Yiorgis Gozadinos
387c4f12a9
multimodal sandbox: show_image + picture_refs, drop llm
2026-05-18 16:48:34 +03:00
Yiorgis Gozadinos
849eca94d0
Make rebuild --embed-only idempotent across crashes
2026-05-14 15:02:12 +03:00
Yiorgis Gozadinos
a035b0f9e4
Stream rebuild --embed-only through a staging table to bound memory
2026-05-14 15:02:12 +03:00
Yiorgis Gozadinos
704bea6f4a
Stabilize test_client_search ranking assertion
2026-05-14 14:37:27 +03:00
Yiorgis Gozadinos
9f8c9fe3b1
cover s3 uri override, unsupported extension, watcher error path
2026-05-11 11:29:56 +03:00
Yiorgis Gozadinos
6631e339ee
record VCR cassettes for s3 source tests
2026-05-11 11:29:56 +03:00
Yiorgis Gozadinos
6af463699d
record VCR cassette for vllm embedder end-to-end test
2026-05-06 20:01:22 +03:00
Yiorgis Gozadinos
08696773fe
Fix vcr test
2026-05-05 14:38:03 +03:00
Yiorgis Gozadinos
a45d82f206
Update benchmark
2026-05-05 13:58:48 +03:00
Yiorgis Gozadinos
e88321767d
always store picture bytes; collapse converter to a single zip path
2026-05-05 10:40:40 +03:00
Yiorgis Gozadinos
aa3e9406cf
auto-append /v1 to per-model Ollama base_url, fix flaky tests
2026-05-04 13:12:37 +03:00
Yiorgis Gozadinos
c9fdad15a9
bump docling-core to >=2.74.1 so that local docling-local and docling-serve chunkers run the same MarkdownTableSerializer
2026-05-03 18:40:44 +03:00
Yiorgis Gozadinos
c9227c649f
emit synthetic picture chunks at ingest under multimodal embedders.
...
processing.chunk() merges text chunks with one synthetic Chunk per PictureItem-with-bytes,
sorted by iterate_items() position so chunk.order is structural.
embed_chunks dispatches on a Chunk._picture_data PrivateAttr
(text through embed_documents, picture through embed_image_query)
2026-05-03 17:04:43 +03:00
Yiorgis Gozadinos
75c8e83515
Allow uri override on create_document_from_source
2026-04-30 16:36:35 +03:00
Yiorgis Gozadinos
191cdc636b
retrieve picture image bytes via referenced+zip path, fix docling-serve not returning images even when set to do so. Remove xfail from relevant test
2026-04-30 11:23:29 +03:00
Yiorgis Gozadinos
821b7361e9
Push document-id filter into chunk search query
2026-04-24 16:07:07 +03:00
Yiorgis Gozadinos
ddcc4518ad
Cover FULL rebuild source-failure branch
2026-04-24 15:32:53 +03:00
Yiorgis Gozadinos
258ffa41fa
Improve test coverage
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
d0ed9e213f
Pin FTS search column to content_fts
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
b6ea07d2de
Track all in-flight background vacuum tasks, not just the last one
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
ba911a35f6
Add test for background vaccum being awaited
2026-04-24 14:42:52 +03:00
Yiorgis Gozadinos
d52f453c44
flatten skill architecture: replace ask/analyze/research with direct tools
2026-04-17 18:35:17 +03:00
Yiorgis Gozadinos
a45820dbf7
add document virtual filesystem to analysis sandbox
...
Replace get_document() and get_docling_document() with a VFS at
/documents/{id}/ with metadata.json (eager), content.txt (lazy),
and items.jsonl (lazy). Keep search(), list_documents() (now returns
all), and llm() as external functions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
bacc21b38b
expose doc_item_refs and labels in sandbox search results
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
4118533db1
fold context expansion into sandbox search and remove get_context
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
44fd0c9906
add get_context() to analysis sandbox and improve prompt
2026-04-17 18:32:45 +03:00
Yiorgis Gozadinos
d2b3ba1b59
rename RLM agent to analysis throughout the codebase
2026-04-17 18:32:01 +03:00
Yiorgis Gozadinos
b6113bf8ab
replace fixed-radius expansion with section-bounded algorithm
...
Context expansion is now automatic and structure-aware. For structured
documents, expands within the section containing the match. For sections
that exceed the budget or are too small, expands item-by-item outward
skipping noise labels. Unstructured documents use budget-based outward
expansion. Results sorted by relevance score.
2026-04-16 12:11:53 +03:00
Yiorgis Gozadinos
a07a64a31f
enable repeat_table_header for self-contained table chunks and docling-serve parity
2026-03-26 14:02:12 +02:00
Yiorgis Gozadinos
2c5128e5ba
Re-record rlm tests
2026-03-12 17:31:26 +02:00
Yiorgis Gozadinos
e2749ad2a6
Cap QA agent search iterations to reduce response time
2026-03-11 12:13:43 +02:00
Yiorgis Gozadinos
d460d553f3
Set repeat_table_header=False to match docling serve
2026-03-05 13:02:18 +02:00
Yiorgis Gozadinos
3c7d746d57
Strengthen search tests, remove redundant title test, relocate primary label test
...
- Strengthen test_search_returns_search_result with chunk_id, document_id, and
non-empty labels assertions
- Remove test_chunks_include_document_title (subsumed by strengthened test) and
its cassette
- Rename test_chunks_include_document_info to
test_search_chunk_includes_document_provenance; add document_title is None
assertion for untitled documents
- Move test_search_result_get_primary_label from test_context_enhancement.py to
test_search.py; rename, remove unnecessary @pytest.mark.vcr() decorator
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-05 11:39:45 +02:00
Yiorgis Gozadinos
f73d4f4da9
Remove stale cassette, dead vcr_cassette_dir fixtures, and unnecessary VCR decorator
2026-03-05 11:36:22 +02:00
Yiorgis Gozadinos
28e90e5a87
Auto-detect structured output mode from model profile. Remove the structured_output config field from ModelConfig.
2026-03-04 14:51:09 +02:00
Yiorgis Gozadinos
c9f63b9ab6
Re-record RLM vcrs
2026-03-03 16:59:35 +02:00
Yiorgis Gozadinos
459fdfca71
Add get_docling_document external function to sandbox
2026-02-24 11:51:43 +02:00
Yiorgis Gozadinos
d3c6322481
Simplify sandbox with run_monty_async, replace manual ThreadPoolExecutor start/resume loop
2026-02-24 11:35:39 +02:00
Yiorgis Gozadinos
454f12b319
Update coverage
2026-02-24 09:55:45 +02:00
Yiorgis Gozadinos
017712c9b1
Update prompts & docs. Remove docker sandbox workflow
2026-02-24 09:55:45 +02:00
Yiorgis Gozadinos
c61ded1271
Replace Docker sandbox with pydantic-monty
2026-02-24 09:55:40 +02:00
Yiorgis Gozadinos
8176103eb0
Remove agents/chat/
2026-02-20 16:36:48 +02:00
Yiorgis Gozadinos
ed89ff0fc9
Simplify tools/ — remove AG-UI state machinery, keep core toolsets
2026-02-20 16:36:48 +02:00
Yiorgis Gozadinos
969c64d106
Add citations_history to SessionState for unified citation rendering between search and ask
2026-02-13 16:21:50 +02:00
Yiorgis Gozadinos
c0ed93da2d
Expand tests
2026-02-13 14:34:24 +02:00
Yiorgis Gozadinos
c916356a42
Clean up toolset exports, simplify update_session_context(), fix health check
2026-02-11 12:46:50 +02:00
Yiorgis Gozadinos
87bcb7a5dc
Extract run_qa_core() from ask closure in QA toolset. Remove redundant tests and cassettes for OpenAI and Anthropic QA tools, as they are now tested in the core function tests.
2026-02-11 11:38:34 +02:00
Yiorgis Gozadinos
2cc4a8a88f
Fix VCR cassette
2026-02-10 18:01:13 +02:00
Yiorgis Gozadinos
cf4083d2d7
Add multi-turn integration test with initial context and summarization
2026-02-10 14:55:12 +02:00
Yiorgis Gozadinos
0dd181356e
Update vcr
2026-02-10 14:38:14 +02:00
