Sign inSign up

batou9150/kb-studio

By batou9150

Updated 6 months ago

Knowledge base management app powering RAG-based AI Agents for non-technical users

Image
Machine learning & AI
1

1.2K

batou9150/kb-studio repository overview

KB-Studio

KB-Studio is a web application designed to allow non-technical users to manage a knowledge base for RAG (Retrieval-Augmented Generation) systems within AI conversational agents.

Installation

docker run -p 8080:8080 \
  -e GCS_BUCKET_NAME=my-bucket \
  -e GOOGLE_CLOUD_PROJECT=my-project \
  -e GEMINI_API_KEY=my-key \
  -e APP_NAME="My Knowledge Base" \
  -e APP_LOGO="https://example.com/logo.png" \
  batou9150/kb-studio

The application is accessible at http://localhost:8080.

VariableDescriptionDefault
GCS_BUCKET_NAMEGoogle Cloud Storage bucket namekb-studio-bucket
GOOGLE_CLOUD_PROJECTGoogle Cloud project ID
GEMINI_API_KEYGemini API key
APP_NAMECustom application nameKB-Studio
APP_LOGOCustom logo URL

Deploy to Google Cloud Run

gcloud run deploy kb-studio \
  --image docker.io/batou9150/kb-studio:latest \
  --region REGION \
  --platform managed \
  --no-allow-unauthenticated \
  --iap \
  --set-env-vars GCS_BUCKET_NAME=my-bucket \
  --set-env-vars GOOGLE_CLOUD_PROJECT=my-project \
  --set-env-vars GEMINI_API_KEY=my-key \
  --set-env-vars APP_NAME="My Knowledge Base" \
  --set-env-vars APP_LOGO="https://example.com/logo.png"

Replace REGION with your preferred region (e.g., europe-west1).

Tip: For sensitive values like GEMINI_API_KEY, consider using Secret Manager instead of plain environment variables.

Tag summary

Content type

Image

Digest

sha256:1e222f3a6

Size

157.4 MB

Last updated

6 months ago

docker pull batou9150/kb-studio