danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
haiku.rag/tests
History
Yiorgis Gozadinos 3603b00513
Fix base64 images leaking into expanded search results 
PictureItem.export_to_markdown() defaults to ImageRefMode.EMBEDDED,
which embeds base64 image data. When _extract_item_text() called this
method during context expansion, base64 data would leak into results.

Now explicitly handles PictureItem with ImageRefMode.PLACEHOLDER to
prevent base64 while still including VLM descriptions and captions.
2026-01-08 18:42:58 +02:00
..
cassettes Fix base64 images leaking into expanded search results 2026-01-08 18:42:58 +02:00
data Commit dataset for CI and github workflow 2025-12-26 19:30:26 +02:00
graph Track potentially more than one running step in agui emitter 2026-01-05 10:41:35 +02:00
store Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
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 Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
json_body_serializer.py Use cassette to record and reply llms in qa tests 2025-12-26 15:41:11 +02:00
test_app.py Tests for history 2025-12-19 12:03:19 +02:00
test_chunk.py Add vcr to tests 2025-12-29 14:59:15 +02:00
test_chunker.py Extract shared DoclingServeClient for async workflow & use it for VLM support, chunking, converting 2026-01-07 11:09:23 +02:00
test_cli.py Fix tests 2025-12-11 16:05:49 +02:00
test_client.py Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_config.py Make tests ignore haiku.rag.yaml 2025-12-19 12:35:06 +02:00
test_context_enhancement.py Fix base64 images leaking into expanded search results 2026-01-08 18:42:58 +02:00
test_converters.py Extract shared DoclingServeClient for async workflow & use it for VLM support, chunking, converting 2026-01-07 11:09:23 +02:00
test_database_autocreate.py Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_document.py Escape when getting by URI 2025-12-12 10:56:37 +02:00
test_embedder.py Extended VCR cassette recording to embedder, client, research graph, and search filter tests 2025-12-26 18:53:17 +02:00
test_embedder_config.py Update tests and client for explicit embed_query/embed_documents API 2025-12-26 11:26:56 +02:00
test_filter.py Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_info.py Do not run test requiring docling OCR in CI 2025-12-29 13:44:57 +02:00
test_inspector.py Infinite scroll lazy load document list in inspector 2025-12-09 17:48:27 +02:00
test_lancedb_connection.py Always upgrade database on access. Explicitly create db by running init or HaikuRAG(path, create=True) 2025-12-02 16:49:55 +02:00
test_mcp.py Remove deep qa graph, everything now uses the simplified research graph 2025-12-18 11:41:10 +02:00
test_monitor.py Clarify folder mounts in docker docs, check monitor paths exist in FileWatcher 2025-12-19 11:58:08 +02:00
test_qa.py Add lint github action 2025-12-27 18:50:57 +02:00
test_reader.py async versions for convert_file() convert_text() 2025-11-26 17:46:25 +02:00
test_rebuild.py Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_reranker.py get_reranker() tests 2025-12-29 17:13:14 +02:00
test_search.py Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_settings.py Extended VCR cassette recording to embedder, client, research graph, and search filter tests 2025-12-26 18:53:17 +02:00
test_utils.py Fix non-reasoning OpenAI models that do not support reasoning config 2026-01-07 18:47:31 +02:00
test_versioning.py Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00