danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
haiku.rag/tests
History
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
..
cassettes Rename document_meta identity column document_id to id 2026-07-08 16:32:55 +03:00
chat rotate chat TUI conversation id per launch / clear-chat 2026-05-21 14:21:51 +03:00
data Remove repliqa from test setup 2026-06-01 10:40:52 +03:00
docker Add a docker-compose for integration test services 2026-06-04 11:13:16 +03:00
ingester Move CircuitBreaker to a shared module 2026-07-08 11:03:30 +03:00
sandbox Serialize shared-connection access across skill tools and the sandbox 2026-06-05 17:22:11 +03:00
skills Build the skills rag_db fixture once per session 2026-06-29 15:15:26 +03:00
store Carry merged chunk ids on SearchResult and Citation 2026-07-09 11:05:41 +03:00
tools remove dead code, add tool descriptions in frontend, update changelog 2026-04-20 15:38:17 +03:00
utils Checkout version logic and datetime utils 2025-12-19 12:03:16 +02:00
__init__.py Use LLM-as-a-judge to test QA 2025-06-25 18:18:28 +03:00
conftest.py Add a docker-compose for integration test services 2026-06-04 11:13:16 +03:00
json_body_serializer.py Use cassette to record and reply llms in qa tests 2025-12-26 15:41:11 +02:00
services.py Add a docker-compose for integration test services 2026-06-04 11:13:16 +03:00
test_cascade_delete.py Cascade delete_document to children via metadata.parent_uri 2026-05-28 15:36:00 +03:00
test_chunk.py Log FTS index build failures at WARNING 2026-06-25 13:00:29 +03:00
test_chunker.py Widen chunk() type to accept None, add test for None guard 2026-06-22 14:24:12 -04:00
test_cli.py drop the old monitor, rename serve→mcp, add e2e tests 2026-05-26 11:42:41 +03:00
test_client.py Draw matched content stronger than expanded context in visualizations 2026-07-09 11:05:41 +03:00
test_client_analyze.py record cassettes against new fixtures, fix stale assertions 2026-05-26 11:44:46 +03:00
test_config.py Treat empty env vars as unset in config expansion 2026-06-25 12:41:04 +03:00
test_context.py Anchor and clip merged citations on the highest-scoring chunk 2026-07-09 11:05:41 +03:00
test_context_enhancement.py Shrink the docling-serve context-expansion cassette 2026-06-29 15:15:26 +03:00
test_converters.py Share the VLM URL builder and centralize the embedder empty guard 2026-06-29 15:15:26 +03:00
test_database_autocreate.py Migrate LanceDB to native async API 2026-04-24 14:42:52 +03:00
test_docling_serve_client.py Fail docling-serve requests over to another instance with per-instance breaking 2026-07-08 11:03:44 +03:00
test_doctor.py Rename document_meta identity column document_id to id 2026-07-08 16:32:55 +03:00
test_document.py Collapse docling compression to a single function 2026-06-24 10:43:27 +03:00
test_download_models.py Drop the multi-agent research workflow 2026-05-20 12:46:48 +03:00
test_duplicate_ingestion.py Re-check URI under the write lock to prevent duplicate ingestion 2026-07-08 11:26:45 +03:00
test_embedder.py Pool HTTP clients for vLLM embedding and vLLM/Jina reranking 2026-07-09 10:32:44 +03:00
test_embedder_config.py auto-append /v1 to vllm base_url, matching ollama behavior 2026-05-05 16:08:14 +03:00
test_filter.py Rename document_meta identity column document_id to id 2026-07-08 16:32:55 +03:00
test_info.py Migrate LanceDB to native async API 2026-04-24 14:42:52 +03:00
test_inspector.py render attached pictures in inspector context modal under qa.model.vision 2026-05-06 12:00:12 +03:00
test_lancedb_connection.py Split meta document attributes into a document_meta table 2026-06-12 10:17:17 +03:00
test_logging.py Additional tests 2026-02-13 18:08:46 +02:00
test_mcp.py rename embed_image_query to embed_image; run description check on text path 2026-05-05 16:15:47 +03:00
test_pdf_attachments.py compare off-loop work against actual event-loop thread, fix ty 2026-06-22 10:17:02 +03:00
test_pdf_concurrency.py Serialize all in-process pdfium access under a shared lock 2026-06-14 10:50:42 +03:00
test_pdf_split.py test: clarify off-loop thread assertions 2026-06-22 10:51:35 +03:00
test_picture_description.py cover picture-description provider and rebuild edge cases 2026-05-05 14:20:37 +03:00
test_picture_in_context.py Dedupe picture chunks and skip small pictures at chunking 2026-07-09 10:24:32 +03:00
test_processing.py Dedupe picture chunks and skip small pictures at chunking 2026-07-09 10:24:32 +03:00
test_reader.py async versions for convert_file() convert_text() 2025-11-26 17:46:25 +02:00
test_rebuild.py Split meta document attributes into a document_meta table 2026-06-12 10:17:17 +03:00
test_reranker.py Pool HTTP clients for vLLM embedding and vLLM/Jina reranking 2026-07-09 10:32:44 +03:00
test_s3_integration.py Clean up S3 test data per-test to keep SeaweedFS writable 2026-06-26 16:41:20 +03:00
test_s3_source.py canonical metadata keys: source_revision + content_type, bump to 0.50.0 2026-05-26 11:43:30 +03:00
test_search.py Remove repliqa from test setup 2026-06-01 10:40:52 +03:00
test_settings.py Test vector_dim mismatch raises in read-only mode 2026-06-05 10:55:38 +03:00
test_skill_generator.py Remove documents from state, fix tests 2026-04-20 09:48:18 +03:00
test_skill_tools.py drop list_documents/get_document from default RAG skill 2026-05-26 11:35:43 +03:00
test_title_generation.py drop private title/embedding forwarders from HaikuRAG 2026-04-24 15:52:50 +03:00
test_utils.py Drop the multi-agent research workflow 2026-05-20 12:46:48 +03:00
test_vacuum_debounce.py Throttle background auto-vacuum to at most once per 5 minutes 2026-06-12 10:17:18 +03:00
test_versioning.py Throttle background auto-vacuum to at most once per 5 minutes 2026-06-12 10:17:18 +03:00