chatblade VS ollama

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

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

Mot the op but I use chatblade[0] on the cli and chatgpt-next-web[1] as webgui.

[0] https://github.com/npiv/chatblade

[1] https://github.com/Yidadaa/ChatGPT-Next-Web/

But something like https://github.com/npiv/chatblade/ makes it easy to call from the command line, without programming experience. I find it handier to quickly connect to other parts of my workflow.

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.

- Basic internet search (I start ollama CLI faster than I can start a browser - https://ollama.com)

- Formatting/changing text

- Troubleshooting code, esp. new frameworks/libs

- Recipes

- Data entry

- Organizing thoughts: High-level lists, comparison, classification, synonyms, jargon & nomenclature

- Learning esp. by analogy and example

RAG for:

- Website assistants (https://github.com/bennyschmidt/ragdoll-studio/tree/master/e...)

- Game NPCs (https://github.com/bennyschmidt/ragdoll-studio/tree/master/e...)

- Discord/Slack/forum bots (https://github.com/bennyschmidt/ragdoll-studio/tree/master/e...)

- Character-driven storytelling and creating art in a specific style for video game loading screens, background images, avatars, website art, etc. (https://github.com/bennyschmidt/ragdoll-studio/tree/master/r...)

Jan goes a step further by integrating with other local engines like LM Studio and ollama.

# install the Ollama curl -fsSL https://ollama.com/install.sh | sh # get the llama3 model ollama pull llama2 # install the MLFlow pip install mlflow

Ollama for running LLMs locally

curl -fsSL https://ollama.com/install.sh | sh

Streaming is not a problem (it's just a simple flag: https://github.com/wiktor-k/llama-chat/blob/main/index.ts#L2...) but I've never used voice input.

The examples show image input though: https://github.com/ollama/ollama/blob/main/docs/api.md#reque...

Maybe you can file an issue here: https://github.com/ollama/ollama/issues

I’m a huge fan of open source models, especially the newly release Llama 3. Because of the performance of both the large 70B Llama 3 model as well as the smaller and self-host-able 8B Llama 3, I’ve actually cancelled my ChatGPT subscription in favor of Open WebUI, a self-hostable ChatGPT-like UI that allows you to use Ollama and other AI providers while keeping your chat history, prompts, and other data locally on any computer you control.