GOgourneau·Sep 9, 2024
I have used https://github.com/lastmile-ai/aiconfig to encode some of my more common prompts into application like things. You can encode them into a yaml/json file.
In Ask HN: How do you manage your prompts in ChatGPT?lastmile-ai
aiconfig
Python2023–2024
lastmile-ai / aiconfig
aiconfig
AIConfig is a config-based framework to build generative AI applications.
4Distinct people
9Mentions
0Explicit recommenders
1.1KGitHub stars
What to know before exploring
What it is
AIConfig is a config-based framework to build generative AI applications.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by month9 dated mentions
Observed mentions: 2023-11-17 17:06:37 UTC to 2024-09-09 23:02:50 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Nov 2023 | 2023-11-01 00:00:00 UTC | 2023-12-01 00:00:00 UTC | 2 | 1 | 1 |
| Dec 2023 | 2023-12-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 3 | 1 | 2 |
| Jan 2024 | 2024-01-01 00:00:00 UTC | 2024-02-01 00:00:00 UTC | 0 | 0 | 0 |
| Feb 2024 | 2024-02-01 00:00:00 UTC | 2024-03-01 00:00:00 UTC | 2 | 1 | 1 |
| Mar 2024 | 2024-03-01 00:00:00 UTC | 2024-04-01 00:00:00 UTC | 1 | 0 | 1 |
| Apr 2024 | 2024-04-01 00:00:00 UTC | 2024-05-01 00:00:00 UTC | 0 | 0 | 0 |
| May 2024 | 2024-05-01 00:00:00 UTC | 2024-06-01 00:00:00 UTC | 0 | 0 | 0 |
| Jun 2024 | 2024-06-01 00:00:00 UTC | 2024-07-01 00:00:00 UTC | 0 | 0 | 0 |
| Jul 2024 | 2024-07-01 00:00:00 UTC | 2024-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 2024 | 2024-08-01 00:00:00 UTC | 2024-09-01 00:00:00 UTC | 0 | 0 | 0 |
| Sep 2024 | 2024-09-01 00:00:00 UTC | 2024-10-01 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
9 sourcesdoesn't collect prompts and there's a way to disable telemetry as well - https://github.com/lastmile-ai/aiconfig/blob/8a5a59d47cef474...
In AIConfig Extension for VS CodeYou can! We artificially limited that in the gradio notebook component right now, but if you check out the core package it’s built on (aiconfig), it shows how to use OpenAI, Claude, and other model providers:
https://github.com/lastmile-ai/aiconfig
Here’s the currently supported list of models: https://aiconfig.lastmileai.dev/docs/overview/model-parsers
Let me know if we should enable non-HF models in the gradio notebook component by default as well — it should be a simple change
In Show HN: Gradio Notebook– Notebook UX for Generative AI models in Hugging FaceShow HN: Gradio Notebook– Notebook UX for Generative AI models in Hugging Face
TLDR: Gradio Notebook is a notebook component for generative AI that offers the fastest way to create a Hugging Face space (in < 10 lines of code), and a familiar notebook interface for interacting with any combination of text, image and audio models in a single space. Follow this Quickstart to create a gradio notebook for yourself:
https://huggingface.co/spaces/lastmileai/gradio-notebook-template
Hi HN Community!
I’m Sarmad, co-founder of LastMile AI, and today I’m excited to share Gradio Notebook, our latest open-source project in collaboration with Hugging Face. Gradio Notebook [1] is a notebook component that offers an interactive playground for Hugging Face models of any modality in a single Hugging Face space. It brings the familiar UX of a notebook to generative AI model inference, and enables much richer interactions than a chat i
Read the rest
nterface allows.
If you're a Hugging Face space creator looking for speed and ease of development, Gradio Notebook gets your space ready in 5 minutes with < 10 lines of code (without having to build your own UI at all).
Key features:
* Use any combination of text, image, or audio models in a single space, and even chain models together.
* Interact and experiment with models using a pre-built notebook UI, which is a familiar, intuitive interface for multimodal interaction. At its core, the notebook contains cells (we call them “prompts”), which are associated with a model to run.
* Get a shareable URL to share the space outputs with others (my personal favorite feature, since it isn’t possible on HF today).
* Download your space config (prompts and model settings) as a JSON file, and use it in your application via our SDK [2].
This is a new user experience for generative AI, and for Hugging Face, and we are looking for feedback. If you frequently use HF spaces, and especially if you like to build spaces, please give this a try and get in touch!
Excited to hear from you, and looking forward to seeing what you create with Gradio Notebook!
To get started, please use the Quickstart [1], which contains everything to set up and play with the component
[1] Link to Quickstart:
https://huggingface.co/spaces/lastmileai/gradio-notebook-template
[2] SDK:
https://aiconfig.lastmileai.dev/docs/gradio-notebook#gradio-notebook-api
[3] Gradio Notebook Docs:
https://aiconfig.lastmileai.dev/docs/gradio-notebook
[4] Repo (it’s all open source):
https://github.com/lastmile-ai/aiconfig/tree/main/gradio-notebook
Take a look at https://github.com/lastmile-ai/aiconfig for refactoring your prompt management - https://github.com/aymenfurter/microagents/tree/main/prompt_...
In Show HN: Microagents: Agents capable of self-editing their prompts / Python codeHappy to answer any questions on the approach here! One thing I was slightly disappointed by was the instruction fine-tuning of LLaMA Guard was good for conversations, but not for declarative statements. So framing things as questions flagged the safeguards, but other styles of interactions didn't.
I wonder if it'll be better with LLaMA-13B instead of 7B.
Also link doesn't render nicely in the text above -- here it is: https://github.com/lastmile-ai/aiconfig/tree/main/cookbooks/...
In Show HN: Use Purple LLaMA to test ChatGPT safeguardsShow HN: Use Purple LLaMA to test ChatGPT safeguards
I spent some time this weekend playing with LLaMA Guard, a fine-tuned LLaMA-7B model by Meta that lets you add guardrails around generative AI. I recorded a quick demo showing what it does and how to use it.
The best part is that you can define your own “safety taxonomy” with it — custom policies for what is safe vs unsafe interactions between humans (prompts) and AI (responses).
I wanted to see how “safe” conversations with OpenAI’s ChatGPT were, so I ran a bunch of prompts (a mixture of innocuous and inappropriate) and asked LLaMA Guard to classify the interactions as safe/unsafe.
My key takeaways from the exercise:
1. OpenAI has done a good job of adding guardrails for its models. LLaMA Guard helped confirm this.
2. What makes this really cool is I may have a very specific set of policies I want to enforce ON TOP of the standard guardr
Read the rest
ails that a model ships with. LLaMA Guard makes this possible.
3. This kind of model chaining — passing responses from OpenAI models to LLaMA is becoming increasingly common, and I think we’ll have even more complex pipelines in the near future. It helped to have a consistent interface to store this multi-model pipeline as a config, especially because that same config also contains my safety taxonomy.
Try it out yourself:
GitHub: https://github.com/lastmile-ai/aiconfig/tree/main/cookbooks/LLaMA-Guard
Colab: https://colab.research.google.com/drive/1CfF0Bzzkd5VETmhsniksSpekpS-LKYtX
YouTube: <https://www.youtube.com/watch?v=XxggqoqIVdg>
Would love the community's feedback on the overall approach.
We have a bit of context about this in the readme: https://github.com/lastmile-ai/aiconfig#what-problem-it-solv.... The main issue with keeping it in code is that it tangles application code with prompts and model-specific logic.
That makes it hard to evaluate the genAI parts of the application, and also iterating on the prompts is not as straightforward as opening up a playground.
Having the config be the source of truth let's you connect it to your application code (and still source controlled), lets you evaluate the config as the AI artifact, and also lets you open the config in a playground to edit and iterate.
For example, compare how much simpler openai function calling becomes with storing the stuff as a config: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/... vs using vanilla openai directly (https://github.com/open
Read the rest
AIConfig – source control format for gen AI prompts, models and settings
97 points · Open discussion