Mickls

国内有浏览器吗，全都是套了一层壳的假浏览器

I also encountered the problem of querying json field content when writing crud code. I am very concerned about whether this discussion has a clear answer. Considering that this is...

代码都是可行的，出现报错请上传报错信息。

> > > > 还有bert编码的时候要设置max length吧，对于字段超过512的会报错维度不匹配。input_ids = tokenizer(text, padding=True, truncation=True,max_length=512, return_tensors="pt")["input_ids"] 这些问题本质上都是你的样本跟代码不匹配导致的，这个仓库仅仅作为readme贴的博文所描述的原理论证，并不能支撑生产环境和复杂情况。如果想要更快的处理文档可以尝试结合langchain来处理： ``` from langchain.vectorstores import Milvus from langchain.document_loaders import DirectoryLoader, TextLoader from langchain.text_splitter import CharacterTextSplitter from langchain.embeddings import HuggingFaceEmbeddings...

> > > > > > > > > > > > > 还有bert编码的时候要设置max length吧，对于字段超过512的会报错维度不匹配。input_ids = tokenizer(text, padding=True, truncation=True,max_length=512, return_tensors="pt")["input_ids"] > > > > > > 这些问题本质上都是你的样本跟代码不匹配导致的，这个仓库仅仅作为readme贴的博文所描述的原理论证，并不能支撑生产环境和复杂情况。如果想要更快的处理文档可以尝试结合langchain来处理： > > ```...

> > > > > > > > > > > > > > > > > > > > > 还有bert编码的时候要设置max length吧，对于字段超过512的会报错维度不匹配。input_ids = tokenizer(text, padding=True, truncation=True,max_length=512, return_tensors="pt")["input_ids"] > >...

> 主layout模型并不太支持这个文件。 有什么其它模型可以搞定这个文件吗

Hello, I am very interested in this feature. Is it possible for it to be merged into the main branch?

> > Hello, I am very interested in this feature. Is it possible for it to be merged into the main branch? > > i believe this pr has gone...

Hello, have you solved this problem? I also encountered the same problem. If you solve this problem, I hope you can tell me how it is implemented. Thank you