HybridGraphRetriever<T>
Models & Types · AiDotNet.RetrievalAugmentedGeneration.Graph
Hybrid retriever that combines vector similarity search with graph traversal for enhanced RAG.
For Beginners
Traditional RAG uses only vector similarity:
Query: “What is photosynthesis?” Traditional RAG:
- Find documents similar to the query
- Return top-k matches
- Misses related context!
Hybrid Graph RAG:
- Find initial matches via vector similarity
- Walk the graph to find related concepts
- Example: photosynthesis → chlorophyll → plants → carbon dioxide
- Provides richer, more complete context
Real-world analogy:
- Traditional: Search “Paris” → get Paris documents
- Hybrid: Search “Paris” → get Paris + France + Eiffel Tower + Seine River
- Graph connections provide context vectors can’t capture!
How It Works
This retriever uses a two-stage approach:
- Vector similarity search to find initial candidate nodes
- Graph traversal to expand context with related nodes
Constructors
| Constructor | Summary |
|---|---|
HybridGraphRetriever(KnowledgeGraph<T> graph, IDocumentStore<T> documentStore) |
Initializes a new instance of the HybridGraphRetriever class. |
Methods
| Method | Summary |
|---|---|
List<RetrievalResult<T>> Retrieve(Vector<T> queryEmbedding, int topK, int expansionDepth, int maxResults) |
Retrieves relevant nodes using hybrid vector + graph approach. |
List<RetrievalResult<T>> RetrieveWithRelationships(Vector<T> queryEmbedding, int topK, Dictionary<string, double> relationshipWeights, int maxResults) |
Retrieves nodes with relationship-aware scoring. |
Task<List<RetrievalResult<T>>> RetrieveAsync(Vector<T> queryEmbedding, int topK, int expansionDepth, int maxResults) |
Retrieves relevant nodes asynchronously using hybrid approach. |