Spaces:
Sleeping
Sleeping
Commit History
23 days ago
-
fix: optimum[onnxruntime] extra for ONNX reranker
AkshayMdc8407f -
fix: job_queue remove relative import for DLQ auto-retry
AkshayMf731db5 -
fix: job_queue absolute imports for DLQ auto-retry
AkshayMaacbd3f -
feat: 10 free upgrades — streaming upload, cache invalidation, hybrid search, ONNX reranker, SQLAlchemy pool tuning, batch embed cache, semantic chunking, Prometheus histograms, DLQ auto-retry, structured logging+OTel
AkshayM3e047b8
-
ci: add keep-alive ping every 12h to prevent HF Space sleep
AkshayM0c37468
-
docs: update README for per-upload PII opt-in and pypdf parser
AkshayM84b2929 -
Add max_tokens parameter to NexAGI endpoint
AkshayMf89f0c8 -
Add privacy column to Document model + migration 005
AkshayM262e6d5 -
Remove PII from research mode and response handlers
AkshayM390b099 -
Tune Presidio: strict mode masks names+orgs for NDA, light mode skips them for research
AkshayM073907c -
Add privacy flag to upload — PII runs only when privacy=True (NDA mode)
AkshayM82a91b9 -
Fix tuple unpacking error in gather result for PDF parsing
AkshayMd3f3dec -
Skip MarkItDown for PDFs — run only as fallback if pypdf returns empty
AkshayMe2a2578 -
Swap pdfplumber → pypdf for upload parsing (3x faster text extraction)
AkshayMa965d17
-
Fix upload dedup crash: scalar_one_or_none → scalars().first() for sha256 lookup
AkshayMf67c9de -
Remove forced section headers from SYSTEM_WHITE_BOX — /query returns raw LLM output
AkshayMd134998 -
Fix NexAGIResponse: reasoning_details is list[dict], not dict
AkshayM807225f -
Fix NexAGI: reasoning_details is already a list of dicts
AkshayM6102a51 -
Fix NexAGI: reasoning_details list model_dump, add reasoning_details to message schema
AkshayM9cb8ece -
Update README + mermaid: add NexAGI free-form reasoning chat
AkshayM0b6e6e0 -
Add /NexAGI endpoint — OpenRouter reasoning via nex-agi/nex-n2-pro:free
AkshayM464d909 -
Update README: dual LLM providers, 1 worker, JSON analyze, PII skips
AkshayM5917ff5 -
Parallelize multi-doc retrieval with asyncio.gather
AkshayMa0f0ee1 -
Restore JSON parsing in analyze_document — populate all DocumentAnalysis fields
AkshayM06a5fdf -
Revert "Remove deepeval test from HF"
AkshayMThis reverts commit 07e4eef4bc167508bb4c26888100c88044a7b4ee.f33ec9c -
Remove deepeval test from HF
AkshayM07e4eef -
Fix import path in deepeval test
AkshayM50842e1 -
Add deepeval RAG quality tests (faithfulness + relevancy)
AkshayMab39019
-
Reduce default concurrent jobs to 5
AkshayM7587052 -
Append verification warning to answer so frontend always shows it
AkshayM1a0d1f5 -
Handle null content in LLM response (NoneType len error)
AkshayM102af7a -
Auto-fallback to mercury when minimax fails (chat + stream)
AkshayMed71b77 -
Skip PERSON/LOCATION/ORG in PII masking — only mask contact & financial IDs
AkshayMebf84fb -
Safe minimax defaults: no thinking, temp=0.3, max_tokens=4096
AkshayM536fca2 -
Profile-aware API key: mercury uses INCEPTION_API_KEY, minimax uses LLM_API_KEY
AkshayMfe833f1 -
Minimax uses LLM_BASE_URL env var; mercury always uses inceptionlabs.ai
AkshayMe2b443d -
Remove LLM_BASE_URL env override — use profile's own base_url
AkshayM08f6f02 -
Keep only mercury + minimax profiles; remove custom profile logic entirely
AkshayM980aa8d -
Drop custom profile as default — always default to mercury; minimax remains selectable
AkshayM17b877a -
Speed up analyze: use black_box mode (no thinking, 2K tokens) instead of white_box
AkshayM3a19fe3 -
Reduce uvicorn workers from 8 to 1 to prevent OOM on HF Spaces
AkshayM3fb79c1 -
Remove _strip_headers post-processing — let LLM output pass through as-is
AkshayMbededb8 -
Strip headers server-side + stronger prompt to enforce plain-text output
AkshayMf4d05f9 -
Force plain-text output: remove all headers/structure from LLM prompt
AkshayMd62b685 -
Simplify document_agent: drop JSON parsing, return raw LLM output; fix llm.py syntax errors
AkshayM7fdb111 -
fix: strict query-only output in analyze — no extra sections
AkshayMPrompt now tells LLM the JSON keys must be exactly the topics the user asked about. No summary, key_findings, analysis, caveats, or other sections unless the question explicitly requests them.79d0c2f -
feat: query-driven analyze + context window bump
AkshayM- Analyze prompt now instructs LLM to skip 'summary' unless the question asks for one; output keys directly match the query topic. - Fallback summary derived from question text if LLM omits it. - Mercury analyze max_tokens: 4096 -> 8192 - Minimax/custom analyze max_tokens: 8192 -> 16384 (leverages 1M ctx)4127275 -
fix: make analyze JSON structure query-driven instead of rigid template
AkshayMRemoved the hardcoded template forcing all sections (summary, key_findings, methodology, research_gaps, contradictions, open_questions, limitations) for every query. Now the LLM derives which keys to include based on the user's question.6d2e6ad -
fix: normalize all LLM JSON fields + wire cross_doc/per_doc
AkshayMNormalize key_findings/research_gaps/contradictions/open_questions when LLM returns bare string instead of list. Normalize confidence. Wire cross_document_comparison and per_document_summary into DocumentAnalysis (previously silently dropped).3788bc0 -
fix: normalize list-typed limitations/methodology from LLM JSON
AkshayMLLM sometimes returns limitations/methodology as arrays when using response_format=json_object. Convert to bullet list string before passing to DocumentAnalysis constructor.ede9cc4