← Open Source
n4ze3m

dialoqbase

Create chatbots with ease

ApplicationsProductivityTypeScript
Open on GitHub
Momentum
+0stars in 24 hours0.0%
1.79k
Stars
270
Forks
+-3
This week
12
Contributors
Created 2023-06-04 · Updated 2026-10-08 · #9459 today
Top developers
README

⚡Dialoqbase ⚡

Create chatbots with ease

Join dialoqbase #welcome Build Status License: MIT

[!IMPORTANT] Project status: Archived. This repository is archived and read-only — it is no longer actively developed and will not receive new features, issues, or pull requests. Forks are welcome if you'd like to continue the project. For critical security vulnerabilities, please email the maintainer; I may temporarily unarchive the repo to ship a fix.

Dialoqbase is an open-source application designed to facilitate the creation of custom chatbots using a personalized knowledge base. The application leverages advanced language models to generate accurate and context-aware responses. Additionally, it utilizes PostgreSQL, a robust relational database management system, for efficient vector search operations and for storing the knowledge base.

Here's a demo of how it works (v0.0.23):

DialoqBase Demo

Want to check more demo videos? Follow me on Twitter or BlueSky for more updates.

Quick Deployments 🚀

Railway (One-click deployment)

Deploy on Railway

Installation 🛠️

  1. Clone the repository and navigate to the docker directory:
git clone https://github.com/n4ze3m/dialoqbase.git
cd dialoqbase/docker
  1. Edit the .env :
  • On Linux:
nano .env

or

vim .env
  • On Windows:
notepad .env

Set the DB_SECRET_KEY varible.

  1. Run the docker-compose file:
docker-compose up -d

or

docker compose up -d
  1. Open your browser and go to http://localhost:3000.
  2. Log in using the default credentials:
username: admin
password: admin

Important: After the first login, remember to change the default credentials.

Features 🚀

  • Create custom chatbots with your own knowledge base
  • Utilize powerful language models to generate responses
  • Utilize PostgreSQL for vector search and storing the knowledge base.
  • Use any language models or embedding models you want

Stack 📚

Disclaimer ⚠️

Dialoqbase is a side project and is not ready for production. It is still in the early stages of development and may contain bugs and security issues. Use it at your own risk. Breaking changes may occur at any time without prior notice.

Roadmap 🗺️

Data loaders

Loader Status
Website ✅
Plain text ✅
PDF ✅
Web crawler ✅
Microsoft Word documents ✅
Github repository ✅
mp3 ✅
mp4 ✅
Sitemap ✅
Youtube ✅
Notion ❌

Language models

Provider Models
OpenAI gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, gpt-4-0613, gpt-3.5-instruct, gpt-3.5-turbo-1106, gpt-4-1106-preview
Anthropic Claude 1, Claude 2
Google chat-bison-001, Gemini
Fireworks Llama 2, Mistral, Mixtral and more
Local AI Local AI models
Ollama All Ollama supported models

Embedding models

Provider Models Status
OpenAI text-embedding-ada-002 ✅
TensorFlow universal-sentence-encoder ❌
Hugging Face distilbert-base-uncased ✅
Cohere Embed ✅
Huggingface Transformers.js all-MiniLM-L6-v2 ✅
Ollama Ollama embedding ✅
Google text-gecko-001, embedding-001 ✅
Jina Jina embedding ✅

need more ? create an issue...

Integrations

Type Stage Status
Web embed script stable ✅
Telegram beta ✅
Discord beta ✅
Slack development ❌
Whatsapp experimental ✅

need more ? create an issue...

This project is tested with BrowserStack.

Contributors ✨

Interested in contributing? Check out the contributing guide.

Sponsors 💖

Dialoqbase nothing without the support of our wonderful sponsors. If you are interested in becoming a sponsor, please visit the sponsorship page.

Wonderful Sponsors

And many more wonderful supporters from Ko-fi.

License 📝

MIT