Logo
Deploy Now

SaaS Alternative

Chatbase CustomGPT Botsonic SiteGPT

Categories

Self-Hosted AI LLM No-Code Knowledge Base Chatbot Customer Support RAG

Stars

1793

Forks

274

Watchers

27

Developer links

Last Updated: 07-04-2026 12:04 AM (UTC)

Dialoqbase

Retrieval-augmented chatbots on your own knowledge base - that is the whole mission of Dialoqbase, an open-source bot-building platform. Feed it content through a broad set of data loaders - web pages and full crawls, sitemaps, PDFs, DOCX, CSV, plain text, GitHub repositories, YouTube videos, and MP3/MP4 audio - and it handles the whole RAG pipeline in one self-contained app: chunking, embedding, vector storage, and LLM querying. The distinguishing architecture choice is PostgreSQL with pgvector for embedding storage and similarity search, which removes the separate vector-database dependency, and Redis-backed Bull queues for ingesting large documents without blocking the API. Model choice is wide open: OpenAI, Anthropic Claude, Google Gemini, Cohere, Fireworks, Hugging Face, local models via Ollama, and any OpenAI-compatible endpoint, with an equally broad list of embedding providers. Finished bots embed on any website with customizable styling or deploy to Telegram, Discord, and WhatsApp, and an API creates and manages bots programmatically. Multi-user support adds registration limits and per-user bot quotas. MIT-licensed and free for commercial use.

Dialoqbase
Dialoqbase

Benefits

  • No Per-Message Pricing
  • Hosted chatbot builders meter messages and characters of training data. Self-hosted Dialoqbase serves unlimited conversations at hosting plus raw model cost.
  • One Database, Not Two
  • pgvector keeps embeddings inside PostgreSQL, so there is no Pinecone or Weaviate subscription and no second data store to operate and back up.
  • Your Documents Stay Private
  • Internal wikis, support docs, and product manuals are ingested and stored on your own server - nothing uploads to a chatbot vendor's cloud.
  • Swap Models Freely
  • OpenAI today, Claude tomorrow, a local Ollama model for sensitive bots - provider choice is per bot, including any OpenAI-compatible endpoint.

Features

  • Rich Data Loaders
  • Web pages, crawls, sitemaps, PDF, DOCX, CSV, text, GitHub repos, YouTube, and MP3/MP4 audio ingestion.
  • pgvector Search
  • Embeddings stored and queried in PostgreSQL - fast similarity search without an external vector database.
  • Multi-Provider Models
  • OpenAI, Anthropic, Google, Cohere, Fireworks, Hugging Face, Ollama, and custom OpenAI-compatible endpoints for both chat and embeddings.
  • Multi-Channel Deployment
  • Embed on websites with custom styling or run the same bot on Telegram, Discord, and WhatsApp.
  • Queue-Based Ingestion
  • Redis-backed Bull queues process large document sets in the background without blocking the app.
  • Multi-User Administration
  • Registration controls and per-user bot quotas for running a shared instance, plus an API for programmatic bot management.