haiku.rag/haiku_rag_slim/haiku/rag
2026-04-20 11:38:09 +03:00
..
agents use MontyRepl for persistent variables across execute_code calls 2026-04-20 10:47:50 +03:00
chat flatten skill architecture: replace ask/analyze/research with direct tools 2026-04-17 18:35:17 +03:00
chunkers enable repeat_table_header for self-contained table chunks and docling-serve parity 2026-03-26 14:02:12 +02:00
config rename RLM agent to analysis throughout the codebase 2026-04-17 18:32:01 +03:00
converters Update docling, docling-core and move to version 1.10.0 of DoclingDocument. 2026-03-23 17:34:06 +02:00
embeddings Add batching to embeddings for huge documents 2026-04-07 12:06:28 +03:00
inspector extract get_database_stats and share it across info, inspector, and backend 2026-04-17 15:33:30 +03:00
providers
reranking Jina uses AutoModel not AutoModelForSequenceClassification 2026-01-21 11:26:23 +02:00
skill_generator Remove documents from state, fix tests 2026-04-20 09:48:18 +03:00
skills Improve analysis SKILL.md 2026-04-20 11:38:09 +03:00
store extract get_database_stats and share it across info, inspector, and backend 2026-04-17 15:33:30 +03:00
tools remove filter parameter from analyze skill tool and clean up unused filter helpers 2026-04-17 18:35:16 +03:00
__init__.py
app.py rename RLM agent to analysis throughout the codebase 2026-04-17 18:32:01 +03:00
cli.py add --skill flag to chat TUI for rag and analysis skills 2026-04-17 18:35:16 +03:00
client.py use MontyRepl for persistent variables across execute_code calls 2026-04-20 10:47:50 +03:00
context.py preserve original chunk when expansion produces less content 2026-04-16 12:11:54 +03:00
logging.py
mcp.py rename RLM agent to analysis throughout the codebase 2026-04-17 18:32:01 +03:00
monitor.py
utils.py deduplicate escape_sql_string into utils 2026-04-16 12:11:53 +03:00