Bowei Xia
Bowei Xia
enmm我早上尝试去看了一下gradio的源码，试了很多种办法，他原理上针对音频流是通过二进制数据输出到/stream/下的一个文件夹内，然后把改地址传到Audio里，但貌似浏览器不支持直接读取二进制文件。我就修改了一下gradio的源码把他弄成每次生成一个文件，包括历史，类似积累的输出吧，然后通过/file=/file_path读取，但每次输出太快会覆盖掉之前的wav文件，没办法也需要要等全部弄好才能播放。可能还是等他怎么处理/stream/。很难受
Hi, I am very interested in this question.
I am very interested in this issues.
> hello @subway-jack ,anything blocking you?let us know if you need any help,thanks Thank you for the gentle reminder. I’m sorry I haven’t pushed the latest changes yet—some other tasks...
> and can you add some examples and tests by updating example/browser_toolkit.py and test/test_browser_toolkit.py? Thank you for the reminder. Since synchronous and asynchronous tests and examples cannot run in the...
Hello, @Wendong-Fan ,I will take it.
Hey @AveryYay , just a suggestion:It seems unnecessary to add a separate search method to BaseVectorStorage. Instead, we can simply enhance the existing query method by adding an optional filter_conditions:...
Oh I see, so the search you are talking about refers to pure filtering without content matching
## Required Libraries Make sure to install `unstructured[pdf]`： ```bash pip install "unstructured[pdf]" ``` Otherwise, you might see the following warnings (they do not cause errors, so they might go unnoticed):...
Can you give me your running code?