ragleap-graph

version — loading live from PyPI…

Knowledge-graph-augmented retrieval for RAG systems: Neo4j-backed entity extraction, co-occurrence graphs, entity deduplication, and hybrid vector+graph retrieval.

pip install ragleap-graph

Highlights

• Framework-agnostic — pairs with ragleap-rag, or standalone
• Regex or LLM-based entity extraction
• Optional multi-tenant namespacing
• No hardcoded models or vocabulary

Tech stack

Core dependencies: neo4j

Optional extras:

• llm (regex or LLM-based extraction)
• retrieval (pairs with ragleap-rag)
• audit

Testing

112 test functions across 4 test files, verified directly from the repo.

Quickstart

from ragleap_graph import GraphConfig, GraphIndex

graph = GraphIndex(config=GraphConfig(
    uri="bolt://localhost:7687", user="neo4j", password="...",
))
graph.upsert_document(
    document_id="doc-1", title="Q3 Report",
    chunks=[{"text": "Acme Corp reported strong Q3 revenue growth."}],
)
docs = graph.find_documents_by_entities(["Acme Corp"])
related = graph.search_related_entities(["Acme Corp"], max_depth=2)