cody VS llm-ls

checkout the cody extension https://github.com/sourcegraph/cody available for various editors like vscode

I don't think it is. There is a test file which includes C#, Kotlin, etc among supported languages, which aren't included in the file you linked: https://github.com/sourcegraph/cody/blob/main/vscode/src/com...

But this test didn't seem to include TypeScript so it's obviously not comprehensive. I'm not convinced this information is actually in one place.

Cody (https://github.com/sourcegraph/cody) supports using Ollama for autocomplete in VS Code. See the release notes at https://sourcegraph.com/blog/cody-vscode-1.1.0-release for instructions. And soon it'll support Ollama for chat/refactoring as well (https://twitter.com/sqs/status/1750045006382162346/video/1).

Disclaimer: I work on Cody.

Have you tried Cody (https://cody.dev)? Cody has a deep understanding of your codebase and generally does much better at code gen than just one-shotting GPT4 without context.

(disclaimer: I work at Sourcegraph)

3️⃣ Cody AI 🤖

Author of the post here—as another commenter mentioned, this is indeed a bit dated now, someone should probably write an updated post!

There's been a ton of evolution in dev tools in the past 3 years with some old workhorses retiring (RIP Phabricator) and new ones (like Graphite, which is awesome) emerging... and of course AI-AI-AI. LLMs have created some great new tools for the developer inner loop—that's probably the most glaring omission here. If I were to include that category today, it would mention tools like ChatGPT, GH Copilot, Cursor, and our own Sourcegraph Cody (https://cody.dev). I'm told that Google has internal AI dev tools now that generate more code than humans.

Excited to see what changes the next 3 years bring—the pace of innovation is only accelerating!

I'm sorry to hear that. We have made a lot of improvements to Cody recently. We had a big release on Oct 4 that significantly decreased latency while improving completion quality. You can read all about it here: https://about.sourcegraph.com/blog/feature-release-october-2...

We love feedback and ideas as well, and like I said are constantly iterating on the UI to improve it. I'm actually wrapping up a blog post on how to better leverage Cody w/ VS Studio, that'll be out either later today or sometime tomorrow. As far as feedback though: https://github.com/sourcegraph/cody/discussions/new?category... would be the place to share ideas :)

Ollama is awesome. I am part of a team building a code AI application[1], and we want to give devs the option to run it locally instead of only supporting external LLMs from Anthropic, OpenAI, etc. Those big remote LLMs are incredibly powerful and probably the right choice for most devs, but it's good for devs to have a local option as well—for security, privacy, cost, latency, simplicity, freedom, etc.

As an app dev, we have 2 choices:

(1) Build our own support for LLMs, GPU/CPU execution, model downloading, inference optimizations, etc.

(2) Just tell users "run Ollama" and have our app hit the Ollama API on localhost (or shell out to `ollama`).

Obviously choice 2 is much, much simpler. There are some things in the middle, like less polished wrappers around llama.cpp, but Ollama is the only thing that 100% of people I've told about have been able to install without any problems.

That's huge because it's finally possible to build real apps that use local LLMs—and still reach a big userbase. Your userbase is now (pretty much) "anyone who can download and run a desktop app and who has a relatively modern laptop", which is a big population.

I'm really excited to see what people build on Ollama.

(And Ollama will simplify deploying server-side LLM apps as well, but right now from participating in the community, it seems most people are only thinking of it for local apps. I expect that to change when people realize that they can ship a self-contained server app that runs on a cheap AWS/GCP instance and uses an Ollama-executed LLM for various features.)

[1] Shameless plug for the WIP PR where I'm implementing Ollama support in Cody, our code AI app: https://github.com/sourcegraph/cody/pull/905.

Awesome. The repository is at https://github.com/sourcegraph/cody for anyone who hasn't seen it yet.

> I'd have expected that the main lever the product has in being better than others is having a custom model that understands code edits much more than others.

True, but this is not something this particular product would solve. There are already models specifically trained to work on code. What's appealing to me is the flexibility of being able to choose which one to use, rather than my workflow being tied to a specific product or company.

> the IDE integration seems to be the "easy bit"

I admittedly haven't researched this much, but this is not currently the case. There is no generic API for LLMs that IDEs can plug into, so all plugins must target a specific model. We ultimately need an equivalent of an LSP server for LLMs, and while such a project exists[1], it looks to be in its infancy, as expected.

[1]: https://github.com/huggingface/llm-ls

Okay, I actually got local co-pilot set up. You will need these 4 things.

1) CodeLlama 13B or another FIM model https://huggingface.co/codellama/CodeLlama-13b-hf. You want "Fill in Middle" models because you're looking at context on both sides of your cursor.

2) HuggingFace llm-ls https://github.com/huggingface/llm-ls A large language mode Language Server (is this making sense yet)

3) HuggingFace inference framework. https://github.com/huggingface/text-generation-inference At least when I tested you couldn't use something like llama.cpp or exllama with the llm-ls, so you need to break out the heavy duty badboy HuggingFace inference server. Just config and run. Now config and run llm-ls.

4) Okay, I mean you need an editor. I just tried nvim, and this was a few weeks ago, so there may be better support. My expereicen was that is was full honest to god copilot. The CodeLlama models are known to be quite good for its size. The FIM part is great. Boilerplace works so much easier with the surrounding context. I'd like to see more models released that can work this way.