This example implements a knowledge graph extraction and question-answering pipeline using IssunDB.
- Reads text documents, splits them into text chunks, extracts entities, and records entity co-occurrences.
- Indexes chunks using a vector index (for semantic retrieval) and a BM25 text index (for keyword retrieval).
- Performs a hybrid search on both indexes and resolves the reciprocal-rank fusion of the results.
- Traverses the graph structure to extract adjacent entities and document contexts.
- Combines the retrieved context and queries an LLM to generate the final answer.
More detailed workflow is shown below:
