haiku.rag/haiku_rag_slim/haiku/rag
2025-12-08 15:55:30 +02:00
..
chunkers Drop ChunkWithMetadata, use good old Chunk 2025-12-08 15:55:30 +02:00
config Use EmbeddingModelConfig similar to ModelConfig for embeddings 2025-12-02 11:55:31 +02:00
converters Always generate page images, default in docling-serve 2025-12-08 15:54:57 +02:00
embeddings Use EmbeddingModelConfig similar to ModelConfig for embeddings 2025-12-02 11:55:31 +02:00
graph Avoid citation meta inside LLM context 2025-12-08 15:55:28 +02:00
inspector Introduce visualize_chunk(), refactor inspector to use it 2025-12-08 15:55:27 +02:00
qa Avoid citation meta inside LLM context 2025-12-08 15:55:28 +02:00
reranking Rename model to name under model 2025-11-25 12:28:43 +02:00
store Drop ChunkWithMetadata, use good old Chunk 2025-12-08 15:55:30 +02:00
__init__.py Restructure into uv workspace to support minimal and full installations 2025-11-04 17:59:12 +02:00
app.py Visualize chunk command, format citations to show chunk id 2025-12-08 15:55:28 +02:00
cli.py Visualize chunk command, format citations to show chunk id 2025-12-08 15:55:28 +02:00
client.py HaikuRag.chunk() utility method 2025-12-08 15:55:30 +02:00
logging.py Restructure into uv workspace to support minimal and full installations 2025-11-04 17:59:12 +02:00
mcp.py Simplify citations in qa & graph agents 2025-12-08 15:55:27 +02:00
monitor.py Implement docling-serve converter 2025-11-17 13:05:05 +02:00
utils.py Visualize chunk command, format citations to show chunk id 2025-12-08 15:55:28 +02:00