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
|
import uuid
import pandas as pd
import numpy as np
from .prompts import extractConcepts
from .prompts import graphPrompt
def documents2Dataframe(documents) -> pd.DataFrame:
rows = []
for chunk in documents:
row = {
"text": chunk.page_content,
**chunk.metadata,
"chunk_id": uuid.uuid4().hex,
}
rows = rows + [row]
df = pd.DataFrame(rows)
return df
def df2ConceptsList(dataframe: pd.DataFrame) -> list:
# dataframe.reset_index(inplace=True)
results = dataframe.apply(
lambda row: extractConcepts(
row.text, {"chunk_id": row.chunk_id, "type": "concept"}
),
axis=1,
)
# invalid json results in NaN
results = results.dropna()
results = results.reset_index(drop=True)
## Flatten the list of lists to one single list of entities.
concept_list = np.concatenate(results).ravel().tolist()
return concept_list
def concepts2Df(concepts_list) -> pd.DataFrame:
## Remove all NaN entities
concepts_dataframe = pd.DataFrame(concepts_list).replace(" ", np.nan)
concepts_dataframe = concepts_dataframe.dropna(subset=["entity"])
concepts_dataframe["entity"] = concepts_dataframe["entity"].apply(
lambda x: x.lower()
)
return concepts_dataframe
def df2Graph(dataframe: pd.DataFrame, model=None) -> list:
# dataframe.reset_index(inplace=True)
results = dataframe.apply(
lambda row: graphPrompt(row.text, {"chunk_id": row.chunk_id}, model), axis=1
)
# invalid json results in NaN
results = results.dropna()
results = results.reset_index(drop=True)
## Flatten the list of lists to one single list of entities.
concept_list = np.concatenate(results).ravel().tolist()
return concept_list
def graph2Df(nodes_list) -> pd.DataFrame:
## Remove all NaN entities
graph_dataframe = pd.DataFrame(nodes_list).replace(" ", np.nan)
graph_dataframe = graph_dataframe.dropna(subset=["node_1", "node_2"])
graph_dataframe["node_1"] = graph_dataframe["node_1"].apply(lambda x: x.lower())
graph_dataframe["node_2"] = graph_dataframe["node_2"].apply(lambda x: x.lower())
return graph_dataframe
|
