chunelfeng / caiss Goto Github PK
View Code? Open in Web Editor NEW一款简单好用的 跨平台/多语言的 相似向量/相似词/相似句 高性能检索引擎。欢迎star & fork。Build together! Power another !
一款简单好用的 跨平台/多语言的 相似向量/相似词/相似句 高性能检索引擎。欢迎star & fork。Build together! Power another !
我看这个库最近一次更新在一年前,是认为已经完善了?还是不准备持续支持了呢?
256 double数组向量,相似度是用余玄夹角计算,可以用caiss做以图搜图吗,另外caiss有交流群吗,谢谢大佬
首先感谢大佬优秀的项目!
我的场景是这样的,想做一个简单的本地以图搜图引擎,只需要本地运行,没有集群需求,所以觉得大佬这个库十分适合(milvus对于我这个需求来说比较复杂了,而且没有官方的Windows版本支持)。
将图片向量化(embedding)这一步我已经实现了(使用towhee),也就是得到了每个图片的向量,那训练样本的格式如何填写?(其实没太懂这里的训练在训练什么哈哈)
是这样填写吗?
{"imagePath1": vector}
{"imagePath2": vector}
希望大佬不吝赐教😁
An English description would help. Thank you! 🙏
DIM = 768
#WORD = 'go|home'
WORD = ['go home']
TOP_K = 5
#SEARCH_TYPE = CAISS_SEARCH_WORD
SEARCH_TYPE=CAISS_SEARCH_QUERY
请问相似句查询时 参数WORD或者QUERY应该写怎样的格式
pyCaiss.py:
if search_type == CAISS_SEARCH_QUERY or search_type == CAISS_LOOP_QUERY:
# 如果传入的是数组信息,需要将数组转成指针传递下去
#print('len:',len(info))
# print('self._dim',self._dim)
# print('info[0]',info[0])
if self._dim != len(info):
return CAISS_RET_DIM, ''
vec = (c_float * self._dim)()
for i in range(0,int(self._dim)):
#print('vec',vec[i])
vec[i] = info[i]
#print('vec',vec[i])
ret = self._caiss.CAISS_Search(handle, vec, search_type, top_k, filter_edit_distance, None, None)
pyCaiss.py文件中当我查询格式换成 CAISS_SEARCH_QUERY是 我应该传怎样的info满足vec
这部分不是很懂,恳请解决一下。
厉害了哈~
这个怎么做俩段话的语义相似度啊
索引的逻辑和检索的逻辑是使用的faiss吗? 还是自己开发的?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.