Enrichment class for enriching OLS terms with textual descriptions
EnrichmentWithOLS
Bases: Enrichments
Enrichment class using OLS terms
Source code in aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py
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 | class EnrichmentWithOLS(Enrichments):
"""
Enrichment class using OLS terms
"""
def enrich_documents(self, texts: list[str]) -> list[str]:
"""
Enrich a list of input OLS terms
Args:
texts: The list of OLS terms to be enriched.
Returns:
The list of enriched descriptions
"""
ols_ids = texts
logger.log(logging.INFO, "Load Hydra configuration for OLS enrichments.")
with hydra.initialize(version_base=None, config_path="../../configs"):
cfg = hydra.compose(
config_name="config", overrides=["utils/enrichments/ols_terms=default"]
)
cfg = cfg.utils.enrichments.ols_terms
descriptions = []
for ols_id in ols_ids:
params = {"short_form": ols_id}
r = requests.get(
cfg.base_url,
headers={"Accept": "application/json"},
params=params,
timeout=cfg.timeout,
)
response_body = json.loads(r.text)
# if the response body is empty
if "_embedded" not in response_body:
descriptions.append("")
continue
# Add the description to the list
description = []
for term in response_body["_embedded"]["terms"]:
# If the term has a description, add it to the list
description += term.get("description", [])
# Add synonyms to the description
description += term.get("synonyms", [])
# Add the label to the description
# Label is not provided as list, so we need to convert it to a list
label = term.get("label", "")
if label:
description += [label]
# Make unique the description
description = list(set(description))
# Join the description with new line
description = "\n".join(description)
# Ensure we always return a string, even if empty
descriptions.append(description if description else "")
return descriptions
def enrich_documents_with_rag(self, texts, docs):
"""
Enrich a list of input OLS terms
Args:
texts: The list of OLS to be enriched.
Returns:
The list of enriched descriptions
"""
return self.enrich_documents(texts)
|
enrich_documents(texts)
Enrich a list of input OLS terms
Parameters:
| Name |
Type |
Description |
Default |
texts
|
list[str]
|
The list of OLS terms to be enriched.
|
required
|
Returns:
| Type |
Description |
list[str]
|
The list of enriched descriptions
|
Source code in aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py
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 | def enrich_documents(self, texts: list[str]) -> list[str]:
"""
Enrich a list of input OLS terms
Args:
texts: The list of OLS terms to be enriched.
Returns:
The list of enriched descriptions
"""
ols_ids = texts
logger.log(logging.INFO, "Load Hydra configuration for OLS enrichments.")
with hydra.initialize(version_base=None, config_path="../../configs"):
cfg = hydra.compose(
config_name="config", overrides=["utils/enrichments/ols_terms=default"]
)
cfg = cfg.utils.enrichments.ols_terms
descriptions = []
for ols_id in ols_ids:
params = {"short_form": ols_id}
r = requests.get(
cfg.base_url,
headers={"Accept": "application/json"},
params=params,
timeout=cfg.timeout,
)
response_body = json.loads(r.text)
# if the response body is empty
if "_embedded" not in response_body:
descriptions.append("")
continue
# Add the description to the list
description = []
for term in response_body["_embedded"]["terms"]:
# If the term has a description, add it to the list
description += term.get("description", [])
# Add synonyms to the description
description += term.get("synonyms", [])
# Add the label to the description
# Label is not provided as list, so we need to convert it to a list
label = term.get("label", "")
if label:
description += [label]
# Make unique the description
description = list(set(description))
# Join the description with new line
description = "\n".join(description)
# Ensure we always return a string, even if empty
descriptions.append(description if description else "")
return descriptions
|
enrich_documents_with_rag(texts, docs)
Enrich a list of input OLS terms
Parameters:
| Name |
Type |
Description |
Default |
texts
|
|
The list of OLS to be enriched.
|
required
|
Returns:
| Type |
Description |
|
|
The list of enriched descriptions
|
Source code in aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py
79
80
81
82
83
84
85
86
87
88
89 | def enrich_documents_with_rag(self, texts, docs):
"""
Enrich a list of input OLS terms
Args:
texts: The list of OLS to be enriched.
Returns:
The list of enriched descriptions
"""
return self.enrich_documents(texts)
|