forked from microsoft/graphrag
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathcli.py
More file actions
212 lines (175 loc) · 6.74 KB
/
cli.py
File metadata and controls
212 lines (175 loc) · 6.74 KB
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
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License
"""Command line interface for the query module."""
import os
from pathlib import Path
from typing import cast
import pandas as pd
from graphrag.config import (
GraphRagConfig,
create_graphrag_config,
)
from graphrag.index.progress import PrintProgressReporter
from graphrag.query.input.loaders.dfs import (
store_entity_semantic_embeddings,
)
from graphrag.vector_stores import VectorStoreFactory, VectorStoreType
from .factories import get_global_search_engine, get_local_search_engine
from .indexer_adapters import (
read_indexer_covariates,
read_indexer_entities,
read_indexer_relationships,
read_indexer_reports,
read_indexer_text_units,
)
reporter = PrintProgressReporter("")
def __get_embedding_description_store(
vector_store_type: str = VectorStoreType.LanceDB, config_args: dict | None = None
):
"""Get the embedding description store."""
if not config_args:
config_args = {}
config_args.update({
"collection_name": config_args.get(
"query_collection_name",
config_args.get("collection_name", "description_embedding"),
),
})
description_embedding_store = VectorStoreFactory.get_vector_store(
vector_store_type=vector_store_type, kwargs=config_args
)
description_embedding_store.connect(**config_args)
return description_embedding_store
def run_global_search(
data_dir: str | None,
root_dir: str | None,
community_level: int,
response_type: str,
query: str,
):
"""Run a global search with the given query."""
data_dir, root_dir, config = _configure_paths_and_settings(data_dir, root_dir)
data_path = Path(data_dir)
final_nodes: pd.DataFrame = pd.read_parquet(
data_path / "create_final_nodes.parquet"
)
final_entities: pd.DataFrame = pd.read_parquet(
data_path / "create_final_entities.parquet"
)
final_community_reports: pd.DataFrame = pd.read_parquet(
data_path / "create_final_community_reports.parquet"
)
reports = read_indexer_reports(
final_community_reports, final_nodes, community_level
)
entities = read_indexer_entities(final_nodes, final_entities, community_level)
search_engine = get_global_search_engine(
config,
reports=reports,
entities=entities,
response_type=response_type,
)
result = search_engine.search(query=query)
reporter.success(f"Global Search Response: {result.response}")
return result.response
def run_local_search(
data_dir: str | None,
root_dir: str | None,
community_level: int,
response_type: str,
query: str,
):
"""Run a local search with the given query."""
data_dir, root_dir, config = _configure_paths_and_settings(data_dir, root_dir)
data_path = Path(data_dir)
final_nodes = pd.read_parquet(data_path / "create_final_nodes.parquet")
final_community_reports = pd.read_parquet(
data_path / "create_final_community_reports.parquet"
)
final_text_units = pd.read_parquet(data_path / "create_final_text_units.parquet")
final_relationships = pd.read_parquet(
data_path / "create_final_relationships.parquet"
)
final_nodes = pd.read_parquet(data_path / "create_final_nodes.parquet")
final_entities = pd.read_parquet(data_path / "create_final_entities.parquet")
final_covariates_path = data_path / "create_final_covariates.parquet"
final_covariates = (
pd.read_parquet(final_covariates_path)
if final_covariates_path.exists()
else None
)
vector_store_args = (
config.embeddings.vector_store if config.embeddings.vector_store else {}
)
vector_store_type = vector_store_args.get("type", VectorStoreType.LanceDB)
description_embedding_store = __get_embedding_description_store(
vector_store_type=vector_store_type,
config_args=vector_store_args,
)
entities = read_indexer_entities(final_nodes, final_entities, community_level)
store_entity_semantic_embeddings(
entities=entities, vectorstore=description_embedding_store
)
covariates = (
read_indexer_covariates(final_covariates)
if final_covariates is not None
else []
)
search_engine = get_local_search_engine(
config,
reports=read_indexer_reports(
final_community_reports, final_nodes, community_level
),
text_units=read_indexer_text_units(final_text_units),
entities=entities,
relationships=read_indexer_relationships(final_relationships),
covariates={"claims": covariates},
description_embedding_store=description_embedding_store,
response_type=response_type,
)
result = search_engine.search(query=query)
reporter.success(f"Local Search Response: {result.response}")
return result.response
def _configure_paths_and_settings(
data_dir: str | None, root_dir: str | None
) -> tuple[str, str | None, GraphRagConfig]:
if data_dir is None and root_dir is None:
msg = "Either data_dir or root_dir must be provided."
raise ValueError(msg)
if data_dir is None:
data_dir = _infer_data_dir(cast(str, root_dir))
config = _create_graphrag_config(root_dir, data_dir)
return data_dir, root_dir, config
def _infer_data_dir(root: str) -> str:
output = Path(root) / "output"
# use the latest data-run folder
if output.exists():
folders = sorted(output.iterdir(), key=os.path.getmtime, reverse=True)
if len(folders) > 0:
folder = folders[0]
return str((folder / "artifacts").absolute())
msg = f"Could not infer data directory from root={root}"
raise ValueError(msg)
def _create_graphrag_config(root: str | None, data_dir: str | None) -> GraphRagConfig:
"""Create a GraphRag configuration."""
return _read_config_parameters(cast(str, root or data_dir))
def _read_config_parameters(root: str):
_root = Path(root)
settings_yaml = _root / "settings.yaml"
if not settings_yaml.exists():
settings_yaml = _root / "settings.yml"
settings_json = _root / "settings.json"
if settings_yaml.exists():
reporter.info(f"Reading settings from {settings_yaml}")
with settings_yaml.open("r") as file:
import yaml
data = yaml.safe_load(file)
return create_graphrag_config(data, root)
if settings_json.exists():
reporter.info(f"Reading settings from {settings_json}")
with settings_json.open("r") as file:
import json
data = json.loads(file.read())
return create_graphrag_config(data, root)
reporter.info("Reading settings from environment variables")
return create_graphrag_config(root_dir=root)