This website requires JavaScript.
70913c4b3e
v1.16.0
jkunz
2026-01-20 17:14:26 +00:00
2ed419f6e4
feat(invoices): add line_items extraction and normalization for invoice parsing
jkunz
2026-01-20 17:14:26 +00:00
45cb87e9e7
v1.15.3
jkunz
2026-01-20 04:15:45 +00:00
74a5b37e92
fix(tests(nanonets)): allow / when normalizing invoice strings in tests
jkunz
2026-01-20 04:15:45 +00:00
2bdcc74df0
v1.15.2
jkunz
2026-01-20 04:12:57 +00:00
981c031c6e
fix(dev-deps): bump devDependencies @push.rocks/smartagent to ^1.6.2 and @push.rocks/smartai to ^0.13.3
jkunz
2026-01-20 04:12:57 +00:00
26d2de824f
v1.15.1
jkunz
2026-01-20 03:19:58 +00:00
969d21c51a
fix(tests): enable progress events in invoice tests and bump @push.rocks/smartagent devDependency to ^1.5.4
jkunz
2026-01-20 03:19:58 +00:00
da2b827ba3
chore: update smartagent to v1.5.2 (streaming support for native tool calling)
jkunz
2026-01-20 02:55:28 +00:00
9bc1f74978
feat(test): enable native tool calling for GPT-OSS invoice extraction
jkunz
2026-01-20 02:51:52 +00:00
cf282b2437
v1.15.0
jkunz
2026-01-20 01:17:41 +00:00
77d57e80bd
feat(tests): integrate SmartAi/DualAgentOrchestrator into extraction tests and add JSON self-validation
jkunz
2026-01-20 01:17:41 +00:00
b202e024a4
v1.14.3
jkunz
2026-01-20 00:55:24 +00:00
2210611f70
fix(repo): no changes detected in the diff; no files modified and no release required
jkunz
2026-01-20 00:55:24 +00:00
d8bdb18841
fix(test): add JSON validation and retry logic to invoice extraction
jkunz
2026-01-20 00:45:30 +00:00
d384c1d79b
feat(tests): integrate smartagent DualAgentOrchestrator with streaming support
jkunz
2026-01-20 00:39:36 +00:00
6bd672da61
v1.14.2
jkunz
2026-01-19 21:28:26 +00:00
44d6dc3336
fix(readme): update README to document Nanonets-OCR2-3B (replaces Nanonets-OCR-s), adjust VRAM and context defaults, expand feature docs, and update examples/test command
jkunz
2026-01-19 21:28:26 +00:00
d1ff95bd94
v1.14.1
jkunz
2026-01-19 21:19:37 +00:00
09770d3177
fix(extraction): improve JSON extraction prompts and model options for invoice and bank statement tests
jkunz
2026-01-19 21:19:37 +00:00
235aa1352b
v1.14.0
jkunz
2026-01-19 21:05:51 +00:00
08728ada4d
feat(docker-images): add vLLM-based Nanonets-OCR2-3B image, Qwen3-VL Ollama image and refactor build/docs/tests to use new runtime/layout
jkunz
2026-01-19 21:05:51 +00:00
b58bcabc76
update
jkunz
2026-01-19 11:51:23 +00:00
6dbd06073b
v1.13.2
jkunz
2026-01-18 23:00:24 +00:00
ae28a64902
fix(tests): stabilize OCR extraction tests and manage GPU containers
jkunz
2026-01-18 23:00:24 +00:00
09ea7440e8
update
jkunz
2026-01-18 15:54:16 +00:00
177e87d3b8
v1.13.1
jkunz
2026-01-18 13:58:26 +00:00
17ea7717eb
fix(image_support_files): remove PaddleOCR-VL server scripts from image_support_files
jkunz
2026-01-18 13:58:26 +00:00
bd5bb5d874
v1.13.0
jkunz
2026-01-18 13:56:46 +00:00
d91df70fff
feat(tests): revamp tests and remove legacy Dockerfiles: adopt JSON/consensus workflows, switch MiniCPM model, and delete deprecated Docker/test variants
jkunz
2026-01-18 13:56:46 +00:00
d6c97a9625
v1.12.0
jkunz
2026-01-18 11:26:38 +00:00
76b21f1f7b
feat(tests): switch vision tests to multi-query extraction (count then per-row/field queries) and add logging/summaries
jkunz
2026-01-18 11:26:38 +00:00
4c368dfef9
v1.11.0
jkunz
2026-01-18 04:50:57 +00:00
e76768da55
feat(vision): process pages separately and make Qwen3-VL vision extraction more robust; add per-page parsing, safer JSON handling, reduced token usage, and multi-query invoice extraction
jkunz
2026-01-18 04:50:57 +00:00
63d72a52c9
update
jkunz
2026-01-18 04:28:57 +00:00
386122c8c7
v1.10.1
jkunz
2026-01-18 04:17:30 +00:00
7c8f10497e
fix(tests): improve Qwen3-VL invoice extraction test by switching to non-stream API, adding model availability/pull checks, simplifying response parsing, and tightening model options
jkunz
2026-01-18 04:17:30 +00:00
9f9ec0a671
v1.10.0
jkunz
2026-01-18 03:35:06 +00:00
3780105c6f
feat(vision): add Qwen3-VL vision model support with Dockerfile and tests; improve invoice OCR conversion and prompts; simplify extraction flow by removing consensus voting
jkunz
2026-01-18 03:35:05 +00:00
d237ad19f4
v1.9.0
jkunz
2026-01-18 02:53:24 +00:00
7652a2df52
feat(tests): add Ministral 3 vision tests and improve invoice extraction pipeline to use Ollama chat schema, sanitization, and multi-page support
jkunz
2026-01-18 02:53:24 +00:00
b316d98f24
v1.8.0
jkunz
2026-01-18 00:11:17 +00:00
f0d88fcbe0
feat(paddleocr-vl): add structured HTML output and table parsing for PaddleOCR-VL, update API, tests, and README
jkunz
2026-01-18 00:11:17 +00:00
0d8a1ebac2
v1.7.1
jkunz
2026-01-17 23:13:47 +00:00
5a311dca2d
fix(docker): standardize Dockerfile and entrypoint filenames; add GPU-specific Dockerfiles and update build and test references
jkunz
2026-01-17 23:13:47 +00:00
ab288380f1
v1.7.0
jkunz
2026-01-17 21:50:09 +00:00
30c73b24c1
feat(tests): use Qwen2.5 (Ollama) for invoice extraction tests and add helpers for model management; normalize dates and coerce numeric fields
jkunz
2026-01-17 21:50:09 +00:00
311e7a8fd4
v1.6.0
jkunz
2026-01-17 20:22:23 +00:00
80e6866442
feat(paddleocr-vl): add PaddleOCR-VL full pipeline Docker image and API server, plus integration tests and docker helpers
jkunz
2026-01-17 20:22:23 +00:00
addae20cbd
v1.5.0
jkunz
2026-01-17 16:57:26 +00:00
0482c35b69
feat(paddleocr-vl): add PaddleOCR-VL GPU Dockerfile, pin vllm, update CPU image deps, and improve entrypoint and tests
jkunz
2026-01-17 16:57:26 +00:00
15ac1fcf67
update
jkunz
2026-01-16 16:21:44 +00:00
3c5cf578a5
v1.4.0
jkunz
2026-01-16 14:24:37 +00:00
82358b2d5d
feat(invoices): add hybrid OCR + vision invoice/document parsing with PaddleOCR, consensus voting, and prompt/test refactors
jkunz
2026-01-16 14:24:37 +00:00
acded2a165
v1.3.0
jkunz
2026-01-16 13:23:01 +00:00
bec379e9ca
feat(paddleocr): add PaddleOCR OCR service (Docker images, server, tests, docs) and CI workflows
jkunz
2026-01-16 13:23:01 +00:00
67c38eeb67
v1.2.0
jkunz
2026-01-16 10:23:32 +00:00
ae4bb26931
feat(paddleocr): add PaddleOCR support: Docker images, FastAPI server, entrypoint and tests
jkunz
2026-01-16 10:23:32 +00:00
bc65ea4ece
v1.1.0
jkunz
2026-01-16 10:22:15 +00:00
379b5c19eb
feat(ocr): add PaddleOCR GPU Docker image and FastAPI OCR server with entrypoint; implement OCR endpoints and consensus extraction testing
jkunz
2026-01-16 10:22:15 +00:00
3dc1881d8b
update
jkunz
2026-01-16 03:58:39 +00:00
6e464cb7e7
update
jkunz
2026-01-16 02:52:54 +00:00
7d135569fe
initial
jkunz
2026-01-16 01:51:57 +00:00
jkunz