-
## The problem
Weaviate includes all relevant properties in vectorization, by default.
The only way we can remove a property from vectorization is by adding `skip: True` in the Collection Configur…
-
# 基于向量化和大型语言模型的知识库与交互系统
各位见笑。我就是一菜鸡，下文如果说得不对的地方请指正，莫要见怪。
就目前而言，各类开源大语言模型最大的使用方向就是知识库、问答系统等垂直领域。
目前的解决方案有二：
## 1、模型外挂知识库，比如【闻达】。
优点：技术比较简单，实用性比较强。
缺点：受模型token限制，自然语言文本信息承载量也比较低，能处理的信息有限，难以整合大…
-
I implemented a multilabel prediction algorithm for NLP text classification.
Basically, use multilabelbinarizer, binary_crossentropy, and a final sigmoid activation. Since I'm not using a softmax o…
-
能否在文档说下 text2vec.SentenceModel 和 SentenceTransformer 到底有什么区别？
我试了readme 给的例子，发现他们计算出的示例句子的词向量是一样的。
-
Hi! I've noticed that text_tokenizer-function does not work with non-ASCII letters. I noticed it when trying to use my own pre-trained Finnish word embeddings as part of a text classifying model.
…
-
### Search before asking
- [X] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar issues.
### Operating system information
MacOS(M1, M2…
-
Use the following `docker-compose.yml` to spin up weaviate and contextionary.
docker-compose.yml
```yml
# docker-compose.yml
---
version: "3.4"
services:
weaviate:
command:
…
-
I can't find this information in the documentation and I'd like to know if it's possible what am I trying or what I am doing wrong.
My goal is to search for a term and filter the results to objects…
-
# 基于向量化和大型语言模型的知识库与交互系统
各位见笑。我就是一菜鸡，下文如果说得不对的地方请指正，莫要见怪。
就目前而言，各类开源大语言模型最大的使用方向就是知识库、问答系统等垂直领域。
目前的解决方案有二：
## 1、模型外挂知识库，比如【闻达】。
优点：技术比较简单，实用性比较强。
缺点：受模型token限制，自然语言文本信息承载量也比较低，能处理的信息有限，难以整合大…
-
```
Warning (test-smallk.R:45:5): small k topicmodels
partial match of 'topic' to 'topics'
Backtrace:
▆
1. ├─testthat::expect_error(...) at test-smallk.R:45:5
2. │ └─testthat:::expect_c…