Live data from Hacker News

Ask HN: Show me your half baked project

news.ycombinator.com

181–190 of 708 posts

Re: Ask HN: Show me your half baked project

#181
Here is a command line code search tool like grep/ack/ag/ripgrep, called grep-ast.

It shows you semantically relevant code context around the lines that match your search. This lets you see the loops, functions, methods, classes, etc that contain all the matching lines. You can get a sense of what's inside a matched class or function definition. It shows relevant code from every layer of the abstract syntax tree, above and below the matches.

https://github.com/paul-gauthier/grep-ast

Here's an example, which would also have colorized matches when run in the terminal:

  django$ grep-ast ROOT_URLCONF

  middleware/locale.py:

  │from django.conf import settings
  │from django.conf.urls.i18n import is_language_prefix_patterns_used
  │from django.http import HttpResponseRedirect
  ⋮...
  │class LocaleMiddleware(MiddlewareMixin):
  │    """
  │    Parse a request and decide what translation object to install in the
  │    current thread context. This allows pages to be dynamically translated to
  │    the language the user desires (if the language is available).
  ⋮...
  │    def process_request(self, request):
  ▶        urlconf = getattr(request, "urlconf", settings.ROOT_URLCONF)
  │        (
  │            i18n_patterns_used,
  │            prefixed_default_language,
  │        ) = is_language_prefix_patterns_used(urlconf)
  ⋮...
  │        if (
  │            not language_from_path
  │            and i18n_patterns_used
  │            and not prefixed_default_language
  │        ):
  │            language = settings.LANGUAGE_CODE
  │        translation.activate(language)
  │        request.LANGUAGE_CODE = translation.get_language()
  │
  │    def process_response(self, request, response):
  │        language = translation.get_language()
  │        language_from_path = translation.get_language_from_path(request.path_info)
  ▶        urlconf = getattr(request, "urlconf", settings.ROOT_URLCONF)
  │        (
  ⋮...
  │        return response

Re: Ask HN: Show me your half baked project

#183
https://www.summarycat.com/

I made a YouTube summarizer, Summary Cat.

————————-

Technical Details

Goal: Generate brief and coherent summaries from YouTube video transcripts

Motivation of building this project: to save myself time watching videos that are too long.

Stack • Frontend: HTML/CSS, plus a tiny bit of Javascript for handling the button • Backend: Python/Flask • Flask served as the backend web framework, handling routes and integrating various services. • Front+Backend has about 500 lines in total • Hosting: AWS Free-tier Elastic Beanstalk • Database: AWS Free-tier RDS

APIs: • For grabbing YouTube's transcripts: I used youtube-transcript-api (https://pypi.org/project/youtube-transcript-api/) • For summarizing the transcripts: I used OpenAI's GPT-3.5-turbo-16k: https://platform.openai.com/docs/guides/gpt. • I used GPT-3.5 because GPT-4 is quite a lot more expensive (roughly 10X).

My Prompt (Super Simple!) • "please summarize the following text into a few paragraphs:" + the full transcript.

Thoughts about GPT-4 vs GPT-3.5-Turbo-16k or Summary Cat • GPT-4 was 20% better for "summary quality" • GPT-4 feels 50% faster • However, GPT-4 is about 10X as expensive as GPT-3.5

Re: Ask HN: Show me your half baked project

#184
https://gist.aviperl.me/

Convert your GitHub Gists into a full featured blog and RSS feed.

Example: https://gist.aviperl.me/avi-perl https://gist.aviperl.me/avi-perl/rss

By default it works as a simple redesign of an existing set of gists. But gist hosted configuration files and compiling gist data to a static site can turn it into something much more rich, seo friendly, etc.

Re: Ask HN: Show me your half baked project

#186
https://github.com/totalhack/zillion

Semantic data warehousing and analytics tool written in python. It has experimental/half-baked NLP features to query your warehouse by interacting with the semantic layer with AI, instead of the normal approach of having an LLM write SQL and needing to know your entire schema.

Re: Ask HN: Show me your half baked project

#188
I love this thread, thank you!

Ampwall. Musician-owned, Public Benefit Co alternative to Bandcamp. (Eventually.) https://ampwall.com. Dogfooding it with my own band’s merch sales at https://woeunholy.ampwall.com. Digital audio will launch soon (2-3 weeks?) and we plan on starting our tests with outside bands/labels by end of year.

I’ve been building this throughout the past year but the stuff that’s publicly available is pretty basic. I was going to keep it quiet but the news about Epic selling Bandcamp two weeks ago prompted me to announce early, so might as well share it here too and really put the cart before the horse!

I have a lot of opinions about things I’ve always wanted Bandcamp to offer. While it’s going to start very similar to BC, we’re going to experiment with some very different things ASAP. The feedback I gathered throughout the year showed me that there’s a hunger for this and the response to my announcement was bigger than I expected, so I’m feeling good about it. It’s been fun to build and it’s going to get better.

It’s all Next.js and TypeScript. Hosted on Node.js servers because I don’t think serverless is for me. I’m using Porter.run for production, a YC alum whose office is in my neighborhood in Queens!

Re: Ask HN: Show me your half baked project

#189
https://github.com/lgrammel/storyteller

StoryTeller is an exploratory web application that creates short audio stories for pre-school kids.

It used speech-to-text, llms, text-to-speech, embeddings and image generation.

StoryTeller is built with the following libraries:

ModelFusion Fastify Next.js shadcn/ui Zod

The following AI APIs are used:

OpenAI Eleven Labs Lmnt Stability

Post reply on HN