Yiorgis Gozadinos c424f51056 Anchor and clip merged citations on the highest-scoring chunk ... A merged search result took its chunk_id from whichever constituent sorted earliest in the document, while its score was the max across the group — so the citation's identity could point at a different, less relevant chunk. Anchor chunk_id and the content/refs fallbacks on the max-score constituent, clip the budget window around that same chunk so its evidence is never trimmed away, and narrow page_numbers, doc_item_refs, and attached image bytes to the items that survive the clip.		2026-07-09 11:05:41 +03:00
..
chat	Visualize all constituent chunks of a merged citation	2026-07-09 11:05:41 +03:00
chunkers	Fail docling-serve requests over to another instance with per-instance breaking	2026-07-08 11:03:44 +03:00
client	Draw matched content stronger than expanded context in visualizations	2026-07-09 11:05:41 +03:00
config	Dedupe picture chunks and skip small pictures at chunking	2026-07-09 10:24:32 +03:00
converters	Fail docling-serve requests over to another instance with per-instance breaking	2026-07-08 11:03:44 +03:00
embeddings	Pool HTTP clients for vLLM embedding and vLLM/Jina reranking	2026-07-09 10:32:44 +03:00
ingester	Move CircuitBreaker to a shared module	2026-07-08 11:03:30 +03:00
inspector	Visualize all constituent chunks of a merged citation	2026-07-09 11:05:41 +03:00
providers	Fail docling-serve requests over to another instance with per-instance breaking	2026-07-08 11:03:44 +03:00
reranking	Pool HTTP clients for vLLM embedding and vLLM/Jina reranking	2026-07-09 10:32:44 +03:00
sandbox	Serialize shared-connection access across skill tools and the sandbox	2026-06-05 17:22:11 +03:00
skill_generator	Drop the multi-agent research workflow	2026-05-20 12:46:48 +03:00
skills	Visualize all constituent chunks of a merged citation	2026-07-09 11:05:41 +03:00
store	Carry merged chunk ids on SearchResult and Citation	2026-07-09 11:05:41 +03:00
tools	Verify picture bytes before attaching to multimodal tool returns	2026-05-13 16:01:39 +03:00
__init__.py	Restructure into uv workspace to support minimal and full installations	2025-11-04 17:59:12 +02:00
app.py	Show a progress spinner while doctor runs	2026-06-28 10:44:30 +03:00
circuit_breaker.py	Move CircuitBreaker to a shared module	2026-07-08 11:03:30 +03:00
cli.py	Add doctor --duplicates-out YAML export; summarize terminal report	2026-06-26 16:52:22 +03:00
context.py	Anchor and clip merged citations on the highest-scoring chunk	2026-07-09 11:05:41 +03:00
doctor.py	Rename document_meta identity column document_id to id	2026-07-08 16:32:55 +03:00
logging.py	Restructure into uv workspace to support minimal and full installations	2025-11-04 17:59:12 +02:00
mcp.py	Always use the Store-owned embedder	2026-05-29 11:36:53 +03:00
s3.py	swap aioboto3 for obstore in the S3 client path	2026-05-11 11:29:42 +03:00
telemetry.py	Use haiku.rag as telemtry scope	2026-05-26 11:44:47 +03:00
utils.py	Drop the multi-agent research workflow	2026-05-20 12:46:48 +03:00