haiku.rag/haiku_rag_slim/haiku/rag
Yiorgis Gozadinos b8bf846bb7
Cite a repeated chunk from its last occurrence
Collision detection replaced the lookup's dict comprehension with
`setdefault`, which also flipped a chunk found by several searches from its
last occurrence to its first. The copies differ in everything the expansion
window decides, figures included, so that silently changed what a citation
renders.

The rules are separate now: a repeated (source, chunk_id) takes the later
result, a chunk_id under two sources is still refused.
2026-08-27 13:25:06 +03:00
..
capabilities Match capability instructions to the run's collection scope 2026-08-27 12:41:15 +03:00
chat Report where a named remote database actually is 2026-08-27 11:40:35 +03:00
chunkers Delete comments that restate the line below them 2026-08-20 15:22:33 +03:00
client Report where a named remote database actually is 2026-08-27 11:40:35 +03:00
config Correct the multi-database prose 2026-08-27 11:40:52 +03:00
converters Add per-endpoint api_key to model and embedding config 2026-08-23 23:54:40 +03:00
embeddings Add per-endpoint api_key to model and embedding config 2026-08-23 23:54:40 +03:00
ingester Split the store module by responsibility 2026-08-20 12:13:51 +03:00
inspector Report where a named remote database actually is 2026-08-27 11:40:35 +03:00
providers Wire providers.docling_serve.timeout through to the client 2026-08-19 13:30:45 +03:00
reranking Add per-endpoint api_key to model and embedding config 2026-08-23 23:54:40 +03:00
sandbox Keep the sandbox's connection open for the owners it hands out 2026-08-27 11:40:43 +03:00
sources Resolve file:// URIs to paths through url2pathname 2026-08-21 10:22:26 +03:00
store Cite a repeated chunk from its last occurrence 2026-08-27 13:25:06 +03:00
tools Render collection identity only for multi-collection searches 2026-08-27 12:41:05 +03:00
__init__.py Restructure into uv workspace to support minimal and full installations 2025-11-04 17:59:12 +02:00
app.py Name the database of a result by what the operation covers 2026-08-26 16:55:56 +03:00
circuit_breaker.py Move CircuitBreaker to a shared module 2026-07-08 11:03:30 +03:00
cli.py Correct the multi-database prose 2026-08-27 11:40:52 +03:00
context.py Ask and analyze across several databases 2026-08-24 10:03:46 +03:00
doctor.py Read a database's stored settings once 2026-08-25 17:38:32 +03:00
logging.py Delete comments that restate the line below them 2026-08-20 15:22:33 +03:00
mcp.py Make get_config the only configuration lookup 2026-08-19 14:43:40 +03:00
s3.py swap aioboto3 for obstore in the S3 client path 2026-05-11 11:29:42 +03:00
telemetry.py Route eval scripts through the shared telemetry configure 2026-07-10 11:38:33 +03:00
uri.py Resolve file:// URIs to paths through url2pathname 2026-08-21 10:22:26 +03:00
utils.py Correct the multi-database prose 2026-08-27 11:40:52 +03:00