Community blog
-
3 different ways to change system prompt in the Cat
The system prompt in LLM based agents is the prompt main part, the one defining who the bot is, its main task and tone of voice.In the Cheshire Cat we call it prompt_prefix, with this… Read more
-
Cheshire Cat in the Cloud – Simply deploy to AWS with CDK
Explore the step-by-step process of deploying Cat on an AWS environment using the AWS CDK framework in this detailed guide.From configuring the environment to releasing your own version of the cat on the cloud. CAUTION… Read more
-
Voicing the Cheshire Cat
A multi-container application that allows the Cheshire Cat to talk! Giving voice to your favorite chatbot can increase the quality of the interaction by introducing a high degree of personalization to it.In this tutorial we… Read more
-
Gentle introduction to Cheshire Cat Vector Search
TL;DRIn previous articles, we have seen how you navigate the vector space, know the memories, export them, … and how these are handled by the Cheshire Cat so as not to run into mistakes.In this… Read more
-
How to use Cheshire Cat behind NGINX
Startup guide with a basic setup to deploy the Cheshire Cat behind a reverse proxy with Nginx. In a production environment you would use Nginx in order to manage access to a specific resource, like… Read more
-
How to Install Cheshire Cat on Raspberry Pi 4
Greetings! In this whimsical guide, we’re about to embark on a journey to make the enigmatic Cheshire Cat come to life on your Raspberry Pi. Brace yourself as we go through the magical steps of… Read more
-
How to Setup a Local Embedder with Fastembed
Easy-to-use setup to run a local embedder model with FastEmbed Commonly, language models (i.e. chat and completion models) like GPTs, LLaMa, Mistral and so on get most of the attention. However, the so-called embedder models… Read more
-
The catSCII artist plugin
A simple plugin to ask the cat for a fact and enjoy it in ASCII art. Learn new stuff everyday with your favorite cat |\ _,,,—,,_ ZZZzz /,`.-‘`’ -. ;-;;,_ |,4- ) )-,_. ,\ (… Read more
-
The Drunken Cat Effect
In the first article about Vector Memory, we talked about: Today, we are going to focus on the last point. Specifically, we are going to see why, when we share memories, the starting embedder must… Read more
-
How to Run a Local Model with Ollama
Easy-to-use setup to extend the Cheshire Cat Docker configuration and run a local model with Ollama. If you’re interested in having the Cheshire Cat running a local Large Language Model (LLM), there are a handful… Read more