771ac9c96c
The README feature list and the overview stopped at the analysis capability. Both examples and the app backend composed agents without the capabilities the documentation recommends alongside an evidence capability. custom_agent.py ran each input as an independent agent run, so it needed a state dict and a carried history before compaction could mean anything there: without state the evidence record is empty, and earlier evidence would reduce to receipts retaining nothing. |
||
|---|---|---|
| .. | ||
| docker | ||
| samples | ||
| custom_agent.py | ||
| custom_agent_agui.py | ||
| README.md | ||
haiku.rag Examples
This directory contains example scripts demonstrating various features of haiku.rag.
Docker Example
Directory: docker/
Complete Docker setup for running haiku.rag with all services:
- Continuous ingestion from a watched directory via
haiku-ingester - MCP server for AI assistant integration
See docker/README.md for setup instructions.
Custom Agent
Script: custom_agent.py
Uses the eagerly loaded RAG capability to build a conversational agent.
uv run python examples/custom_agent.py /path/to/db.lancedb
Custom Agent with AG-UI Streaming
Script: custom_agent_agui.py
A Starlette app that adapts a native RAG-capable agent to AG-UI.
DB_PATH=/path/to/db.lancedb uv run uvicorn examples.custom_agent_agui:app --reload --port 8000