Christopher

Only outputs about 500 bytes of text ?

3

hear -i some.mp3 > text.txt or hear -i some.mp3 ... only outputs the same first 500 bytes of text macOS Monterey version 12.4 Thoughts? chris

What are some best practices or good techniques for rate limiting or throttling outbound HTTP GET and POST requests ? For example, getting Stumbleupon's for a particular URL: "http://www.stumbleupon.com/services/1.01/badge.getinfo?url=http://amazon.com" ......

errors in Hello World example

6

Hi, Like others have noted I am also experiencing errors regarding 4.png and crossdomain.xml. You may view the example here: http://cl.clsmith.org/ ... I haven't altered any of the code. I'm...

Chat with local files (Retrieval Augmented Generation?)

5

This is a cool project and works on my old Mac (Intel) and a newer Air (M1). Well, it's slow of course due to my hardware, but so easy to...

### What do you need? Some youtube video transcript grabbers don't work for previous live videos, but the one from the langchain community does, so consider using this one instead...

### What do you need? From a security point of view, when i ran ```fabric --setup``` it asks for keys (openai, claude, youtube) then failed updating patterns because i turned...

how do i change the models: llm or embedding

6

It seems that editing settings.yaml and running again isn't enough to change to different models. Are there any instructions for exactly how to do this? I see nothing in the...

server side validations

1

In chapter9+recipe1+contacts, for example: - entering "jjj" into the age field causes a validation error - follow that by entering "123" into to age field should give just that validation...

code 501, message Unsupported method ('GET')

10

pip install mlx-llm-server Works fine via curl. But some apps use a request to get a list of available models. The same as OpenAI's API does. This causes an issue...

If only convert_output.py did paragraphs (for readibility)

1

Wow! Well done, spot on, etc. This worked perfect on a MacBook Pro M3 after doing this: install: pipx install insanely-fast-whisper PYTORCH_ENABLE_MPS_FALLBACK=1 insanely-fast-whisper --file-name audio.mp3 --device-id mps --model-name openai/whisper-large-v3 --batch-size...