pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

code cleans. (#9916)

Browse Source 
### What problem does this PR solve?



### Type of change

- [x] Refactoring
- [x] Performance Improvement

Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
This commit is contained in:
湛露先生
2025-09-05 09:59:27 +08:00
committed by GitHub
parent ddaed541ff
commit b14052e5a2
4 changed files with 7 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
example/sdk/dataset_example.py
View File

@ -36,10 +36,8 @@ try:
updated_dataset = dataset_instance.update(updated_message) updated_dataset = dataset_instance.update(updated_message)
# get the dataset (list datasets) # get the dataset (list datasets)
dataset_list = ragflow_instance.list_datasets(id=dataset_instance.id)
dataset_instance_2 = dataset_list[0]
print(dataset_instance) print(dataset_instance)
print(dataset_instance_2) print(updated_dataset)
# delete the dataset (delete datasets) # delete the dataset (delete datasets)
to_be_deleted_datasets = [dataset_instance.id] to_be_deleted_datasets = [dataset_instance.id]

6
graphrag/general/entity_embedding.py
View File

@ -21,7 +21,7 @@ class NodeEmbeddings:
embeddings: np.ndarray embeddings: np.ndarray
def embed_nod2vec( def embed_node2vec(
graph: nx.Graph | nx.DiGraph, graph: nx.Graph | nx.DiGraph,
dimensions: int = 1536, dimensions: int = 1536,
num_walks: int = 10, num_walks: int = 10,
@ -44,13 +44,13 @@ def embed_nod2vec(
return NodeEmbeddings(embeddings=lcc_tensors[0], nodes=lcc_tensors[1]) return NodeEmbeddings(embeddings=lcc_tensors[0], nodes=lcc_tensors[1])
def run(graph: nx.Graph, args: dict[str, Any]) -> NodeEmbeddings: def run(graph: nx.Graph, args: dict[str, Any]) -> dict:
"""Run method definition.""" """Run method definition."""
if args.get("use_lcc", True): if args.get("use_lcc", True):
graph = stable_largest_connected_component(graph) graph = stable_largest_connected_component(graph)
# create graph embedding using node2vec # create graph embedding using node2vec
embeddings = embed_nod2vec( embeddings = embed_node2vec(
graph=graph, graph=graph,
dimensions=args.get("dimensions", 1536), dimensions=args.get("dimensions", 1536),
num_walks=args.get("num_walks", 10), num_walks=args.get("num_walks", 10),

4
graphrag/search.py
View File

@ -23,7 +23,7 @@ import trio
from api.utils import get_uuid from api.utils import get_uuid
from graphrag.query_analyze_prompt import PROMPTS from graphrag.query_analyze_prompt import PROMPTS
from graphrag.utils import get_entity_type2sampels, get_llm_cache, set_llm_cache, get_relation from graphrag.utils import get_entity_type2samples, get_llm_cache, set_llm_cache, get_relation
from rag.utils import num_tokens_from_string, get_float from rag.utils import num_tokens_from_string, get_float
from rag.utils.doc_store_conn import OrderByExpr from rag.utils.doc_store_conn import OrderByExpr
@ -42,7 +42,7 @@ class KGSearch(Dealer):
return response return response
def query_rewrite(self, llm, question, idxnms, kb_ids): def query_rewrite(self, llm, question, idxnms, kb_ids):
ty2ents = trio.run(lambda: get_entity_type2sampels(idxnms, kb_ids)) ty2ents = trio.run(lambda: get_entity_type2samples(idxnms, kb_ids))
hint_prompt = PROMPTS["minirag_query2kwd"].format(query=question, hint_prompt = PROMPTS["minirag_query2kwd"].format(query=question,
TYPE_POOL=json.dumps(ty2ents, ensure_ascii=False, indent=2)) TYPE_POOL=json.dumps(ty2ents, ensure_ascii=False, indent=2))
result = self._chat(llm, hint_prompt, [{"role": "user", "content": "Output:"}], {}) result = self._chat(llm, hint_prompt, [{"role": "user", "content": "Output:"}], {})

2
graphrag/utils.py
View File

@ -561,7 +561,7 @@ def merge_tuples(list1, list2):
return result return result
async def get_entity_type2sampels(idxnms, kb_ids: list): async def get_entity_type2samples(idxnms, kb_ids: list):
es_res = await trio.to_thread.run_sync(lambda: settings.retrievaler.search({"knowledge_graph_kwd": "ty2ents", "kb_id": kb_ids, "size": 10000, "fields": ["content_with_weight"]}, idxnms, kb_ids)) es_res = await trio.to_thread.run_sync(lambda: settings.retrievaler.search({"knowledge_graph_kwd": "ty2ents", "kb_id": kb_ids, "size": 10000, "fields": ["content_with_weight"]}, idxnms, kb_ids))
res = defaultdict(list) res = defaultdict(list)