Chipper AI/RAG Interface for Tinkerers (Ollama, Haystack RAG, Python)
Chipper AI/RAG Interface for Tinkerers (Ollama, Haystack RAG, Python)
I started this project as a way to help my girlfriend with her new book and to learn a bit about LLMs and RAGs. The idea was to use local embeddings to ask questions about characters and explore creative possibilities, all while keeping everything local. What began as a bunch of a wild colelction of scripts is now growing into a labour of love pet-project. You maybe know how it sometimes goes :) It's not finished and polished yet, but I've made some good progress and brought it to a much better overall state over Christmas day. I'd love to show it to a few people and get some feedback and contributors. Your thoughts could really help me improve it and make it even better.
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Incorrect prediction on native model
Similar products
Local RAG with Ollama, Gemma and RETSim
Vectorless RAG
PageIndex – Vectorless RAG
Preprocess maximises RAG performances
PyFilesystem 2.0 – A Python interface to filesystems of all kinds
A Python interface to splice(2) syscall
C implementation of Karpathy's micrograd and with a Python Interface
RAGLite – A Python package for the unhobbling of RAG
Local RAG Pipeline with Weaviate and Ollama
Private RAG with Mistral, Ollama and Pathway