Commit History
-
fix: switch to Qwen2.5-7B-Instruct with provider=auto — confirmed available on HF
ritvikv03e3d8c22 -
fix: switch provider from hf-inference to nebius — hf-inference dropped large LLM support (July 2025 per docs)
ritvikv032a80b84 -
fix: switch HF model to mistral-7b
ritvikv03477e777 -
fix: update HuggingFace model ID
ritvikv03127f878 -
updates
ritvikv036b2ec79
-
updates
ritvikv036098bde
-
feat: Nuclear visibility fix (Black on White) + Phase 2 features (Radar table, Feed sorting)
ritvikv031e1e189
-
fix: remove stale Gemini/ChromaDB refs, improve chart contrast, harden error handling
ritvikv03 +1: Claude Sonnet 4.6- Replace all Gemini/ChromaDB references in comments/docstrings with HuggingFace/Astra DB - Raise chart axis tickfont from #3d4f62 (invisible) to #6a8099 - Raise _CHART_BASE font_color from #7d8fa8 to #a8bcd0 - Fix _SEV_COLOUR low from #3d4f62 (invisible) to #607d8b - Fix empty-state annotation colours to match readable palette - Wrap _get_all_signals_cached() in try/except — UI never crashes without DB token - Fix scraper.py XML element deprecation warnings (or -> is not None) - Delete test_hf.py and output.txt debug artifacts - Gitignore .playwright-mcp/ and screenshot files Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>97b3013
-
fix: switch HuggingFace provider to cerebras + Llama-3.1-8B-Instruct
ritvikv03 +1: Claude Sonnet 4.6meta-llama/Llama-3.2-3B-Instruct has no provider mapping in huggingface_hub 0.36.x, causing StopIteration inside get_provider_helper() on every LLM call — the root cause of 'Analysis unavailable' in the Strategic Advisor. Fix across all three LLM call sites: - core/agents.py: provider="cerebras", model → Llama-3.1-8B-Instruct - core/pipeline.py: provider="cerebras", model → Llama-3.1-8B-Instruct - core/summary_engine.py: provider="cerebras", model → Llama-3.1-8B-Instruct Tested: full router → analyst chain returns structured strategic analysis. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>8c8e18f
-
feat: model unification, node truncation, generate brief button
ritvikv03 +1: Claude Sonnet 4.6- Step 1: Replace all HF model strings with meta-llama/Llama-3.2-3B-Instruct across pipeline.py, graph_engine.py, summary_engine.py, and app.py chat - Step 1 (continued): Replace HuggingFaceEndpoint (LangChain, broken novita text-generation task) with InferenceClient.chat_completion() in summary_engine._call_llm() and app.py _llm_chat() - Step 2: Node label truncation in graph_engine.update_graph() — both new signal nodes and historical match nodes now use 35-char + "..." truncation - Step 3: Add "Generate New Intelligence Brief" button to Strategic Reports tab; new generate_intelligence_brief() callback fetches top-10 signals, calls generate_brief_markdown(), writes outputs/reports/Strategic_Brief_<ts>.md, refreshes dropdown and renders new report inline - Add generate_brief_markdown() + _rule_based_brief() module functions to summary_engine.py with full LLM + deterministic fallback implementation Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>81a544d
-
refactor: replace Gemini with HuggingFace/LangGraph stack
ritvikv03 +1: Claude Sonnet 4.6- Swap core/pipeline.py to HuggingFaceEndpoint (Mistral-7B-Instruct-v0.3) with module-level singleton, [INST] format, and severity_score removed - Swap core/summary_engine.py to HuggingFace, fix dead q2_solution db path - Add semantic deduplication (cosine threshold 0.08) before LLM scoring - Create core/graph_engine.py: 4-node LangGraph RAG knowledge-graph workflow with aborted sentinel, correct short-circuit logic, and edge deduplication - Hook run_graph_update() into scheduler after each successful signal insert - Add Export Report button + dcc.Download HTML export in app.py - Rename tabs: Field Intelligence, Disruption Horizon, Signal Feed, Strategic Advisor - Update sidebar brand to AGRO-MARKET INTELLIGENCE, remove Gemini branding - Reset data/graph.json to empty template (no synthetic data) - Add langchain/langgraph/huggingface_hub deps with upper-bound caps Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>c9dcf7a