haiku.rag/src/haiku/rag
2025-09-19 17:25:04 +03:00
..
embeddings Fix missing vllm embeddings from embedder factory 2025-09-09 10:58:41 +03:00
qa Simplify structured output for research agents 2025-09-17 18:31:55 +03:00
reranking Research agent as a pydantic graph 2025-09-19 14:39:39 +03:00
research Cleanup console logging 2025-09-19 17:25:04 +03:00
store Upgrade fts index for phrase queries 2025-09-19 12:06:12 +03:00
__init__.py
app.py Cleanup console logging 2025-09-19 17:25:04 +03:00
chunker.py Operate on DoclingDocument instead of Document 2025-08-08 17:24:34 +02:00
cli.py Set default concurrency to 1 2025-09-19 16:54:06 +03:00
client.py Upgrades are back. Make chunk order a table column rather than a metadata property 2025-09-18 13:42:07 +03:00
config.py Change default config to use gpt-oss for QA 2025-09-17 12:39:58 +03:00
logging.py Suppress warnings in cli 2025-09-10 13:36:12 +03:00
mcp.py Basic moving to lancedb. 2025-09-01 14:56:14 +03:00
migration.py vacuum() in store, client, cli. Removes old versions and reduces disk usage 2025-09-10 11:24:51 +03:00
monitor.py
reader.py Operate on DoclingDocument instead of Document 2025-08-08 17:24:34 +02:00
utils.py Allow for custom pre-processing after markdown is generated and before it is chunked. 2025-09-15 11:02:34 +03:00