Spaces:
Paused
Paused
Commit History
20 days ago
-
Upload Dockerfile
Verified signature39c03a8 -
Upload Dockerfile
Verified signature3517d32 -
Upload patch_restore_full_app.py
Verified signature1d6872e -
Upload BUILD_TRIGGER
Verified signature8ddc36d -
Upload patch_frontend.py
Verified signature7155db3 -
Upload README.md
Verified signature1ba0abe -
Upload patch_models.py
Verified signature12981e9 -
Upload BUILD_TRIGGER
Verified signature3f601ad -
Upload README.md
Verified signaturef1d8dde -
Upload Dockerfile
Verified signature82cf28b -
Upload patch_space_bunny.py
Verified signature8dbf890 -
Upload patch_models.py
Verified signaturec7a9183
-
Fix OpenRouter models: add custom_llm_provider='openrouter' so litellm stops failing on non-provider org prefixes (upstage/nvidia/liquid)
9800705 -
Add 3 new OpenRouter models: UPSTAGE Solar Pro 4, NVIDIA Nemotron 3.5 Lightning:free, Liquid LFM 2.5 2.6B:free
768a8d3 -
Support multi-file uploads (many images/files at once)
Backend: - Upload route now accepts up to 20 files per request (max_files=20) - Replaced single-file helper with multi-file helper - Returns list[DatasetUploadResponse]; injects context note per file Frontend: - Added 'multiple' to file input so users can select many files/images - handleDatasetFileChange sends all selected files in one request and parses the list response, showing how many files were uploaded Dockerfile: run new frontend + backend multi-upload patches5150658 -
Localize upload error messages (VI) + force cache-bust rebuild
- Frontend: clearer Vietnamese error msg listing all supported formats -> changes bundle hash so all cached clients reload - Backend: replace legacy 'Only .csv/.json/.jsonl...' message with Vietnamese listing all formats - No stale 'Only CSV/JSON/JSONL' message remains anywhere9f0f104 -
trigger rebuild after TS fix
7f7d89e -
Fix frontend patch: use array not object literal in new Set() for extension types
839ccab -
Document multi-format uploads + force rebuild
5c664a6 -
Support multi-format uploads (PDF/images/Excel/Word/PPT/ODF/text) with AI text extraction
- Backend: extend ALLOWED_DATASET_EXTENSIONS + BINARY_EXTRACTION_EXTS - Add backend/document_parser.py: extract text from PDF (pypdf), images (pytesseract OCR), XLSX (openpyxl), DOCX (python-docx), PPTX (python-pptx), legacy/ODF via LibreOffice - Inject extracted text as SYSTEM context so text-only LLM backends can understand files - Frontend: widen file accept + extension checks + error message - Dockerfile: install tesseract-ocr(+eng, vie), libreoffice, and python doc deps21c88c7
-
🔄 Rebuild: Fix DeepSeek V4 Flash routing (deepseek-ai/DeepSeek-V4-Flash:deepinfra + OpenRouter prefix strip)
Verified signatureb04cf06 -
Trigger rebuild with DeepSeek V4 Flash routing fix
Verified signaturee86d633 -
Update error report with DeepSeek V4 Flash routing fix details
Verified signature7d99409 -
Fix: DeepSeek V4 Flash routing - use HF Router path instead of broken OpenRouter path
Verified signature2f5416d
-
Trigger rebuild for model updates (#16)
- Trigger rebuild for model updates (7a0818b6e685ac001d77821149c733af06ec7b85)884f8f4 -
Upload patch_models.py (#14)
- Upload patch_models.py (6fbdc461b270691e9ef2b6d6fb794428a34cc6fe)9c808b3 -
Upload patch_models.py (#13)
- Upload patch_models.py (5a9a1c157e3e285c730131498bdafeaf9f704e26)c956f2e -
Upload patch_models.py (#12)
- Upload patch_models.py (3bb3d5520b35c7204430a47145371756e4e85536)a9d1ee5 -
Upload patch_models.py (#11)
- Upload patch_models.py (04ab38fff856b257679361ec37fd26727776aeb7)8ee1ea0 -
Upload patch_frontend.py (#9)
- Upload patch_frontend.py (34e0141bb27fa695c9d247d51756fd9da42bc439)4d2fcd9 -
Upload patch_models.py (#8)
- Upload patch_models.py (98d34b539287dde3567f97d3714939fe5c571dda)206e8c5 -
Upload patch_models.py (#7)
- Upload patch_models.py (f78d2c4c3f57fcd6ca8bf1c756cc98d50f29da37)a8fca56 -
Upload patch_frontend.py (#6)
- Upload patch_frontend.py (0041fd08a9bb27477f20ac810ed613197be9f13a)b87f698 -
Upload patch_models.py (#5)
- Upload patch_models.py (1f852d0995f225c5653dd884eaa710e35b76eff7)880781c -
Upload patch_frontend.py (#3)
- Upload patch_frontend.py (f6d3613d3ce279e98e2b977d85abf7f7c92bae41)cfaf7b7 -
Upload README.md (#4)
- Upload README.md (64a2fa7e0060cb89e9febb5ff35d74b4b876d41c)77439fc -
Upload patch_models.py
Verified signature334f0c9
-
Run patch_agent_backend.py + auto-approve + mid-task detection
Verified signature300132c -
patches: agent_loop detection + auto-approve toggle
Verified signatureb996e23
-
V18: Fix patch_models.py syntax + all patches working
Verified signature39a3de5 -
Fix syntax error in patch_models.py - unclosed string
Verified signature362b9e1 -
Add nex-agi/nex-n2-mini + inclusionai/ling-3.0-flash:free (backend)
Verified signaturecd5342c -
Add nex-agi/nex-n2-mini + inclusionai/ling-3.0-flash:free models
Verified signaturea68f195 -
V17: Use V17 auto-continue patch
Verified signature1eac1e9 -
V17: Perfect Python - no syntax errors, exact two-line marker
Verified signature4eab82e -
V16: Match exact two-line return pattern - THE final fix
Verified signature24bc8ad -
V15: Use V15 auto-continue patch
Verified signature8b9afb9 -
V15: Fix Button detection (check Button,) + fix return statement
Verified signatureba4fc37 -
V14: Use V14 auto-continue patch (ASCII only) - Build First
Verified signature1d21713 -
V14: Simple ASCII text - build first, add Vietnamese later
Verified signaturecd124c3