phasellm
cuttlefish
phasellm | cuttlefish | |
---|---|---|
14 | 6 | |
443 | 86 | |
- | - | |
8.9 | 7.5 | |
3 months ago | about 1 year ago | |
Python | TypeScript | |
MIT License | Mozilla Public License 2.0 |
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.
phasellm
-
Ask HN: Any recommended AI tools to analyze data and generate insights?
If you're looking for an open source solution you can customize, check out the ResearchLLM demo: https://phasellm.com/researchllm
Code: https://github.com/wgryc/phasellm/tree/main/demos-and-produc...
- PhaseLLM Eval: run batch LLM jobs and evals via visual front-end (MIT licensed)
-
To everyone who is using alternative bots (e.g. Claude) - your comparisons?
Using Claude, Cohere, GPT-4, OpenAssistant. Formally swapping between them using PhaseLLM (open source library similar to LangChain).
-
April 2023
Large language model evaluation and workflow framework from Phase AI. (https://github.com/wgryc/phasellm)
- Ask HN: Freelancer? Seeking freelancer? (June 2023)
-
ResearchGPT: Automated Data Analysis and Interpretation
Fantastic questions! Re: working/not working at times -- this is still an issue. It's why I'm building PhaseLLM more broadly (https://github.com/wgryc/phasellm) -- need a robust pipeline that can also "reset" parts of itself if an LLM makes errors or mistakes.
You can see my prompts in this file: https://github.com/wgryc/phasellm/blob/main/demos-and-produc... I autogenerate a fairly big starting prompt and keep resubmitting it. It describes the data set extensively, which helps quite a bit.
That being said, a lot more can be done here around prompt optimization + making this more robust.
- ResearchGPT: LLMs to write stats code, analyze, and interpret results for you
-
Best way to use GPT offline with own content?
That being said, you might want to actually run head-to-head tests between models. PhaseLLM (free, open source) allows you to build a workflow and plug and play various models (including Dolly 2.0 and GPT-4). Then you can run tests to see how much worse/better the various LLMs are and if that's acceptable for your use case.
-
12-Apr-2023 AI Summary
Large language model evaluation and workflow framework from Phase AI. (https://github.com/wgryc/phasellm)
- PhaseLLM: Standardized Chat LLM API (Cohere, Claude, GPT) + Evaluation Framework
cuttlefish
-
ResearchGPT: Automated Data Analysis and Interpretation
I made something vaguely similar for your local terminal[0].
The idea is to give you a chat with an assistant that can use local tooling. Here it's Python for data analysis, I went more in the direction of "give it access to your terminal, so it can answer questions / do tasks on your local machine" which is something web-based options can't do right now.
I.e. ask it about your system details (processes, wifi) or to do things (configure something). Have it run the relevant commands, analyze the output, and respond either in natural language or i.e. a chart.
It's a really cool area of putting AI in a feedback loop (langchain-like), which I think is where the magic happens, and where we'll see much more happening in the future.
[0]:https://github.com/cube2222/cuttlefish
- Cuttlefish – Desktop ChatGPT-based Assistant that uses Tools
- Cuttlefish – Desktop ChatGPT-based Assistant that uses your Terminal
- Show HN: Cuttlefish – Desktop ChatGPT app that uses your Terminal
What are some alternatives?
awesome-chatgpt - 🧠 A curated list of awesome ChatGPT resources, including libraries, SDKs, APIs, and more. 🌟 Please consider supporting this project by giving it a star.
gdansk-ai - 🦭 Full stack AI voice chatbot (speech-to-text, LLM, text-to-speech) with integrations to Auth0, OpenAI, Google Cloud and Stripe - Web App, Web API and AI API
telegram-chatgpt-concierge-bot - Interact with OpenAI's ChatGPT via Telegram and Voice.
E2B - Secure cloud runtime for AI apps & AI agents. Fully open-source.
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
OpenAI-DotNet - A Non-Official OpenAI RESTful API Client for DotNet
rel-events - The relevant React Events Library.
promptsandbox.io - user-friendly visual canvas for creating chatbots powered by OpenAI APIs with no-code
kivy - Open source UI framework written in Python, running on Windows, Linux, macOS, Android and iOS
botpress - The open-source hub to build & deploy GPT/LLM Agents ⚡️
prompt-engineering - ChatGPT Prompt Engineering for Developers - deeplearning.ai
chatgpt-prompts - A NodeJS ChatGPT prompts library that contains more than 140+ awesome prompts