DnD Campaign Chatbot

A self-hosted RAG (Retrieval Augmented Generation) chatbot for querying D&D campaign notes. Polish-language content.

Features

• Hybrid search: BM25 (keyword) + vector (semantic) with RRF fusion and optional cross-encoder reranking
• Contextual prefixes: LLM-generated chunk context for better retrieval (Anthropic technique)
• Auto-indexing: Watches content directory, incrementally indexes new/modified markdown files
• REST API: Fast context endpoint for external integrations (used by Nanobot Telegram bot)
• Web UI: Chainlit chat interface with streaming responses
• Polish language: Optimized for Polish content with wiki-link parsing

Architecture

Markdown files (dnd-summaries/content/)
        |
        v
   +---------+    contextual     +--------+
   |  ingest  |---prefixes (LLM)-| Ollama |
   |          |    embeddings     |(remote)|
   +----+-----+                  +--------+
        |
        v
   +----------+
   | ChromaDB |  (vector store, port 8100 external / 8000 internal)
   +----+-----+
        |
        v
   +----------+    hybrid search    +--------+
   |   chat   |----LLM response----| Ollama |
   |(Chainlit|    (streaming)      |(remote)|
   |+FastAPI) |                     +--------+
   +----------+
     port 7860

Three Docker Compose services:

Service	Container	Port	Role
chromadb	dnd-chromadb	8100:8000	Vector store (persistent on NAS)
ingest	dnd-ingest	—	Indexes markdown, watches for changes
chat	dnd-chat	7860:7860	Web UI + REST API

Quick Start

1. Configure

cp .env.example .env

Edit .env:

CONTENT_PATH=/path/to/your/markdown/content
OLLAMA_BASE_URL=http://your-ollama-host:11434
LLM_MODEL=SpeakLeash/bielik-11b-v3.0-instruct:Q4_K_M
EMBEDDING_MODEL=bge-m3

2. Start

docker compose up -d

3. Use

• Web UI: http://localhost:7860
• Context API: http://localhost:7860/api/context?q=your+question
• Query API: http://localhost:7860/api/query?q=your+question
• Health: http://localhost:7860/api/health

Configuration

All settings via .env file:

Variable	Default	Description
CONTENT_PATH	./_content	Path to markdown files
OLLAMA_BASE_URL	http://ollama:11434	Ollama server URL
LLM_MODEL	gemma3:12b	Model for chat and contextual prefixes
EMBEDDING_MODEL	bge-m3	Model for embeddings
RETRIEVER_K	6	Number of context chunks to retrieve
CHUNK_SIZE	1000	Text chunk size for indexing
CHUNK_OVERLAP	200	Overlap between chunks
RERANKER_ENABLED	false	Enable cross-encoder reranking (slower, more precise — useful for large corpora)

RAG Pipeline

1. Ingestion (ingest.py): Markdown → chunks → contextual prefixes via LLM (cached) → embeddings via bge-m3 → ChromaDB
2. Retrieval (retriever.py): BM25 + vector search → RRF fusion → optional cross-encoder reranking (bge-reranker-v2-m3, off by default)
3. Generation (chat.py): Retrieved chunks as context → LLM streaming response

API Endpoints

Endpoint	Speed	Description
GET /api/context?q=...	~1.5s	RAG chunks only, no LLM — for external integrations
GET /api/query?q=...	~30-40s	Full LLM-generated answer with sources
GET /api/health	instant	Health check

Content Format

Pattern	Type	Example
DD.MM.YYYY.md	Session notes	15.11.2025.md
postacie/*.md	Character	Thok Darkhide.md
lokacje/*.md	Location	Luskan.md

Wiki-links ([[Name]] and [[Name|Display]]) are resolved during ingestion.

Commands

# Start
docker compose up -d

# Logs
docker compose logs -f chat
docker compose logs -f ingest

# Rebuild after code changes
docker compose build && docker compose up -d

# Force full reindex (delete ChromaDB collection)
curl -X DELETE http://localhost:8100/api/v2/tenants/default_tenant/databases/default_database/collections/dnd_campaign
docker compose restart ingest

# Stop
docker compose down

Development

# Run locally (needs Ollama + ChromaDB running)
uv run python ingest.py
uv run python chat.py

# Lint
uv run ruff check .

License

MIT