Feat/graphviz experimental support #237
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add support for Graphviz visualization capabilities through pygraphviz, enabling experimental features in the project. This commit includes: - Add Taskfile.yml for automated setup of Graphviz and dependencies - Add environment setup script for Graphviz library paths - Configure Poetry to install experimental extras with Graphviz support - Add test script to verify Graphviz installation The setup process includes: 1. Building Graphviz 8.1.0 from source with custom prefix 2. Setting up environment variables for library paths 3. Installing build dependencies (gcc, python3-dev) 4. Installing project with experimental features via Poetry To replicate this setup: 1. Install Task (taskfile.dev) 2. Run: task all Technical details: - Graphviz Version: 8.1.0 - Installation prefix: /home/gonzo/local - Required env vars: LD_LIBRARY_PATH, PATH, CFLAGS, LDFLAGS Resolves the pygraphviz installation issues and enables graph visualization capabilities for the knowledge graph project.
Add support for building a medical knowledge graph from research papers, focusing on Systemic Lupus Erythematosus (SLE) and related concepts. Key changes: - Add setup_knowledge_graph.py for processing medical PDFs - Create medical_kg_pipeline_config.json with domain-specific entities - Update pipeline to use asyncio for async operations - Define medical entities (diseases, biomarkers, treatments) - Define medical relationships (causes, treats, indicates) - Fix prompt template and OpenAI API configuration The pipeline extracts medical entities and relationships using GPT-4 and stores them in a Neo4j graph database for later retrieval.
Add new components for improved GraphRAG functionality: - Add EnhancedGraphRAG with post-processing capabilities - Add OptimizedGraphRAG with performance improvements - Add MonitoredGraphRAG with logging capabilities - Add HybridRetriever combining vector and graph-based retrieval - Add graph visualization utility Also update .gitignore to exclude test files and data directory.
Update the tutorial documentation to include: - Examples of medical knowledge graph creation - Sample output from GraphRAG queries - Code snippets for enhanced retrievers - Best practices for graph visualization
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds tutorial and supporting features