chatblade

https://github.com/npiv/chatblade Basically GPT on the command line. I had my own, but chatblade is just prettier. I thought with the ChatGPT subscriptions I wouldn't have to use it anymore, but there's just a lot of raw searches that the API does much better than the chat. Recent example is how to access new fonts from mac's Pages app, both Google and ChatGPT gave incorrect answers on top.

Those are great links. I’ve been using: https://github.com/npiv/chatblade https://github.com/tbckr/sgpt I totally agree with LLM+CLI are perfect fit. One pattern I used recently was httrack + w3m dump + sgpt images with gpt vision to generate a 278K token specific knowledge base with a custom perl hack for a RAG that preserved the outline of the knowledge. Which brings me to my question for you - have you seen anything unix philosophy aligned for processing inputs and doing RAG locally? EDIT. Turns out OP has done quite a bit toward what I’m asking. Written up here: https://simonwillison.net/2023/Oct/23/embeddings/ Something I’m currently a bit hung up on is finding a toolchain for chunking content on which to create embeddings. Ideally it would detect location context, like section “2.1 Failover” or “Chapter 8: The dream” or whatever fro

Chatblade is another good one: https://github.com/npiv/chatblade

If you're using ChatGPT Plus only for GPT-4, you can get it cheaper via the API. I use it quite a bit - doing PRs, writing code, stories, hackathons, asking step by step instructions on how to do things. It cost me $3 last month. You can use the OpenAI playground, build your own chat interface, ask GPT to build it for you, but I just use Chatblade: https://github.com/npiv/chatblade

Made one myself, then found this on HN and have been using it since: https://github.com/npiv/chatblade Some say it's because it's not free, but it just feels good

Not the op but I use chatblade[0] on the cli, chatgpt-next-web[1] as webgui and quivr[2] for multimodal stuff files/images/audio/video. atm everything goes over a azure openai endpoint but would love to infere an llm locally. [0] https://github.com/npiv/chatblade [1] https://github.com/Yidadaa/ChatGPT-Next-Web/ [2] https://github.com/StanGirard/quivr

CLI: https://github.com/npiv/chatblade

https://github.com/npiv/chatblade this has built in history and lots of other features that a serious user needs, like checking token limits and estimating costs, etc.

Its not doing anything special that could "trash" the input. In fact no other env variables are read at all. So the fact that you are seeing your email, is a pretty strong indication that it is being set by you somewhere. Where else could it even get it from? An other option is that you passed your email as a parameter mistakingly (which takes precedence over the env variable) But the code is really pretty simple. https://github.com/npiv/chatblade/blob/4ce28739ca7ada1611029...

integrate chatGPT into your scripts or terminal work. Supports piping text, saving prompts, estimating costs, and some basic json/yaml extraction. I've added some elaborate examples on the readme of how to use it with pictures, that may provide a better overview.