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
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 | 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(None)
continue
# Add the description to the list
description = response_body['_embedded']['terms'][0]['description']
# Add synonyms to the description
description += response_body['_embedded']['terms'][0]['synonyms']
# Add the label to the description
# Label is not provided as list, so we need to convert it to a list
description += [response_body['_embedded']['terms'][0]['label']]
descriptions.append('\n'.join(description))
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
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 | 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(None)
continue
# Add the description to the list
description = response_body['_embedded']['terms'][0]['description']
# Add synonyms to the description
description += response_body['_embedded']['terms'][0]['synonyms']
# Add the label to the description
# Label is not provided as list, so we need to convert it to a list
description += [response_body['_embedded']['terms'][0]['label']]
descriptions.append('\n'.join(description))
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
66
67
68
69
70
71
72
73
74
75
76 | 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)
|