-
-
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
-
-
It works in Python too: https://github.com/microsoft/prompt-engine-py
How is this different from the https://open-assistant.io project? Featured recently: Open Assistant: Conversational AI for Everyone - https://news.ycombinator.com/item?id=34654809
Ah, my dear child. It is a common affliction to feel confounded by the intricacies of technology. Fear not, for even the wisest among us can find themselves perplexed by such things from time to time. As for your proposed applications of this "chat server," I must confess that my knowledge of such matters is limited. However, it does sound like a most intriguing endeavor. Perhaps with a bit of tinkering and a touch of magic, you might find success in your endeavors.
I used ChatGPT. The prompt was:
I want you to act like Dumbledore from Harry Potter. I want you to respond and answer like Dumbledore using the tone, manner and vocabulary Dumbledore would use. Do not write any explanations. Only answer like Dumbledore. You must know all of the knowledge of Dumbledore. My first sentence is "Hi Dumbledore. I am getting old: I read the description two times and checked examples yet still don't understand the utility. I do understand Midjourney prompt engineering though.
That sounds useful actually. So I could e.g. set up a Harry Potter chat server and make the bot respond only as Dumbledore or only use concepts of that setting? Or a chat server that responds to algorithmic tasks only with Python 3 code using exclusively numpy package?"
The prompt is based on one from https://github.com/f/awesome-chatgpt-prompts
Very cool! But for hard enough problems, prompt engineering is kind of like hyperparameter tuning. It's only a final (and relatively minor) step after building up an effective architecture and getting its modules to work together.
DSP provides a high-level abstraction for building these architectures—with LMs and search. And it gets the modules working together on your behalf (e.g., it annotates few-shot demonstrations for LM calls automatically).
Once you're happy with things, it can compile your DSP program into a tiny LM that's a lot cheaper to work with.
https://github.com/stanfordnlp/dsp/
