Spaces:
Running
Running
File size: 1,387 Bytes
37f0321 d02622b 37f0321 d02622b 37f0321 31086ae d02622b 37f0321 31086ae 37f0321 31086ae 37f0321 31086ae 37f0321 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
from collections import defaultdict
from typing import List
from graphgen.bases import BaseLLMWrapper
from graphgen.bases.base_storage import BaseGraphStorage
from graphgen.bases.datatypes import Chunk
from graphgen.models import LightRAGKGBuilder
from graphgen.utils import run_concurrent
def build_text_kg(
llm_client: BaseLLMWrapper,
kg_instance: BaseGraphStorage,
chunks: List[Chunk],
):
"""
:param llm_client: Synthesizer LLM model to extract entities and relationships
:param kg_instance
:param chunks
:return:
"""
kg_builder = LightRAGKGBuilder(llm_client=llm_client, max_loop=3)
results = run_concurrent(
kg_builder.extract,
chunks,
desc="[2/4]Extracting entities and relationships from chunks",
unit="chunk",
)
nodes = defaultdict(list)
edges = defaultdict(list)
for n, e in results:
for k, v in n.items():
nodes[k].extend(v)
for k, v in e.items():
edges[tuple(sorted(k))].extend(v)
run_concurrent(
lambda kv: kg_builder.merge_nodes(kv, kg_instance=kg_instance),
list(nodes.items()),
desc="Inserting entities into storage",
)
run_concurrent(
lambda kv: kg_builder.merge_edges(kv, kg_instance=kg_instance),
list(edges.items()),
desc="Inserting relationships into storage",
)
|