How janani-chandrakanth/graphrag works
This is a requirements-to-knowledge-graph application: users ingest requirement documents, normalize and extract structured items, persist them as a graph, then query, inspect, compare, and analyze that graph. Additional capabilities include community summaries, semantic retrieval, flow analysis, evaluation, and test-case generation. The README is empty; relationships below rely on source excerpts and SOURCE INDEX references. Some integration paths are therefore shown as unverified rather than asserted as confirmed calls.
Main entry points: update_graph_tab.py Document Update · neo4j_manager.py Graph Store · langchain_qa.py Natural Language QA · incremental_merge.py Incremental Merge
Components 32
Document Ingestion
- Document Parser
parser/parser.py - Document Type Detection
parser/document_type_detector.py - Normalization
parser/normalization.py - Text Extractors
parser/extractors.py - Requirement Chunking
chunking/chunker.py
Knowledge Graph
- Entity Extraction
graph/entity_extractor.py - Requirement Linking
parser/requirement_linker.py - Deduplication
graph/deduplicator.py - Graph Validation
graph/validator.py - Incremental Merge
graph/incremental_merge.py - Graph Versions
graph/version_manager.py
Graph Insights
- Community Summaries
graph/community_engine.py - GraphRAG Query
graph/query_engine.py - Natural Language QA
graph/langchain_qa.py - Graph Analysis
graph/graph_analysis.py - Flow Analysis
graph/flow_graph_analysis.py - Feature Extraction
graph/feature_extractor.py - Test Generation
graph/graph_test_case_generator.py - Hybrid Test Generation
graph/hybrid_test_case_generator.py - Graph Evaluation
graph/evaluation/graph_evaluators.py
User Interface
- Application
app.py - Document Update
ui/update_graph_tab.py - Graph Visualization
graph/graph_visualizer.py - Query View
ui/query_graph_tab.py - Dashboard
ui/dashboard_tab.py - Feature Flow View
ui/feature_flow_tab.py - Evaluation View
ui/evaluation_tab.py - Version Comparison
ui/compare_tab.py
Persistence
- Graph Store
graph/neo4j_manager.py - Vector Store
vectorstore/chroma_manager.py
Other components
- User
- Ollama Service
Connections 48
- User → Application: uses
- User → Document Update: submits documents
- Application → Document Update: shows
app.py - Document Update → Document Parser: parses
ui/update_graph_tab.py - Document Parser → Text Extractors: extracts text
parser/parser.py - Document Parser → Normalization: normalizes
parser/parser.py - Document Update → Document Type Detection: detects type
ui/update_graph_tab.py - Document Update → Requirement Chunking: chunks items
ui/update_graph_tab.py - Document Update → Entity Extraction: extracts entities
ui/update_graph_tab.py - Document Update → Deduplication: deduplicates
ui/update_graph_tab.py - Document Update → Graph Validation: validates
ui/update_graph_tab.py - Document Update → Graph Store: stores graph
ui/update_graph_tab.py - Document Update → Incremental Merge: merges updates
ui/update_graph_tab.py - Document Update → Graph Versions: versions graph
ui/update_graph_tab.py - Document Update → Community Summaries: refreshes summaries
ui/update_graph_tab.py - Document Update → Natural Language QA: refreshes QA
ui/update_graph_tab.py - Document Update → Ollama Service: requests extraction
- Entity Extraction → Ollama Service: requests extraction
graph/entity_extractor.py - Normalization → Ollama Service: fills gaps
parser/normalization.py - Incremental Merge → Deduplication: deduplicates
graph/incremental_merge.py - Incremental Merge → Graph Store: merges graph
graph/incremental_merge.py - Incremental Merge → Vector Store: updates vectors
graph/incremental_merge.py - Community Summaries → Graph Store: reads graph
graph/community_engine.py - Community Summaries → Vector Store: stores summaries
graph/community_engine.py - Community Summaries → Ollama Service: summarizes
graph/community_engine.py - Query View → Natural Language QA: asks
ui/query_graph_tab.py - Natural Language QA → GraphRAG Query: retrieves context
graph/langchain_qa.py - Natural Language QA → Graph Store: queries graph
graph/langchain_qa.py - Natural Language QA → Vector Store: searches vectors
graph/langchain_qa.py - GraphRAG Query → Vector Store: retrieves summaries
graph/query_engine.py - GraphRAG Query → Ollama Service: generates answer
graph/query_engine.py - Query View → Graph Store: runs Cypher
ui/query_graph_tab.py - Query View → Graph Visualization: renders results
ui/query_graph_tab.py - Dashboard → Graph Store: reads graph
ui/dashboard_tab.py - Dashboard → Graph Versions: lists versions
ui/dashboard_tab.py - Feature Flow View → Feature Extraction: extracts features
ui/feature_flow_tab.py - Feature Flow View → Graph Store: reads graph
ui/feature_flow_tab.py - Feature Flow View → Graph Visualization: renders flow
ui/feature_flow_tab.py - Feature Extraction → Flow Analysis: analyzes flow
graph/feature_extractor.py - Graph Analysis → Flow Analysis: analyzes sequences
graph/graph_analysis.py - Graph Analysis → Graph Store: reads graph
graph/graph_analysis.py - Graph Visualization → Flow Analysis: analyzes layout
graph/graph_visualizer.py - Evaluation View → Graph Evaluation: evaluates graph
ui/evaluation_tab.py - Evaluation View → Graph Store: reads graph
ui/evaluation_tab.py - Graph Evaluation → Ollama Service: evaluates semantics
- Test Generation → Feature Extraction: uses features
graph/graph_test_case_generator.py - Test Generation → Flow Analysis: analyzes flow
graph/graph_test_case_generator.py - Hybrid Test Generation → Test Generation: extends generation
graph/hybrid_test_case_generator.py