sketch
trivial-gamekit
Our great sponsors
sketch | trivial-gamekit | |
---|---|---|
20 | 7 | |
2,179 | 162 | |
3.0% | - | |
4.4 | 0.0 | |
about 2 months ago | over 2 years ago | |
Python | Common Lisp | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sketch
-
Ask HN: What have you built with LLMs?
We've made a lot of data tooling things based on LLMs, and are in the process of rebranding and launching our main product.
1. sketch (in notebook, ai for pandas) https://github.com/approximatelabs/sketch
2. datadm (open source, "chat with data", with support for the open source LLMs (https://github.com/approximatelabs/datadm)
3. Our main product: julyp. https://julyp.com/ (currently under very active rebrand and cleanup) -- but a "chat with data" style app, with a lot of specialized features. I'm also streaming me using it (and sometimes building it) every weekday on twitch to solve misc data problems (https://www.twitch.tv/bluecoconut)
For your next question, about the stack and deploy:
-
Pandas AI – The Future of Data Analysis
Sketch is similar, but can do code generation (with `.sketch.howto`): https://github.com/approximatelabs/sketch
> This because the function is no longer idempotent, each call to the AI can yield a different result.
Also, it means that processing larger datasets may be more expensive.
This morning I added a "Related Projects" [3] Section to the Buckaroo docs. If Buckaroo doesn't solve your problem, look at one of the other linked projects (like Mito).
[1] https://github.com/approximatelabs/sketch
-
Ask HN: What's your favorite GPT powered tool?
For GPT/Copilot style help for pandas, in notebooks REPL flow (without needing to install plugins), I built sketch. I genuinely use it every-time I'm working on pandas dataframes for a quick one-off analysis. Just makes the iteration loop so much faster. (Specifically the `.sketch.howto`, anecdotally I actually don't use `.sketch.ask` anymore)
-
RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI
https://github.com/approximatelabs/lambdaprompt It has served all of my personal use-cases since making it, including powering `sketch` (copilot for pandas) https://github.com/approximatelabs/sketch
Core things it does: Uses jinja templates, does sync and async, and most importantly treats LLM completion endpoints as "function calls", which you can compose and build structures around just with simple python. I also combined it with fastapi so you can just serve up any templates you want directly as rest endpoints. It also offers callback hooks so you can log & trace execution graphs.
All together its only ~600 lines of python.
I haven't had a chance to really push all the different examples out there, but most "complex behaviors", so there aren't many patterns to copy. But if you're comfortable in python, then I think it offers a pretty good interface.
I hope to get back to it sometime in the next week to introduce local-mode (eg. all the open source smaller models are now available, I want to make those first-class)
-
[D] The best way to train an LLM on company data
Please look at sketch and langchain pandas/SQL plugins. I have seen excellent results with both of these approaches. Both of these approaches will require you to send metadata to openAI.
-
Replacing a SQL analyst with 26 recursive GPT prompts
(3) Asking for re-writes of failed queries (happens occasionally) also helps
The main challenge I think with a lot of these "look it works" tools for data applications, is how do you get an interface that actually will be easy to adopt. The chat-bot style shown here (discord and slack integration) I can see being really valuable, as I believe there has been some traction with these style integrations with data catalog systems recently. People like to ask data questions to other people in slack, adding a bot that tries to answer might short-circuit a lot of this!
We built a prototype where we applied similar techniques to the pandas-code-writing part of the stack, trying to help keep data scientists / data analysts "in flow", integrating the code answers in notebooks (similar to how co-pilot puts suggestions in-line) -- and released https://github.com/approximatelabs/sketch a little while ago.
-
FLiP Stack Weekly for 21 Jan 2023
Python AI Helper https://github.com/approximatelabs/sketch
-
LangChain: Build AI apps with LLMs through composability
In terms of applications with it, I have made things like sketch: https://github.com/approximatelabs/sketch
Raw prompt-structure ideas i've worked with:
trivial-gamekit
-
interested in learning lisp, (specifically for games, but also for everything else including tui and gui applications for linux. currently have next to no programming knowledge, can i get forwarded some resources and some tips on what exactly i should do? any videos i should watch?
If you insist on learning through game development -- and admittedly I learn best by just jumping in and doing something -- you should at least try making something simpler than a full 3D game first, like a roguelike: https://github.com/borodust/trivial-gamekit, https://borodust.org/projects/trivial-gamekit/.
-
Common lisp game development libraries
For something simple, https://github.com/borodust/trivial-gamekit would do.
-
Cl-bodge: a cross-platform Common Lisp game and application framework
Playing with their 'trivial-gamekit' based on cl-bodge now, very nice I think!
https://borodust.org/projects/trivial-gamekit/
alien-works also looks cool and under active development
-
[SBCL] Generating a binary of a GUI built with Sketch
If all else fails, I recommend trying to contact author through creating an issue on github. If that fails too and you are too tired to continue that fight, have a look at trivial-gamekit (beware: shameful self-plug).
-
Should I learn OpenGL, or try building a graphics engine from scratch ?
Learn Common Lisp and high-level 2D graphics using Sketch or trivial-gamekit. It's lispy, super fun and enjoyable way. Seriously. 2D graphics are easy to grasp and intuitive.
What are some alternatives?
Carp - A statically typed lisp, without a GC, for real-time applications.
alien-works - Multiplatform game foundation framework for Common Lisp
lmql - A language for constraint-guided and efficient LLM programming.
tank-command-2000 - A 3d tank game
RasaGPT - 💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram
gpt_index - LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data. [Moved to: https://github.com/jerryjliu/llama_index]
nature-of-code - Nature of code exercises and examples implemented in Common Lisp
alloy - A new user interface protocol and toolkit implementation
pandas-ai - Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
sketch - A Common Lisp framework for the creation of electronic art, visual design, game prototyping, game making, computer graphics, exploration of human-computer interaction, and more.
trial - A fully-fledged Common Lisp game engine
cl-opengl - cl-opengl is a set of CFFI bindings to the OpenGL, GLU and GLUT APIs.