Bill Chen
Bill Chen
I notice that the output is not prefect especially the eyes and mouth with the pre-trained data v0.2.0. Is there better pre-trained data we can use? Thank you.
there is an error occurs. >>> api._get('/volumes',params) Traceback (most recent call last): File "", line 1, in File "/usr/local/lib/python3.5/site-packages/googlebooks.py", line 18, in _get return json.loads(resp.content) File "/usr/local/lib/python3.5/json/__init__.py", line 312, in...
$ lx Traceback (most recent call last): File "/bin/lx", line 3, in from lixian_commands.util import * ImportError: No module named lixian_commands.util to fix this issue, I have to modify lixian_cli.py...
### Your DownThemAll! and Browser Version and Language and Operating System dTa! v3.0.8 Firefox 55.0.3 (64-bit) Windows 7 SP1, English ### Expected Behavior Feature 1: alternative download URL(s) I'm in...
I'm trying to import torch and run torch.cuda.get_device_name(0), it throws the following error message： RuntimeError: The NVIDIA driver on your system is too old (found version 2147483647). Please update your...
The error occurs on Synology DSM 7 x86 often when I scan a folder with bunch of files: fatal error: runtime: out of memory runtime stack: runtime.throw({0x836229?, 0x0?}) /usr/local/go/src/runtime/panic.go:1047 +0x5d...
**Describe the feature you'd like** Is there a plan to automate the docker image deployment? There are so many new features/changes on the codes and new AI models everyday, and...
建议支持Voyage Embedding。这是Anthropic的御用embeddings，虽然[Voyage的价格](https://docs.voyageai.com/docs/pricing)比[OpenAI的](https://openai.com/pricing)还是贵一些，但是前50M tokens是免费的，羊毛够薅一阵子的了 🤣 ``` Embeddings We charge for requests to the Voyage embedding endpoint based on the number of tokens in the docs/queries. The first 50 million tokens for...
我是在相同的host上独立运行Ollama和Chroma的container。Chroma显示`{"detail":"Not Found"}`表示运行正常，Ollama Open WebUI连接Ollama没有问题，可以显示已经有3个模型了。 我在chatollama配置了Ollama和Chroma的连接，也配置了Anthropic的API，但是不显示任何模型，Ollama和Claude的模型都不显示。可以保存Instruction。不能生成Knowledge Base显示fetch failed（应该是不能调用embedding吧）。 查看docker的logs，显示如下： '''Ollama: { host: 'http://172.17.0.11:11434', username: null, password: null } Authorization: dW5kZWZpbmVkOnVuZGVmaW5lZA== [nuxt] [request error] [unhandled] [500] fetch failed at Object.fetch (node:internal/deps/undici/undici:11576:11) at...
现在建立KB的方式是一上传文件，二输入URL。我建议增加第三种方式，就是本地文件或者文件夹(recursive)，这样在服务器本地部署，或者用docker部署的时候，可以用导入本地文件（夹）的方式快速导入大量文件，避免上传过程的timeout或者各种限制。