-
Here would agree a series of tests using the same test text(s), and compare performance in a set of agreed tasks. This would provide a nice way of seeing how the various packages and approaches work f…
-
模型文件具体在哪，我没看到，但是再开头的log日志里我看到快7个G的文件是下载完了的，我用的hugging face
-
## Description
Hi, nice application :)
I try to use it with local ollama & weaviate vector DB
Seems to be an default communication issue, verba try to connect on IPV6 tcp [::1] and recei…
-
# 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 am going through the text2vec-transformers how to guide (https://weaviate.io/developers/weaviate/modules/retriever-vectorizer-modules/text2vec-transformers) and I am at the part in option 2 where I'…
-
https://weaviate.slack.com/archives/C017EG2SL3H/p1636103379214500
-
When there is an error the client returns a stack trace. Sometimes the stack trace is very long, which makes it hard to find the error statement. Can the stack traces be shortened (or made optional)? …
-
## 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…
-
1. Cloned and installed with `pip install -e .`
2. Went to examples directory `cd examples`
3. Tried one of the examples with `python Single_Agent/run_gradio.py --agent Single_Agent/shopping_assista…