Spaces:
Running
Running
Commit History
Yesterday
-
feat(rag): isolate conversational mode from stored docs unless explicitly attached or mentioned
2926b6d -
fix(chat): detect casual conversation to prevent unwanted web search on chit-chat
a7887b4 -
feat(research): enrich academic queries with active document topic and enforce verified arXiv citations
29a9e61 -
fix(llm): guard Groq fallback against 8000 TPM limit with prompt compaction and context trimming
2789a91 -
fix(studio): switch Groq model to high-quota gpt-oss-120b and parallelize quiz generation
4677a3b -
feat(studio): enrich mindmap nodes with full text and provide evidence_text excerpts in quiz
f3f0bbe -
chore(deps): declare missing runtime dependencies and refresh requirements lock
841b61d -
feat(llm): add explicit client and streaming timeouts with failover preservation
ee92077 -
feat(auth): enforce client ownership and data isolation across all endpoints and databases
a506cc3 -
feat(rag): implement nucleus top_p retrieval and exact inner page citation pinning
AI Assistant- Add temperature-scaled Softmax over weighted RRF consensus scores with top_p=0.75, min_p=0.18, and multi-hop min_k=2 - Implement exact inner-page citation pinning (active_page) during Sub-Node Paragraph Pruning from --- [PAGE X] --- markers - Update LLMService section prompt header formatting to cite active_page - Rebuild IEEE index cache with exact per-paragraph page bounds - Re-run full 95-question benchmark pushing Context Precision to 82.5% and Citation Page Accuracy to 83.1% on IEEE (+ 81.1% on FinanceBench)de0d0d6 -
feat: upgrade FastMCP and internal tools to Research & Study MCP suite
AI Assistant- Add Deep Web Reader tool (read_webpage_markdown) with clean HTML parsing and 6s timeout - Add Academic & arXiv Research tool (search_arxiv_papers) querying public arXiv API with direct PDF links - Add YouTube Lecture Transcript tool (fetch_youtube_transcript) with 3-minute timestamped chapters and citations - Add Safe AST Math & Table Calculator (evaluate_math_expression) without eval() - Expose Atlas internal capabilities as FastMCP tools (atlas_list_documents, atlas_query_document, atlas_get_knowledge_dossier) - Expose REST router /tools with companion endpoints - Integrate arXiv research auto-triggering into VectorlessRAG and conversational stream - Update pyproject.toml, requirements.txt, and uv.lock with beautifulsoup4 and youtube-transcript-apidad455c -
feat(studio): implement Phase 4 Interactive Study Studio backend with mindmap graph and AI quiz generator
AI Assistant9ad6c13 -
feat(retrieval): implement Phase 3 query intent classification and dossier root context injection
AI Assistantf4d3bb7 -
feat(rag): inject page boundaries and implement sub-node paragraph pruning for precise citations
AI Assistant2bc0095
11 days ago
-
feat: add active HTTP link testing and strict content validation prompt directives
AI Assistant7d5d266 -
feat: add FastMCP web search server, tool and dual citations
AI Assistant63f56d4
13 days ago
-
feat: add multi-document vectorless RAG, session isolation, and memory services
AI Assistant0039ed6 -
feat: add Atlas identity, document endpoints, and Groq fallback for depleted tokens
AI Assistantdff6fcd
23 days ago
-
feat: asynchronous PDF upload and background indexing with status polling
AI Assistantd13ebb9 -
update
AI Assistantbe59b3a -
feat: add RAG application modules, services, routers, and schemas for document and chat processing
AI Assistant7b5352e
-
Enhance LLMService to coerce node IDs and improve tree normalization
AI Assistant9c36dc8 -
update
AI Assistant9b5a2e4 -
Refactor LLMService to integrate gemini client and update dependencies in pyproject.toml
AI Assistantad67d8e -
Refactor DocumentService to allow optional API key during initialization
AI Assistantbfe9d27 -
update
AI Assistant274ce7e -
update
AI Assistant2a38361 -
Refactor code structure for improved readability and maintainability
AI Assistantbdf20e7