Buckets:
AnonymousSpottedToad/candidate_bucket / codebase /python /HKUDS_LightRAG /examples /insert_custom_kg.py
| import os | |
| from lightrag import LightRAG | |
| from lightrag.llm.openai import gpt_4o_mini_complete | |
| ######### | |
| # Uncomment the below two lines if running in a jupyter notebook to handle the async nature of rag.insert() | |
| # import nest_asyncio | |
| # nest_asyncio.apply() | |
| ######### | |
| WORKING_DIR = "./custom_kg" | |
| if not os.path.exists(WORKING_DIR): | |
| os.mkdir(WORKING_DIR) | |
| rag = LightRAG( | |
| working_dir=WORKING_DIR, | |
| llm_model_func=gpt_4o_mini_complete, # Use gpt_4o_mini_complete LLM model | |
| # llm_model_func=gpt_4o_complete # Optionally, use a stronger model | |
| ) | |
| custom_kg = { | |
| "entities": [ | |
| { | |
| "entity_name": "CompanyA", | |
| "entity_type": "Organization", | |
| "description": "A major technology company", | |
| "source_id": "Source1", | |
| }, | |
| { | |
| "entity_name": "ProductX", | |
| "entity_type": "Product", | |
| "description": "A popular product developed by CompanyA", | |
| "source_id": "Source1", | |
| }, | |
| { | |
| "entity_name": "PersonA", | |
| "entity_type": "Person", | |
| "description": "A renowned researcher in AI", | |
| "source_id": "Source2", | |
| }, | |
| { | |
| "entity_name": "UniversityB", | |
| "entity_type": "Organization", | |
| "description": "A leading university specializing in technology and sciences", | |
| "source_id": "Source2", | |
| }, | |
| { | |
| "entity_name": "CityC", | |
| "entity_type": "Location", | |
| "description": "A large metropolitan city known for its culture and economy", | |
| "source_id": "Source3", | |
| }, | |
| { | |
| "entity_name": "EventY", | |
| "entity_type": "Event", | |
| "description": "An annual technology conference held in CityC", | |
| "source_id": "Source3", | |
| }, | |
| ], | |
| "relationships": [ | |
| # Each real source_id contributes an evidence-count floor of 1.0. | |
| # Larger values are optional boosts; omit source_id for a source-less | |
| # non-negative fractional weight. | |
| { | |
| "src_id": "CompanyA", | |
| "tgt_id": "ProductX", | |
| "description": "CompanyA develops ProductX", | |
| "keywords": "develop, produce", | |
| "weight": 1.0, | |
| "source_id": "Source1", | |
| }, | |
| { | |
| "src_id": "PersonA", | |
| "tgt_id": "UniversityB", | |
| "description": "PersonA works at UniversityB", | |
| "keywords": "employment, affiliation", | |
| "weight": 1.25, | |
| "source_id": "Source2", | |
| }, | |
| { | |
| "src_id": "CityC", | |
| "tgt_id": "EventY", | |
| "description": "EventY is hosted in CityC", | |
| "keywords": "host, location", | |
| "weight": 1.0, | |
| "source_id": "Source3", | |
| }, | |
| ], | |
| "chunks": [ | |
| { | |
| "content": "ProductX, developed by CompanyA, has revolutionized the market with its cutting-edge features.", | |
| "source_id": "Source1", | |
| "source_chunk_index": 0, | |
| }, | |
| { | |
| "content": "One outstanding feature of ProductX is its advanced AI capabilities.", | |
| "source_id": "Source1", | |
| "chunk_order_index": 1, | |
| }, | |
| { | |
| "content": "PersonA is a prominent researcher at UniversityB, focusing on artificial intelligence and machine learning.", | |
| "source_id": "Source2", | |
| "source_chunk_index": 0, | |
| }, | |
| { | |
| "content": "EventY, held in CityC, attracts technology enthusiasts and companies from around the globe.", | |
| "source_id": "Source3", | |
| "source_chunk_index": 0, | |
| }, | |
| { | |
| "content": "None", | |
| "source_id": "UNKNOWN", | |
| "source_chunk_index": 0, | |
| }, | |
| ], | |
| } | |
| rag.insert_custom_kg(custom_kg) | |
Xet Storage Details
- Size:
- 3.86 kB
- Xet hash:
- b029a45c699372965dcf8bf9d58b9ef05a1ea396f2044d9708a40530bae6d21c
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.