firezym
firezym
### System Info The llm model using default davinci example provided in https://python.langchain.com/en/latest/ecosystem/wandb_tracking.html is OK. But seems not able to handle ChatOpenAI object. How to solve this? The code is...
### Describe the bug In WSL Ubuntu 22.04.1 LTS, I use the following proxy setting so that I can get to OpenAI and pips behind the proxy. If I add...
新闻通讯`pro.major_news`中，部分`src`重复新闻在一个很短时间段超过200篇，很容易挤占其他`src`的新闻提取，因为接口有每次提取的限额，这样会导致有些新闻提取不到，以下面时间段为例，5分钟内有超过200篇，实际上去重后仅有16篇。期待官方去重。 ```python df = pro.major_news(src='', start_date='2020-06-03 08:30:00', end_date='2020-06-03 08:35:00', fields='pub_time,title,content,src') print(len(df)) print(len(df.drop_duplicates(subset=['title', 'content']))) df ``` 下面列出了部分有大量重复的时间段，因为数据没拉完，所以应该还不是全部，看了下，其中src='凤凰财经'出现概率较高（22年2月以后，这个现象少很多）： ``` 2020-05-18 08:30:00 2020-05-18 09:00:00 2020-06-03 08:30:00 2020-06-03 09:00:00 2020-06-05 08:30:00 2020-06-05 09:00:00 2020-06-06...
@srstevenson Thanks for this awesome repo. I am having some trouble cleaning notebooks with html/js inside. Below is the detailed error. Please kindly check it out :) ## System :...
有网址不能提取
`curl https://r.jina.ai/https://www.stats.gov.cn/sj/zxfb/202405/t20240517_1955759.html` - 统计局的网站似乎就访问不了：https://www.stats.gov.cn - Error Message: {"data":null,"cause":{"name":"TimeoutError"},"code":422,"name":"AssertionFailureError","status":42206,"message":"Failed to goto https://www.stats.gov.cn/sj/zxfb/202405/t20240517_1955759.html: TimeoutError: Navigation timeout of 30000 ms exceeded","readableMessage":"AssertionFailureError: Failed to goto https://www.stats.gov.cn/sj/zxfb/202405/t20240517_1955759.html: TimeoutError: Navigation timeout of 30000 ms exceeded"}
First connection to server by python client sdk is very slow. Usually takes up to 30~40s to connect to local docker instance. Version: v0.6.0-dev3 Docker Version: nightly, sha256:964f74c366a7f8ee929c3b08978f32c7188f7eb544f0f14387d030b6855180b2 Seems this...
### Is there an existing issue for the same bug? - [x] I have checked the existing issues. ### Version or Commit ID 0.6.0 ### Other environment information ```Markdown Docker...
### Describe your problem If I have a large database storing colbert tensors and I want `match_tensor` ranking in hybrid search `rrf` or `weighted_sum` (but not in final stage reranking)....
I have other packages depending on higher versions of transformer such as sentence-transformers, marker-pdf and so on. Can the future releases upgrade transformers version requirements? ``` flagembedding 1.3.2 has requirement...