File size: 2,602 Bytes
b9fe2b4 |
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 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
#
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import argparse
import json
from api import settings
import networkx as nx
import logging
import trio
from api.db import LLMType
from api.db.services.document_service import DocumentService
from api.db.services.knowledgebase_service import KnowledgebaseService
from api.db.services.llm_service import LLMBundle
from api.db.services.user_service import TenantService
from graphrag.general.index import update_graph
from graphrag.light.graph_extractor import GraphExtractor
settings.init_settings()
def callback(prog=None, msg="Processing..."):
logging.info(msg)
async def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"-t",
"--tenant_id",
default=False,
help="Tenant ID",
action="store",
required=True,
)
parser.add_argument(
"-d",
"--doc_id",
default=False,
help="Document ID",
action="store",
required=True,
)
args = parser.parse_args()
e, doc = DocumentService.get_by_id(args.doc_id)
if not e:
raise LookupError("Document not found.")
kb_id = doc.kb_id
chunks = [
d["content_with_weight"]
for d in settings.retrievaler.chunk_list(
args.doc_id,
args.tenant_id,
[kb_id],
max_count=6,
fields=["content_with_weight"],
)
]
_, tenant = TenantService.get_by_id(args.tenant_id)
llm_bdl = LLMBundle(args.tenant_id, LLMType.CHAT, tenant.llm_id)
_, kb = KnowledgebaseService.get_by_id(kb_id)
embed_bdl = LLMBundle(args.tenant_id, LLMType.EMBEDDING, kb.embd_id)
graph, doc_ids = await update_graph(
GraphExtractor,
args.tenant_id,
kb_id,
args.doc_id,
chunks,
"English",
llm_bdl,
embed_bdl,
callback,
)
print(json.dumps(nx.node_link_data(graph), ensure_ascii=False, indent=2))
if __name__ == "__main__":
trio.run(main)
|