FRESH

Hacker News

Home

Show HN: Semantic grep with local embeddings

169 points by Runonthespot

by MarkMarine

1 subcomments

I saw this comment a little bit back and I don’t think the OP expanded on it, but this looks like a fantastic idea to me:
sam0x17 20 days ago:
Didn't want to bury the lead, but I've done a bunch of work with this myself. It goes fine as long as you give it both the textual representation and the ability to walk along the AST. You give it the raw source code, and then also give it the ability to ask a language server to move a cursor that walks along the AST, and then every time it makes a change you update the cursor location accordingly. You basically have a cursor in the text and a cursor in the AST and you keep them in sync so the LLM can't mess it up. If I ever have time I'll release something but right now just experimenting locally with it for my rust stuff On the topic of LLMs understanding ASTs, they are also quite good at this. I've done a bunch of applications where you tell an LLM a novel grammar it's never seen before _in the system prompt_ and that plus a few translation examples is usually all it takes for it to learn fairly complex grammars. Combine that with a feedback loop between the LLM and a compiler for the grammar where you don't let it produce invalid sentences and when it does you just feed it back the compiler error, and you get a pretty robust system that can translate user input into valid sentences in an arbitrary grammar.
https://news.ycombinator.com/item?id=44941999

by athrowaway3z

1 subcomments

> thread 'main' (17953) panicked at ck-cli/src/main.rs:305:41: byte index 100 is not a char boundary
I seem to have gotten 'lucky' and it split an emoji just right.
---
For anyone curious: this is great for large, disjointed, and/or poorly documented code bases. If you kept yours tight and files smaller than ~600 lines, it is almost always better to nudge llm's into reading whole files.

by dorian-graph

1 subcomments

There's also https://github.com/bartolli/codanna, that's similarly new. I'll have to try that again, and this one.

by ozten

1 subcomments

This generalizes to a whole new category of tools: UX which requires more thought and skill, but is way more powerful. Human devs are mostly too lazy to use, but LLMs will put in the work to use them.

by CuriouslyC

1 subcomments

I actually have a WIP library for this, the indexing server isn't where I want it just yet, but I have an entire agent toolkit that does this stuff, and the indexing server is quite advance, with self-tuning, raptor/lsp integration, solves for optimal result set using knapsack, etc.
https://github.com/sibyllinesoft/grimoire

by joecarpenter

0 subcomment

Well, there's also mine https://github.com/VectorOps/know with some details what it does and how: https://vectorops.dev/blog/post-1/

by rane

0 subcomment

Cool. Some AI fluff can be detected in the README.
For example under the "Why CK?" section, "For teams" is of no substance compared to "For developers"

0 subcomment

by 0x696C6961

2 subcomments

This is cool, but I don't understand why it tries to re-implement (a subset of) grep. Not only that, but the grep-like behaviour is the default and I need to opt-in to the semantic search using the --sem flag. If I want grep I can use grep/ripgrep.

by rane

1 subcomments

I tried in my relatively small project.

    ~/c/l/web % ck --sem 'error handling'
    ℹ Semantic search: top 10 results, threshold ≥0.6
    ⠹ Searching with semantic mode...

All I got was spinning M2 Mac fan after a minute, and gave up.

by nwienert

0 subcomment

The biggest improvement to CC would be it using the TypeScript LSP to immediately get type feedback and inspect types.
I added the VSCode plugin but it didn’t seem to help, likewise searching around yesterday I didn’t see anything surprisingly.

by jarek83

1 subcomments

Man, that's a great thing! Really waiting to see Ruby and Elixir. Fingers crossed for you!

0 subcomment

by skybrian

1 subcomments

This looks very useful.
Looks like you have to build an index. When should it be rebuilt? Any support for automatic rebuilds?

by abyesilyurt

1 subcomments

What model are you using to create the embeddings?

by dprophecyguy

4 subcomments

this is so cool, is there any other tool which is more mature?

by Alifatisk

1 subcomments

At this point, we aren't even saying it's written in Rust anymore, we just mention it in the title whenever possible.
I did look into the core features and I gotta say, that looked quite cool. It's like Google search, but for the codebase. What does it take to support other languages?

by farhan99

0 subcomment

[dead]

by dang

4 subcomments

[stub for offtopicness]