Commits
User selector
Commit history
Commits on Jan 10, 2026
Add evaluation script for comparing Naive RAG and RAG Agent
Show description for ecdd30ecommitted
Commits on Jan 4, 2026
Add retrieval ablation study and hybrid weight optimization
Show description for 7692132committed- committed
Add parallel and async evaluation support with optimizations
Show description for d8f9a92committed
Commits on Jan 3, 2026
Refactor conversation history management and streamline CLI interactions
Show description for d7e4abdcommittedAdd Streamlit UI for RAG agent with environment variable support
Show description for e26dc18committedFix RAGAS metrics UnboundLocalError and improve error handling
Show description for 78891becommittedRefactor evaluation scripts to reduce code duplication
Show description for 62ee92bandcommitted
Commits on Jan 2, 2026
Fix linting, formatting, and test issues
Show description for 6f90590committed
Commits on Jan 1, 2026
Add evaluation script for comparing knowledge graph implementations
Show description for 16341b1andcommitted
Commits on Dec 31, 2025
fix: Disable randomization in eval scripts to match targeted pool
Show description for 4278320andcommittedfix: Remove invalid enable_evidence_gap_critic parameter from eval scripts
Show description for 48afebaandcommittedArchive cleanup: convert analyze_retrieval to integration test and keep generate_report
Show description for 7af3bdfcommitted
Commits on Dec 29, 2025
refactor: Move retrieval components from integration/rag3 to retrieval/
Show description for 51f92cdandcommitted
Commits on Dec 28, 2025
chore: Archive outdated docs, scripts, and evaluation results
Show description for 24de8fbandcommitteddocs: Add experiment proposals for improving context_recall and KG
Show description for 506e307andcommittedfix: Use targeted retrieval pool with GT docs for meaningful evaluation
Show description for ed55464andcommittedfix: Fix KnowledgeGraphRetriever Pydantic field initialization
Show description for c65dec1andcommitted
Commits on Dec 27, 2025
fix: Fix infinite loop in document grading when features disabled
Show description for 605636candcommittedeval: add new defaults evaluation script
Show description for 1498b7fandcommitted
Commits on Dec 26, 2025
eval: Add Tier 3/4 evaluation scripts and fix JSON serialization
Show description for ceae1c6andcommittedeval: comprehensive Tier 3.2 & 3.3 evaluation with documented findings
Show description for 0f76abdandcommittedfix: refactor evidence-gap critic to proper LangGraph node architecture
Show description for f837ff2andcommittedeval: add Tier 1+2 RAG evaluation with trade-off analysis
Show description for 6d4d15candcommittedfeat: add LanceDB vector store support with persistence and reconstruction
Show description for 7fe9b34committed
Commits on Dec 23, 2025
Fix context recall issue: use full retrieval pool by default
Show description for 6c0ad46committed
Commits on Dec 21, 2025
Add randomization and eval LLM support for performance evaluation
Show description for fb04c69committedFix retrieval issue
Show description for ba0b26bcommitted
Commits on Dec 20, 2025
Optimize retrieval defaults based on analysis
Show description for 23428bdcommitted- committed
Add health monitoring, early exit, and LangSmith integration
Show description for db105d0committed
Commits on Dec 19, 2025
Add test coverage reporting and performance optimizations
Show description for a874098committedAdd timeout adjustments and local model comparison
Show description for 8ddec9ecommitted- committed
Configure tests for local Ollama model and fix test failures
Show description for 2e8a451committed