sketch
NeMo-Guardrails
Our great sponsors
sketch | NeMo-Guardrails | |
---|---|---|
20 | 13 | |
2,194 | 3,338 | |
1.8% | 7.9% | |
4.4 | 9.9 | |
3 months ago | 6 days ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
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
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
[2] https://github.com/paddymul/buckaroo
[3] https://buckaroo-data.readthedocs.io/en/latest/FAQ.html
-
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)
https://github.com/approximatelabs/sketch
-
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.
-
Meet Sketch: An AI code Writing Assistant For Pandas
👉 Understand your data through questions 👉 Create code from plain text Quick Read: https://www.marktechpost.com/2023/02/01/meet-sketch-an-ai-code-writing-assistant-for-pandas/ Github: https://github.com/approximatelabs/sketch
-
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
- Show HN: Sketch – AI code-writing assistant that understands data content
NeMo-Guardrails
- NeMO Guardrails from Nvidia
-
Run and create custom ChatGPT-like bots with OpenChat
- https://github.com/NVIDIA/NeMo-Guardrails/
- LangChain: The Missing Manual
-
The Dual LLM pattern for building AI assistants that can resist prompt injection
Here's "jailbreak detection", in the NeMo-Guardrails project from Nvidia:
https://github.com/NVIDIA/NeMo-Guardrails/blob/327da8a42d5f8...
I.e. they ask the llm if the prompt will break the llm. (I believe that more data /some evaluation on how well this performs is intended to be released. Probably fair to call this stuff "not battle tested".)
-
How To Setup a Model With Guardrails?
I have been playing around with some models locally and creating a discord bot as a fun side project, and I wanted to setup some guardrails on inputs / outputs of the bot to make sure that it isn't violating any ethical boundaries. I was going to use Nvidia's Nemo guardrails, but they only support openai currently. Are there any other good ways to control inputs?
-
RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI
Thanks, I hadn't seen those. I did find https://github.com/NVIDIA/NeMo-Guardrails earlier but haven't looked into it yet.
I'm not sure it solves the problem of restricting the information it uses though. For example, as a proof of concept for a customer, I tried providing information from a vector database as context, but GPT would still answer questions that were not provided in that context. It would base its answers on information that was already crawled from the customer website and in the model. That is concerning because the website might get updated but you can't update the model yourself (among other reasons).
- How do we prevent prompt injection in a GPT API app?
- Nvidia NeMo Guardrails – open-source guardrails to conversational systems
-
Should LangChain be used in Prod?
you can use guard rails with langchain - https://github.com/NVIDIA/NeMo-Guardrails
What are some alternatives?
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
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
lmql - A language for constraint-guided and efficient LLM programming.
langchainrb - Build LLM-powered applications in Ruby
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]
guidance - A guidance language for controlling large language models.
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.
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
basaran - Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
rasa - 💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.