I've built the same toy project (personalized bedtime story generator) with lang-chain and lang-graph + pydanticAI. I preferred the latter. With agents right now the priority is to try to wrestle predictability out of the models and working with pydantic backed dependencies and state is great

I am very impressed and I am getting great results for queries like "Show me how to use langchain in python".

However I am disappointed that when I provide a url it can not read the page. Given that this is a search engine I would expect it to be able to read any public URL I provide it. For example I attached a PDF of my resume and provided a link to a public job description and asked it to generate a cover letter tailored to my experience for this position. This is something I have done with easy success with ChatGPT GPT-4o, but Phind throws its hands up. :(

Thank you! Appreciate the feedback. Custom links are something we should be able to do -- we'll run some checks and make sure that feature is working properly. Thanks for letting me know.

My pleasure. Here are the searches in question: https://www.phind.com/search/cm73qdt6s00043b6qgccsnse8 https://www.phind.com/search/cm73qi43300003b6r8hlbxblw

Location: Los Angeles, CA

Remote: Open to remote or hybrid

Willing to relocate: No

Technologies: Python, Django, FastAPI, PostgreSQL

Résumé/CV: https://drive.google.com/file/d/13lFWbghYECCzY8QAEjXcC44RlPd...

Email: joshszep@gmail.com

Hey HN,

I’m a Staff Backend Engineer with 20+ years of experience, currently looking for my next opportunity. I specialize in Python, Django, FastAPI, PostgreSQL, and scalable system architecture. I’ve built and led the development of high-performance applications, mentored engineers, and leveraged AI-assisted development tools to accelerate workflows.

I’m particularly interested in startups or small companies where I can have a high impact, take ownership, and help build something great. I thrive in fast-moving environments and love solving complex problems at scale.

this happens after I've moved everything to height. downside is it was a lot of work. upside is height is amazing and I'm pleased with the choice. anyone else using it?

> anyone else using it?

We're looking for a new home, with Pivotal Tracker shutting down on April 30th (101 days left!). I had not heard of Height before.

On first glance, it looks like a genuinely modern project management service -- which is both interesting and unsettling.

We are loving it and we aren't even using it fully to its ability. For example we do almost no communication in the 'chat' that exists for each issue (in place of comments) since we are a very small team and still are talking mostly in slack about the issues, but I predict as we grow this will become a useful feature for us.

In the meantime we are loving the 'every issue can have sub-issues' and have customized the fields to our liking.

This is a tool with a lot of power. I can see a well-intentioned PM going crazy with it, but for our needs I was startled with how great it is.

what is height?

Maybe this? https://height.app/

I really wanted to click on the features as they slid by to learn more about them. I was disappointed when I couldn't.

I bit the bullet and am trying it out. I'll let anyone who is interested know how it goes.

pylance is pyright under the hood, isn't it? it's the main reason I use pyright over mypy: I work in VSCode and I want compatible type checking

excellent! I have been using Cursor for the last couple months after a year of using GitHub Co-Pilot.

it's not even a fair comparison. Cursor is just so much better, especially comparing it's chat quality to GitHub Co-Pilot chat.

DMNO looks wonderful. I would love to use it for a monorepo which is using TypeScript/React for frontend services and Python for the backend. Native Python support please, `user_demand += 1`

And the following examples show it is not. While it is pretty straightforward to add `uv ` in front of any pip calls, it is not API compatible.

Granted they are still working on it, but in the meantime - add a shell alias for uv?

alias pip="/usr/bin/uv pip"

How does that solve the problem that uv isn't a drop-in replacement? Are they going to implement the whole of pip, warts and all? Unlikely, because even though its in rust, they're getting a fair bit of speedup by making assumptions (see their ruff benchmarks, most of pylint isn't implemented), and as we've seen with both poetry and pipenv, those assumptions break down. pixi may get somewhat closer (given their experience with conda, and so familiarity with workflows and needs outside webdev), but I suspect uv will only further add issues and confusion to Python installs (especially if people decide to try aliasing and things break).

I jumped to conclusions in my previous comment, but that was based on a personal experience. Realistically, I've only ever needed 2 commands: `pip freeze > requirements.txt` and `pip install -r requirements.txt`. They don't need 100% API compatibility to deliver value, just "good enough". 80/20 rule and all that.

The issue is, Python has multiple projects that are already doing that, and they've not been adopted (and then everyone complains that Python packaging is a mess...). Maybe uv will be like the easy_install -> pip transition, but I doubt it (the requirements are much higher and more diverse).

Arguably they'd get significantly further choosing a specific and narrow use-cased and nailing it (e.g. deploying WSGI/ASGI apps via OCI containers, with the ability to have live reload during dev), rather than introducing another option whose main selling point is speed, which while nice, is hardly going to resolve why we have the different use-cases and hence solutions.

I can't use it unless it implements list -o and install -U

take it all the way and force integrate it into venv