AllyCat is full stack, open source chatbot that uses GenAI LLMs to answer questions about your website. It is simple by design and will run on your laptop or server.
AllyCat is purposefully simple so it can be used by developers to learn how RAG-based GenAI works. Yet it is powerful enough to use with your website, You may also extend it for your own purposes.
⭐ Found this tool helpful? Give it a star on GitHub to support the project and help others discover it!
🗞️ Allycat news - releases and new features!
AllyCat uses your choice of LLM and vector database to implement a chatbot written in Python using RAG architecture. AllyCat also includes web scraping tools that extract data from your website (or any website).
- Web crawler to download content from website
- HTML processing/cleanup, text extraction and conversion to markdown. Uses Docling
- Chunking, vector embedding creation, saving to vector database. Uses Llama Index and Granite Embedding Model
- Supports multiple vector databases. Milvus or Weaviate
- Use local LLMs using Ollama or use any inference service. Uses LiteLLM
- Chatbot with interface to answer questions with text scraped from a website.
- End User and New Contributor Friendly.
- Entity & Relationship Extraction - Automatically identifies key entities and their relationships
- Community Detection - Uses Louvain algorithm to discover knowledge communities
- Graph Database Integration - Stores knowledge graph in Neo4j
- 7-Phase Query System - Advanced query processing with query-aware ranking
- Hybrid Search - Combines vector search with graph traversal for better answers
- Multiple Deployment Options - Local (Ollama) or Cloud (Nebius/OpenAI)
- Docker Ready - Full containerized setup with auto-pipeline
You can run allycat in following settings:
| Setup | Stack | Description |
|---|---|---|
| RAG (local) | Milvus (DB) + Ollama (LLMs) | Everything runs locally. No API keys needed. |
| RAG (remote) | Milvus (DB) + models running on the cloud | All models are running on cloud. API keys are required |
| GraphRAG (local) | Neo4j + Milvus + Ollama | Full GraphRAG with local infrastructure. Heavy but private. |
| GraphRAG (cloud) | Neo4j Aura + Zilliz + Nebius | Full GraphRAG with cloud services. Lightweight and scalable. |
See deployment guide
Originally AllianceChat, we shortened it to AllyCat when we learned chat means cat in French. Who doesn't love cats?!