https://github.com/humankernel/rag-next-langchain
Retrieval Augmented Generation
https://github.com/humankernel/rag-next-langchain
Last synced: 15 days ago
JSON representation
Retrieval Augmented Generation
- Host: GitHub
- URL: https://github.com/humankernel/rag-next-langchain
- Owner: humankernel
- Created: 2024-05-15T02:36:08.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-06-15T21:29:21.000Z (about 2 years ago)
- Last Synced: 2025-04-27T05:19:03.497Z (about 1 year ago)
- Language: TypeScript
- Size: 7.17 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 📃 RAG - Next + Langchain
This is a RAG app. In other words a chatbot with a local modal that response using your documents an only your documents
## Getting Started
### Start Ollama
```sh
# create the model
ollama create -f '.\Modelfile - Llama2'
# the machine that runs ollama have to set this env variables
OLLAMA_HOST = 0.0.0.0
OLLAMA_ORIGINS = *
OLLAMA_KEEP_ALIVE = 30
# run ollama
ollama serve
```
### Start Postgres (pg-vector)
```sh
# download pv-vector (w/ vpn)
docker pull ankane/pgvector:latest
# move to project folder
docker compose up -d
```
### Start webpage
```sh
pnpm dev
# or
pnpm dev --turbo
# or
npx next dev --turbo
```
## Backups
```sh
# install cron, rsync in archlinux
sudo pacman -S cronie rsync
# Para programar la ejecución diaria de tu script, edita el archivo crontab:
crontab -e
# Esto le dice a cron que ejecute el script backup_incremental.sh todos los dÃas a las 2:00 AM.
0 2 * * * /ruta/a/tu/script/backup.sh
```