981c031c6e
fix(dev-deps): bump devDependencies @push.rocks/smartagent to ^1.6.2 and @push.rocks/smartai to ^0.13.3
2026-01-20 04:12:57 +00:00
969d21c51a
fix(tests): enable progress events in invoice tests and bump @push.rocks/smartagent devDependency to ^1.5.4
2026-01-20 03:19:58 +00:00
9bc1f74978
feat(test): enable native tool calling for GPT-OSS invoice extraction
...
- Update smartai to v0.13.2 (native tool calling support)
- Update smartagent to v1.5.1 (useNativeToolCalling option)
- Enable think: true for GPT-OSS reasoning mode in Ollama config
- Enable useNativeToolCalling: true in DualAgentOrchestrator
- Simplify driver system message (native tools don't need XML instructions)
Native tool calling uses Ollama's built-in Harmony format parser
instead of requiring XML generation, which is more efficient for GPT-OSS models.
2026-01-20 02:51:52 +00:00
77d57e80bd
feat(tests): integrate SmartAi/DualAgentOrchestrator into extraction tests and add JSON self-validation
2026-01-20 01:17:41 +00:00
d8bdb18841
fix(test): add JSON validation and retry logic to invoice extraction
...
- Add tryExtractJson function to validate JSON before accepting
- Use orchestrator.continueTask() to request correction if JSON is invalid
- Retry up to 2 times for malformed JSON responses
- Remove duplicate parseJsonToInvoice function
2026-01-20 00:45:30 +00:00
d384c1d79b
feat(tests): integrate smartagent DualAgentOrchestrator with streaming support
...
- Update test.invoices.nanonets.ts to use DualAgentOrchestrator for JSON extraction
- Enable streaming token callback for real-time progress visibility
- Add markdown caching to avoid re-running Nanonets OCR for cached files
- Update test.bankstatements.minicpm.ts and test.invoices.minicpm.ts with streaming
- Update dependencies to @push.rocks/smartai@0.11 .1 and @push.rocks/smartagent@1.2.8
2026-01-20 00:39:36 +00:00
09770d3177
fix(extraction): improve JSON extraction prompts and model options for invoice and bank statement tests
2026-01-19 21:19:37 +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
2026-01-19 21:05:51 +00:00
b58bcabc76
update
2026-01-19 11:51:23 +00:00
ae28a64902
fix(tests): stabilize OCR extraction tests and manage GPU containers
2026-01-18 23:00:24 +00:00
09ea7440e8
update
2026-01-18 15:54:16 +00:00
d91df70fff
feat(tests): revamp tests and remove legacy Dockerfiles: adopt JSON/consensus workflows, switch MiniCPM model, and delete deprecated Docker/test variants
2026-01-18 13:56:46 +00:00
76b21f1f7b
feat(tests): switch vision tests to multi-query extraction (count then per-row/field queries) and add logging/summaries
2026-01-18 11:26:38 +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
2026-01-18 04:50:57 +00:00
63d72a52c9
update
2026-01-18 04:28:57 +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
2026-01-18 04:17:30 +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
2026-01-18 03:35:05 +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
2026-01-18 02:53:24 +00:00
f0d88fcbe0
feat(paddleocr-vl): add structured HTML output and table parsing for PaddleOCR-VL, update API, tests, and README
2026-01-18 00:11:17 +00:00
5a311dca2d
fix(docker): standardize Dockerfile and entrypoint filenames; add GPU-specific Dockerfiles and update build and test references
2026-01-17 23:13:47 +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
2026-01-17 21:50:09 +00:00
80e6866442
feat(paddleocr-vl): add PaddleOCR-VL full pipeline Docker image and API server, plus integration tests and docker helpers
2026-01-17 20:22:23 +00:00
0482c35b69
feat(paddleocr-vl): add PaddleOCR-VL GPU Dockerfile, pin vllm, update CPU image deps, and improve entrypoint and tests
2026-01-17 16:57:26 +00:00
15ac1fcf67
update
2026-01-16 16:21:44 +00:00
82358b2d5d
feat(invoices): add hybrid OCR + vision invoice/document parsing with PaddleOCR, consensus voting, and prompt/test refactors
2026-01-16 14:24:37 +00:00
bec379e9ca
feat(paddleocr): add PaddleOCR OCR service (Docker images, server, tests, docs) and CI workflows
2026-01-16 13:23:01 +00:00
379b5c19eb
feat(ocr): add PaddleOCR GPU Docker image and FastAPI OCR server with entrypoint; implement OCR endpoints and consensus extraction testing
2026-01-16 10:22:15 +00:00
3dc1881d8b
update
2026-01-16 03:58:39 +00:00
