rerank-0.1.1-py3-none-any.whl.
File metadata
- Download URL: openai_simple_rerank-0.1.1-py3-none-any.whl
- Upload date:
- Size: 9.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d96a307a2b8fefeee00e29d293ca69cb829f7862fbbe1cbb0881a39069161b61
|
|
| MD5 |
7016c9a744f5943c6be03adf5442a307
|
|
| BLAKE2b-256 |
9889433837618f31423c3a6f6cc9698471342153990ecba58f4759e71b6d01b9
|