Upload 2 files
Browse files- src/api/agent.py +17 -159
- src/api/search.py +137 -316
src/api/agent.py
CHANGED
|
@@ -112,9 +112,6 @@ class AgentResponse(BaseModel):
|
|
| 112 |
ai_tool_query: Optional[str] = None
|
| 113 |
primo_boolean_query: Optional[str] = None
|
| 114 |
primo_search_url: Optional[str] = None
|
| 115 |
-
primo_ai_url: Optional[str] = None
|
| 116 |
-
pubmed_search_url: Optional[str] = None
|
| 117 |
-
contact_html: Optional[str] = None
|
| 118 |
|
| 119 |
|
| 120 |
# ββ Constants βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
|
@@ -203,10 +200,6 @@ CURRENT_INFO_RE = re.compile(
|
|
| 203 |
r"|news|update|updated|prime minister|ceo|minister|king|ruler|who won)\b",
|
| 204 |
re.IGNORECASE,
|
| 205 |
)
|
| 206 |
-
DATABASE_RECOMMENDATION_RE = re.compile(
|
| 207 |
-
r"\b(best database|best databases|which database|which databases|recommended databases?|database should i use|databases should i use|database for|databases for)\b",
|
| 208 |
-
re.IGNORECASE,
|
| 209 |
-
)
|
| 210 |
SUMMARY_RE = re.compile(
|
| 211 |
r"\b(summar(y|ize|ise|izing|ising)|overview|explain|what is|what are|describe"
|
| 212 |
r"|tell me about|give me a summary|give me an overview|give me a brief"
|
|
@@ -1038,125 +1031,29 @@ def _tool_urls(context: SearchContextPayload) -> Dict[str, str]:
|
|
| 1038 |
}
|
| 1039 |
|
| 1040 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1041 |
def _database_guidance_for_topic(context: SearchContextPayload) -> str:
|
| 1042 |
topic = _escape(context.display_topic or context.topic)
|
|
|
|
| 1043 |
if context.intent == "search_medical":
|
| 1044 |
return (
|
| 1045 |
-
f"For
|
| 1046 |
-
"
|
| 1047 |
-
"Some freemium tools may require account creation."
|
| 1048 |
)
|
| 1049 |
return (
|
| 1050 |
-
f"For deeper
|
| 1051 |
-
"
|
| 1052 |
-
"
|
| 1053 |
-
)
|
| 1054 |
-
|
| 1055 |
-
|
| 1056 |
-
def _is_database_recommendation_question(question: str) -> bool:
|
| 1057 |
-
return bool(DATABASE_RECOMMENDATION_RE.search(question or ""))
|
| 1058 |
-
|
| 1059 |
-
|
| 1060 |
-
def _primary_contact_for_question(question: str, intent: str) -> dict:
|
| 1061 |
-
q = (question or '').lower()
|
| 1062 |
-
walter = {
|
| 1063 |
-
'label': 'Systems & website support',
|
| 1064 |
-
'name': 'Walter Brian Hall',
|
| 1065 |
-
'role': 'Digital & Technology Services Librarian / Systems Librarian',
|
| 1066 |
-
'email': 'walter.hall@ku.ac.ae',
|
| 1067 |
-
'phone': '+971 2 312 3163',
|
| 1068 |
-
}
|
| 1069 |
-
rani = {
|
| 1070 |
-
'label': 'E-resources support',
|
| 1071 |
-
'name': 'Rani Anand',
|
| 1072 |
-
'role': 'E-Resources Librarian',
|
| 1073 |
-
'email': 'rani.anand@ku.ac.ae',
|
| 1074 |
-
'phone': '+971 2 312 3935',
|
| 1075 |
-
}
|
| 1076 |
-
nikesh = {
|
| 1077 |
-
'label': 'Research support',
|
| 1078 |
-
'name': 'Nikesh Narayanan',
|
| 1079 |
-
'role': 'Research & Access Services Librarian',
|
| 1080 |
-
'email': 'nikesh.narayanan@ku.ac.ae',
|
| 1081 |
-
'phone': '+971 2 312 3980',
|
| 1082 |
-
}
|
| 1083 |
-
muna = {
|
| 1084 |
-
'label': 'Public services',
|
| 1085 |
-
'name': 'Muna Ahmad Mohammad Al Blooshi',
|
| 1086 |
-
'role': 'Manager, Public Services',
|
| 1087 |
-
'email': 'muna.alblooshi@ku.ac.ae',
|
| 1088 |
-
'phone': '+971 2 312 4212',
|
| 1089 |
-
}
|
| 1090 |
-
|
| 1091 |
-
if any(t in q for t in ['system', 'systems', 'website', 'web site', 'technical', 'technology', 'digital', 'error', 'bug', 'broken page', 'page not loading']):
|
| 1092 |
-
return walter
|
| 1093 |
-
if any(t in q for t in ['database access', 'off campus', 'remote access', 'proxy', 'login problem', 'login issue', 'cannot access', "can't access", 'full text', 'libkey', 'vendor', 'e-resource', 'eresource', 'subscription access']):
|
| 1094 |
-
return rani
|
| 1095 |
-
if intent in {'search_academic', 'search_medical'} or any(t in q for t in ['research', 'literature', 'systematic review', 'orcid', 'open access', 'apc', 'bibliometric', 'scopus', 'scival', 'impact', 'citation', 'ai tool', 'best database', 'best databases', 'which database', 'which databases']):
|
| 1096 |
-
return nikesh
|
| 1097 |
-
return muna
|
| 1098 |
-
|
| 1099 |
-
|
| 1100 |
-
def _contact_footer_html(question: str, intent: str) -> str:
|
| 1101 |
-
primary = _primary_contact_for_question(question, intent)
|
| 1102 |
-
return (
|
| 1103 |
-
'<div style="margin-top:14px;padding:12px 14px;background:#f8fafc;border:1px solid #dbeafe;border-radius:12px;font-size:.8rem;line-height:1.6">'
|
| 1104 |
-
'<strong>Library contact points</strong><br>'
|
| 1105 |
-
f'General help: <a href="{ASK_LIBRARIAN_URL}" target="_blank" style="color:#003366;font-weight:700">Ask a Librarian</a> Β· '
|
| 1106 |
-
'<a href="mailto:libse@ku.ac.ae" style="color:#003366">libse@ku.ac.ae</a><br>'
|
| 1107 |
-
f'{_escape(primary["label"])}: <strong>{_escape(primary["name"])}</strong> β {_escape(primary["role"])} Β· '
|
| 1108 |
-
f'<a href="mailto:{primary["email"]}" style="color:#003366">{_escape(primary["email"])}</a> Β· '
|
| 1109 |
-
f'<a href="tel:{primary["phone"].replace(" ", "")}" style="color:#003366">{_escape(primary["phone"])}</a>'
|
| 1110 |
-
'</div>'
|
| 1111 |
-
)
|
| 1112 |
-
|
| 1113 |
-
|
| 1114 |
-
async def _database_recommendation_answer(question: str, history: List[ChatMessage], model: str) -> Tuple[str, List[dict]]:
|
| 1115 |
-
try:
|
| 1116 |
-
from app import rag_service
|
| 1117 |
-
rag_query = f"{question} recommended databases by subject Khalifa University Library databases"
|
| 1118 |
-
rag_results = await rag_service.hybrid_search(rag_query, top_k=5)
|
| 1119 |
-
except Exception as e:
|
| 1120 |
-
logger.error(f"Database recommendation search failed: {e}")
|
| 1121 |
-
rag_results = []
|
| 1122 |
-
|
| 1123 |
-
if not rag_results:
|
| 1124 |
-
answer = (
|
| 1125 |
-
'I could not pull the subject database guidance from the library knowledge base right now.<br><br>'
|
| 1126 |
-
'A good general starting point is <strong>PRIMO Library Discovery</strong>, then move to subject databases such as Scopus, Web of Science, IEEE Xplore, ACM Digital Library, PubMed, or Embase depending on your topic.'
|
| 1127 |
-
)
|
| 1128 |
-
return answer + _source_badge('ku_library', 'https://library.ku.ac.ae/eresources'), []
|
| 1129 |
-
|
| 1130 |
-
context_text = "\n\n---\n\n".join(r['content'] for r in rag_results)
|
| 1131 |
-
settings = get_settings()
|
| 1132 |
-
if not settings.openai_api_key:
|
| 1133 |
-
answer = 'I found KU Library database guidance for this subject in the knowledge base.'
|
| 1134 |
-
answer += _source_badge('rag', 'https://library.ku.ac.ae/eresources')
|
| 1135 |
-
sources = [{'title': r.get('title', 'Library guide'), 'url': r.get('source', '')} for r in rag_results if r.get('source')]
|
| 1136 |
-
return answer, sources
|
| 1137 |
-
|
| 1138 |
-
system = (
|
| 1139 |
-
'You are LibBee, the Khalifa University Library AI Assistant. '
|
| 1140 |
-
'Answer as an expert academic librarian using ONLY the context provided. '
|
| 1141 |
-
"Recommend the best KU databases for the user's subject. "
|
| 1142 |
-
'Start with one short sentence. Then list 3 to 6 databases using HTML <br>, with each database name in <strong> and a brief explanation of why or when to use it. '
|
| 1143 |
-
'Where appropriate, include PRIMO Library Discovery as a starting point and then subject-specific databases. '
|
| 1144 |
-
'End with one short sentence offering to search directly in PRIMO Library Discovery.'
|
| 1145 |
)
|
| 1146 |
-
try:
|
| 1147 |
-
llm = _get_llm(model, temperature=0.2, max_tokens=420)
|
| 1148 |
-
response = await llm.ainvoke([
|
| 1149 |
-
{'role': 'system', 'content': system + "\n\nCONTEXT:\n" + context_text},
|
| 1150 |
-
{'role': 'user', 'content': question},
|
| 1151 |
-
])
|
| 1152 |
-
answer = response.content.strip()
|
| 1153 |
-
except Exception as e:
|
| 1154 |
-
logger.error(f"Database recommendation answer failed: {e}")
|
| 1155 |
-
answer = 'I found subject-specific database guidance in the library knowledge base, but I had trouble formatting it into a recommendation right now.'
|
| 1156 |
-
|
| 1157 |
-
answer += _source_badge('rag', 'https://library.ku.ac.ae/eresources')
|
| 1158 |
-
sources = [{'title': r.get('title', 'Library guide'), 'url': r.get('source', '')} for r in rag_results if r.get('source')]
|
| 1159 |
-
return answer, sources
|
| 1160 |
|
| 1161 |
|
| 1162 |
# ββ Research Snapshot βββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
|
@@ -1379,7 +1276,7 @@ async def _generate_topic_follow_ups(topic: str, model: str) -> List[dict]:
|
|
| 1379 |
if not isinstance(questions, list):
|
| 1380 |
return []
|
| 1381 |
return [
|
| 1382 |
-
{"label": q.strip("?") + "?", "question":
|
| 1383 |
for q in questions[:3]
|
| 1384 |
if isinstance(q, str) and q.strip()
|
| 1385 |
]
|
|
@@ -1619,7 +1516,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1619 |
response_time=time.time() - start_time,
|
| 1620 |
follow_up_question=follow_up_question,
|
| 1621 |
follow_up_suggestions=follow_up_suggestions,
|
| 1622 |
-
contact_html=_contact_footer_html(question, "library_info"),
|
| 1623 |
)
|
| 1624 |
|
| 1625 |
staff_role_match = match_staff_role(question) if should_attempt_staff_lookup(question) else None
|
|
@@ -1634,7 +1530,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1634 |
response_time=time.time() - start_time,
|
| 1635 |
follow_up_question=follow_up_question,
|
| 1636 |
follow_up_suggestions=follow_up_suggestions,
|
| 1637 |
-
contact_html=_contact_footer_html(question, "library_info"),
|
| 1638 |
)
|
| 1639 |
|
| 1640 |
if _is_greeting_menu_followup(question, history):
|
|
@@ -1660,7 +1555,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1660 |
response_time=time.time() - start_time,
|
| 1661 |
follow_up_question=follow_up_question,
|
| 1662 |
follow_up_suggestions=follow_up_suggestions,
|
| 1663 |
-
contact_html=_contact_footer_html(question, "library_info"),
|
| 1664 |
)
|
| 1665 |
|
| 1666 |
if _looks_campus_question(question):
|
|
@@ -1674,27 +1568,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1674 |
response_time=time.time() - start_time,
|
| 1675 |
follow_up_question=follow_up_question,
|
| 1676 |
follow_up_suggestions=follow_up_suggestions,
|
| 1677 |
-
contact_html=_contact_footer_html(question, "library_info"),
|
| 1678 |
-
)
|
| 1679 |
-
|
| 1680 |
-
if _is_database_recommendation_question(question):
|
| 1681 |
-
answer, sources = await _database_recommendation_answer(question, history, model)
|
| 1682 |
-
follow_up_question = "Would you like me to search one of these databases directly or show the AI research tools for this topic?"
|
| 1683 |
-
follow_up_suggestions = [
|
| 1684 |
-
{"label": "Search PRIMO Library Discovery", "question": "Search PRIMO Library Discovery for this topic"},
|
| 1685 |
-
{"label": "Show AI research tools", "question": "Show the AI research tools for this topic"},
|
| 1686 |
-
]
|
| 1687 |
-
return AgentResponse(
|
| 1688 |
-
answer=answer,
|
| 1689 |
-
intent="library_info",
|
| 1690 |
-
tools_used=["database_recommendation_rag"],
|
| 1691 |
-
sources=sources,
|
| 1692 |
-
ask_librarian=False,
|
| 1693 |
-
model_used=model,
|
| 1694 |
-
response_time=time.time() - start_time,
|
| 1695 |
-
follow_up_question=follow_up_question,
|
| 1696 |
-
follow_up_suggestions=follow_up_suggestions,
|
| 1697 |
-
contact_html=_contact_footer_html(question, "library_info"),
|
| 1698 |
)
|
| 1699 |
|
| 1700 |
is_follow_up, follow_up_action, base_context = _detect_follow_up(question, client_state)
|
|
@@ -1735,9 +1608,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1735 |
follow_up_suggestions=follow_up_suggestions,
|
| 1736 |
search_context=_context_to_dict(context),
|
| 1737 |
is_follow_up=True,
|
| 1738 |
-
primo_ai_url=f"{PRIMO_AI_URL}{quote(context.ai_tool_query or context.topic)}",
|
| 1739 |
-
pubmed_search_url=(f"https://pubmed.ncbi.nlm.nih.gov/?term={quote(context.topic)}" if context.intent == "search_medical" else None),
|
| 1740 |
-
contact_html=_contact_footer_html(question, context.intent),
|
| 1741 |
)
|
| 1742 |
|
| 1743 |
answer, search_results, sources, source_url = await _run_search_mode(question, context, model, True)
|
|
@@ -1760,9 +1630,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1760 |
follow_up_suggestions=follow_up_suggestions,
|
| 1761 |
search_context=_context_to_dict(context),
|
| 1762 |
is_follow_up=True,
|
| 1763 |
-
primo_ai_url=f"{PRIMO_AI_URL}{quote(context.ai_tool_query or context.topic)}",
|
| 1764 |
-
pubmed_search_url=(f"https://pubmed.ncbi.nlm.nih.gov/?term={quote(context.topic)}" if context.intent == "search_medical" else None),
|
| 1765 |
-
contact_html=_contact_footer_html(question, context.intent),
|
| 1766 |
)
|
| 1767 |
|
| 1768 |
cls_result = await _llm_classify(question, history, model)
|
|
@@ -1818,7 +1685,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1818 |
response_time=time.time() - start_time,
|
| 1819 |
follow_up_question=follow_up_question,
|
| 1820 |
follow_up_suggestions=follow_up_suggestions,
|
| 1821 |
-
contact_html=_contact_footer_html(question, "library_info"),
|
| 1822 |
)
|
| 1823 |
|
| 1824 |
if intent in ("search_academic", "search_medical"):
|
|
@@ -1868,9 +1734,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1868 |
follow_up_question=follow_up_question,
|
| 1869 |
follow_up_suggestions=follow_up_suggestions,
|
| 1870 |
search_context=_context_to_dict(context),
|
| 1871 |
-
primo_ai_url=f"{PRIMO_AI_URL}{quote(context.ai_tool_query or context.topic)}",
|
| 1872 |
-
pubmed_search_url=(f"https://pubmed.ncbi.nlm.nih.gov/?term={quote(context.topic)}" if intent == "search_medical" else None),
|
| 1873 |
-
contact_html=_contact_footer_html(question, intent),
|
| 1874 |
)
|
| 1875 |
|
| 1876 |
answer, search_results, sources, source_url = await _run_search_mode(question, context, model, False)
|
|
@@ -1892,9 +1755,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1892 |
follow_up_question=follow_up_question,
|
| 1893 |
follow_up_suggestions=follow_up_suggestions,
|
| 1894 |
search_context=_context_to_dict(context),
|
| 1895 |
-
primo_ai_url=f"{PRIMO_AI_URL}{quote(context.ai_tool_query or context.topic)}",
|
| 1896 |
-
pubmed_search_url=(f"https://pubmed.ncbi.nlm.nih.gov/?term={quote(context.topic)}" if intent == "search_medical" else None),
|
| 1897 |
-
contact_html=_contact_footer_html(question, intent),
|
| 1898 |
)
|
| 1899 |
|
| 1900 |
if intent == "general_recent":
|
|
@@ -1908,7 +1768,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1908 |
response_time=time.time() - start_time,
|
| 1909 |
follow_up_question=follow_up_question,
|
| 1910 |
follow_up_suggestions=follow_up_suggestions,
|
| 1911 |
-
contact_html=_contact_footer_html(question, "general_recent"),
|
| 1912 |
)
|
| 1913 |
|
| 1914 |
answer = await _web_search_answer(question, history, model) + _source_badge("web")
|
|
@@ -1921,7 +1780,6 @@ async def agent_query(request: Request, req: AgentRequest):
|
|
| 1921 |
response_time=time.time() - start_time,
|
| 1922 |
follow_up_question=follow_up_question,
|
| 1923 |
follow_up_suggestions=follow_up_suggestions,
|
| 1924 |
-
contact_html=_contact_footer_html(question, "general"),
|
| 1925 |
)
|
| 1926 |
|
| 1927 |
|
|
|
|
| 112 |
ai_tool_query: Optional[str] = None
|
| 113 |
primo_boolean_query: Optional[str] = None
|
| 114 |
primo_search_url: Optional[str] = None
|
|
|
|
|
|
|
|
|
|
| 115 |
|
| 116 |
|
| 117 |
# ββ Constants βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
|
|
|
| 200 |
r"|news|update|updated|prime minister|ceo|minister|king|ruler|who won)\b",
|
| 201 |
re.IGNORECASE,
|
| 202 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
SUMMARY_RE = re.compile(
|
| 204 |
r"\b(summar(y|ize|ise|izing|ising)|overview|explain|what is|what are|describe"
|
| 205 |
r"|tell me about|give me a summary|give me an overview|give me a brief"
|
|
|
|
| 1031 |
}
|
| 1032 |
|
| 1033 |
|
| 1034 |
+
def _ai_source_links_html(context: SearchContextPayload) -> str:
|
| 1035 |
+
urls = _tool_urls(context)
|
| 1036 |
+
return (
|
| 1037 |
+
f'<a href="{urls["leapspace"]}" target="_blank" style="color:#9a3412;font-weight:700;text-decoration:none">LeapSpace</a> Β· '
|
| 1038 |
+
f'<a href="{urls["scopus_ai"]}" target="_blank" style="color:#1e40af;font-weight:700;text-decoration:none">Scopus AI</a> Β· '
|
| 1039 |
+
f'<a href="{urls["consensus"]}" target="_blank" style="color:#86198f;font-weight:700;text-decoration:none">Consensus</a> Β· '
|
| 1040 |
+
f'<a href="{urls["primo_discovery"]}" target="_blank" style="color:#5b21b6;font-weight:700;text-decoration:none">PRIMO Library Discovery</a>'
|
| 1041 |
+
)
|
| 1042 |
+
|
| 1043 |
+
|
| 1044 |
def _database_guidance_for_topic(context: SearchContextPayload) -> str:
|
| 1045 |
topic = _escape(context.display_topic or context.topic)
|
| 1046 |
+
links = _ai_source_links_html(context)
|
| 1047 |
if context.intent == "search_medical":
|
| 1048 |
return (
|
| 1049 |
+
f"For a stronger evidence trail on <strong>{topic}</strong>, start with <strong>PubMed</strong> or <strong>Embase</strong> for the core medical literature, "
|
| 1050 |
+
f"then continue with {links}."
|
|
|
|
| 1051 |
)
|
| 1052 |
return (
|
| 1053 |
+
f"For deeper work on <strong>{topic}</strong>, continue with {links}. "
|
| 1054 |
+
"Use Scopus AI for broader scholarly mapping, LeapSpace for guided evidence exploration, "
|
| 1055 |
+
"Consensus for quick paper-grounded answers, and PRIMO Library Discovery for KU-accessible material."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1056 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1057 |
|
| 1058 |
|
| 1059 |
# ββ Research Snapshot βββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
|
|
|
| 1276 |
if not isinstance(questions, list):
|
| 1277 |
return []
|
| 1278 |
return [
|
| 1279 |
+
{"label": q.strip("?") + "?", "question": q.strip("?") + " β find articles", "action": "new_search"}
|
| 1280 |
for q in questions[:3]
|
| 1281 |
if isinstance(q, str) and q.strip()
|
| 1282 |
]
|
|
|
|
| 1516 |
response_time=time.time() - start_time,
|
| 1517 |
follow_up_question=follow_up_question,
|
| 1518 |
follow_up_suggestions=follow_up_suggestions,
|
|
|
|
| 1519 |
)
|
| 1520 |
|
| 1521 |
staff_role_match = match_staff_role(question) if should_attempt_staff_lookup(question) else None
|
|
|
|
| 1530 |
response_time=time.time() - start_time,
|
| 1531 |
follow_up_question=follow_up_question,
|
| 1532 |
follow_up_suggestions=follow_up_suggestions,
|
|
|
|
| 1533 |
)
|
| 1534 |
|
| 1535 |
if _is_greeting_menu_followup(question, history):
|
|
|
|
| 1555 |
response_time=time.time() - start_time,
|
| 1556 |
follow_up_question=follow_up_question,
|
| 1557 |
follow_up_suggestions=follow_up_suggestions,
|
|
|
|
| 1558 |
)
|
| 1559 |
|
| 1560 |
if _looks_campus_question(question):
|
|
|
|
| 1568 |
response_time=time.time() - start_time,
|
| 1569 |
follow_up_question=follow_up_question,
|
| 1570 |
follow_up_suggestions=follow_up_suggestions,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1571 |
)
|
| 1572 |
|
| 1573 |
is_follow_up, follow_up_action, base_context = _detect_follow_up(question, client_state)
|
|
|
|
| 1608 |
follow_up_suggestions=follow_up_suggestions,
|
| 1609 |
search_context=_context_to_dict(context),
|
| 1610 |
is_follow_up=True,
|
|
|
|
|
|
|
|
|
|
| 1611 |
)
|
| 1612 |
|
| 1613 |
answer, search_results, sources, source_url = await _run_search_mode(question, context, model, True)
|
|
|
|
| 1630 |
follow_up_suggestions=follow_up_suggestions,
|
| 1631 |
search_context=_context_to_dict(context),
|
| 1632 |
is_follow_up=True,
|
|
|
|
|
|
|
|
|
|
| 1633 |
)
|
| 1634 |
|
| 1635 |
cls_result = await _llm_classify(question, history, model)
|
|
|
|
| 1685 |
response_time=time.time() - start_time,
|
| 1686 |
follow_up_question=follow_up_question,
|
| 1687 |
follow_up_suggestions=follow_up_suggestions,
|
|
|
|
| 1688 |
)
|
| 1689 |
|
| 1690 |
if intent in ("search_academic", "search_medical"):
|
|
|
|
| 1734 |
follow_up_question=follow_up_question,
|
| 1735 |
follow_up_suggestions=follow_up_suggestions,
|
| 1736 |
search_context=_context_to_dict(context),
|
|
|
|
|
|
|
|
|
|
| 1737 |
)
|
| 1738 |
|
| 1739 |
answer, search_results, sources, source_url = await _run_search_mode(question, context, model, False)
|
|
|
|
| 1755 |
follow_up_question=follow_up_question,
|
| 1756 |
follow_up_suggestions=follow_up_suggestions,
|
| 1757 |
search_context=_context_to_dict(context),
|
|
|
|
|
|
|
|
|
|
| 1758 |
)
|
| 1759 |
|
| 1760 |
if intent == "general_recent":
|
|
|
|
| 1768 |
response_time=time.time() - start_time,
|
| 1769 |
follow_up_question=follow_up_question,
|
| 1770 |
follow_up_suggestions=follow_up_suggestions,
|
|
|
|
| 1771 |
)
|
| 1772 |
|
| 1773 |
answer = await _web_search_answer(question, history, model) + _source_badge("web")
|
|
|
|
| 1780 |
response_time=time.time() - start_time,
|
| 1781 |
follow_up_question=follow_up_question,
|
| 1782 |
follow_up_suggestions=follow_up_suggestions,
|
|
|
|
| 1783 |
)
|
| 1784 |
|
| 1785 |
|
src/api/search.py
CHANGED
|
@@ -1,6 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import logging
|
| 2 |
-
import
|
| 3 |
-
from typing import Optional, List, Dict
|
| 4 |
from urllib.parse import quote
|
| 5 |
|
| 6 |
import httpx
|
|
@@ -12,68 +20,6 @@ from src.config import get_settings
|
|
| 12 |
logger = logging.getLogger(__name__)
|
| 13 |
router = APIRouter()
|
| 14 |
|
| 15 |
-
PRIMO_BASE_URL = "https://khalifa.primo.exlibrisgroup.com/discovery/search?vid=971KUOSTAR_INST:KU"
|
| 16 |
-
PRIMO_AI_URL = "https://khalifa.primo.exlibrisgroup.com/discovery/researchAssistant?vid=971KUOSTAR_INST:KU&query="
|
| 17 |
-
|
| 18 |
-
_RESOURCE_NOISE_RE = re.compile(
|
| 19 |
-
r"\b(articles?|papers?|books?|ebooks?|journals?|publications?|monographs?"
|
| 20 |
-
r"|peer[- ]reviewed|open[- ]access|studies|study|research|latest|recent|current"
|
| 21 |
-
r"|summary|summarize|summarise|overview|brief|analysis|review|deep|dive)\b",
|
| 22 |
-
re.IGNORECASE,
|
| 23 |
-
)
|
| 24 |
-
|
| 25 |
-
_MEDICAL_HINT_RE = re.compile(
|
| 26 |
-
r"\b(pubmed|embase|cinahl|clinicalkey|cochrane|uptodate|medline|medicine|medical|health|clinical|nursing|pharmacy|biomedical|disease|therapy|treatment|diagnosis|patient|cancer|diabetes|epidemiology|oncology|cardiology)\b",
|
| 27 |
-
re.IGNORECASE,
|
| 28 |
-
)
|
| 29 |
-
|
| 30 |
-
_PREFIXES = [
|
| 31 |
-
"summarize the latest studies in ", "summarize latest studies in ",
|
| 32 |
-
"summarize the latest research on ", "summarize latest research on ",
|
| 33 |
-
"summarize recent studies in ", "summarize recent research on ",
|
| 34 |
-
"latest studies in ", "latest research on ", "recent studies in ", "recent research on ",
|
| 35 |
-
"give me a summary of ", "give me an overview of ", "give me a brief on ",
|
| 36 |
-
"give me articles on ", "peer reviewed papers on ", "peer-reviewed papers on ", "peer reviewed articles on ", "peer-reviewed articles on ",
|
| 37 |
-
"find peer reviewed articles on ", "find peer-reviewed articles on ",
|
| 38 |
-
"find articles on ", "find papers on ", "find books on ",
|
| 39 |
-
"search for articles on ", "search for papers on ", "look for articles on ",
|
| 40 |
-
"i need articles on ", "i need books on ", "research on ", "literature on ",
|
| 41 |
-
"tell me about ", "explain ", "what is ", "what are ",
|
| 42 |
-
]
|
| 43 |
-
|
| 44 |
-
PHRASE_SYNONYMS: List[tuple[str, List[str]]] = [
|
| 45 |
-
("global warming", ["climate change"]),
|
| 46 |
-
("climate change", ["global warming"]),
|
| 47 |
-
("machine learning", ["artificial intelligence", "AI"]),
|
| 48 |
-
("artificial intelligence", ["AI", "machine learning"]),
|
| 49 |
-
("higher education", ["universities", "tertiary education"]),
|
| 50 |
-
("university libraries", ["academic libraries", "academic library"]),
|
| 51 |
-
("university library", ["academic library"]),
|
| 52 |
-
("renewable energy", ["sustainable energy", "clean energy"]),
|
| 53 |
-
("solar energy", ["solar power", "photovoltaics"]),
|
| 54 |
-
("cyber security", ["cybersecurity", "information security"]),
|
| 55 |
-
("internet of things", ["IoT"]),
|
| 56 |
-
("big data", ["data analytics"]),
|
| 57 |
-
("public health", ["population health"]),
|
| 58 |
-
("gene editing", ["CRISPR", "genome editing"]),
|
| 59 |
-
("mental health", ["psychological wellbeing", "wellbeing"]),
|
| 60 |
-
("supply chain", ["logistics"]),
|
| 61 |
-
("academic writing", ["scholarly writing"]),
|
| 62 |
-
]
|
| 63 |
-
|
| 64 |
-
TOKEN_SYNONYMS: Dict[str, List[str]] = {
|
| 65 |
-
"healthcare": ["medicine", "clinical"],
|
| 66 |
-
"agriculture": ["farming"],
|
| 67 |
-
"education": ["teaching", "learning"],
|
| 68 |
-
"student": ["students"],
|
| 69 |
-
"students": ["student"],
|
| 70 |
-
"library": ["libraries"],
|
| 71 |
-
"libraries": ["library"],
|
| 72 |
-
"energy": ["power"],
|
| 73 |
-
"sustainability": ["sustainable development"],
|
| 74 |
-
"older": ["aging"],
|
| 75 |
-
}
|
| 76 |
-
|
| 77 |
|
| 78 |
class SearchRequest(BaseModel):
|
| 79 |
query: str
|
|
@@ -83,8 +29,8 @@ class SearchRequest(BaseModel):
|
|
| 83 |
open_access: bool = False
|
| 84 |
year_from: Optional[str] = None
|
| 85 |
year_to: Optional[str] = None
|
| 86 |
-
resource_type
|
| 87 |
-
|
| 88 |
|
| 89 |
@field_validator("query")
|
| 90 |
@classmethod
|
|
@@ -114,21 +60,12 @@ class SearchRequest(BaseModel):
|
|
| 114 |
@field_validator("resource_type")
|
| 115 |
@classmethod
|
| 116 |
def valid_resource_type(cls, v: str) -> str:
|
| 117 |
-
|
|
|
|
| 118 |
return "articles"
|
| 119 |
return v
|
| 120 |
|
| 121 |
|
| 122 |
-
class SearchPlanRequest(BaseModel):
|
| 123 |
-
question: str
|
| 124 |
-
peer_reviewed: bool = False
|
| 125 |
-
open_access: bool = False
|
| 126 |
-
year_from: Optional[str] = None
|
| 127 |
-
year_to: Optional[str] = None
|
| 128 |
-
resource_type: Optional[str] = None
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
def _safe_metrics_increment(key: str) -> None:
|
| 133 |
try:
|
| 134 |
from app import metrics_service
|
|
@@ -145,196 +82,6 @@ def _safe_metrics_bucket(bucket: str, key: str) -> None:
|
|
| 145 |
return
|
| 146 |
|
| 147 |
|
| 148 |
-
def _normalize(text: str) -> str:
|
| 149 |
-
return re.sub(r"\s+", " ", (text or "").strip())
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
def strip_resource_noise(query: str) -> str:
|
| 153 |
-
cleaned = _RESOURCE_NOISE_RE.sub(" ", query or "")
|
| 154 |
-
cleaned = re.sub(r"\b(last|past)\s+\d+\s+years?\b", " ", cleaned, flags=re.IGNORECASE)
|
| 155 |
-
cleaned = re.sub(r"\b(19\d{2}|20\d{2})\b", " ", cleaned)
|
| 156 |
-
cleaned = re.sub(r"\s+(AND|OR)\s+(AND|OR)\s+", " AND ", cleaned, flags=re.IGNORECASE)
|
| 157 |
-
cleaned = re.sub(r"^\s*(AND|OR)\s+", "", cleaned, flags=re.IGNORECASE)
|
| 158 |
-
cleaned = re.sub(r"\s+(AND|OR)\s*$", "", cleaned, flags=re.IGNORECASE)
|
| 159 |
-
return _normalize(cleaned).strip(".?,")
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
def _light_correct_question(question: str) -> str:
|
| 163 |
-
q = _normalize(question)
|
| 164 |
-
q = re.sub(r"\bpeer reviewd\b", "peer reviewed", q, flags=re.IGNORECASE)
|
| 165 |
-
q = re.sub(r"\bpubmedd\b", "PubMed", q, flags=re.IGNORECASE)
|
| 166 |
-
q = q.rstrip(".?")
|
| 167 |
-
if q and not q.endswith("."):
|
| 168 |
-
q += "."
|
| 169 |
-
return q
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
def extract_topic_from_question(question: str) -> str:
|
| 173 |
-
q = _normalize(question)
|
| 174 |
-
lower = q.lower()
|
| 175 |
-
for prefix in _PREFIXES:
|
| 176 |
-
if lower.startswith(prefix):
|
| 177 |
-
q = q[len(prefix):]
|
| 178 |
-
break
|
| 179 |
-
q = strip_resource_noise(q)
|
| 180 |
-
q = re.sub(r"^(on|about|for)\s+", "", q, flags=re.IGNORECASE)
|
| 181 |
-
return _normalize(q).strip(".?") or _normalize(question).strip(".?")
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
def derive_resource_type(question: str, explicit: Optional[str] = None) -> str:
|
| 185 |
-
if explicit in {"articles", "books", "both"}:
|
| 186 |
-
return explicit
|
| 187 |
-
q = (question or "").lower()
|
| 188 |
-
if any(t in q for t in ["book", "books", "ebook", "ebooks"]):
|
| 189 |
-
return "books"
|
| 190 |
-
if any(t in q for t in ["article", "articles", "paper", "papers", "journal", "journals", "study", "studies"]):
|
| 191 |
-
return "articles"
|
| 192 |
-
return "articles"
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
def is_medical_query(question: str, topic: str = "") -> bool:
|
| 196 |
-
return bool(_MEDICAL_HINT_RE.search(f"{question} {topic}"))
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
def _quote_term(term: str) -> str:
|
| 200 |
-
term = _normalize(term)
|
| 201 |
-
if not term:
|
| 202 |
-
return ""
|
| 203 |
-
if re.fullmatch(r"[A-Z]{2,6}", term):
|
| 204 |
-
return term
|
| 205 |
-
if re.fullmatch(r"[A-Za-z0-9_-]+", term):
|
| 206 |
-
return f'"{term}"'
|
| 207 |
-
return f'"{term}"'
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
def _dedupe_keep_order(items: List[str]) -> List[str]:
|
| 211 |
-
seen = set()
|
| 212 |
-
out = []
|
| 213 |
-
for item in items:
|
| 214 |
-
norm = item.lower().strip()
|
| 215 |
-
if not norm or norm in seen:
|
| 216 |
-
continue
|
| 217 |
-
seen.add(norm)
|
| 218 |
-
out.append(item)
|
| 219 |
-
return out
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
def _build_concept_groups(topic: str) -> List[List[str]]:
|
| 223 |
-
work = f" {_normalize(topic).lower()} "
|
| 224 |
-
groups: List[List[str]] = []
|
| 225 |
-
phrase_keys = sorted(PHRASE_SYNONYMS, key=lambda x: len(x[0]), reverse=True)
|
| 226 |
-
for phrase, syns in phrase_keys:
|
| 227 |
-
needle = f" {phrase} "
|
| 228 |
-
if needle in work:
|
| 229 |
-
groups.append(_dedupe_keep_order([phrase] + syns))
|
| 230 |
-
work = work.replace(needle, " ")
|
| 231 |
-
|
| 232 |
-
leftovers = [w for w in re.findall(r"[a-z0-9]+", work) if len(w) > 2 and w not in {
|
| 233 |
-
"and", "or", "for", "with", "from", "into", "onto", "about", "using", "based", "among",
|
| 234 |
-
"between", "effects", "effect", "impact", "role", "use", "uses", "application", "applications",
|
| 235 |
-
}]
|
| 236 |
-
for token in leftovers:
|
| 237 |
-
groups.append(_dedupe_keep_order([token] + TOKEN_SYNONYMS.get(token, [])))
|
| 238 |
-
|
| 239 |
-
if not groups:
|
| 240 |
-
cleaned = strip_resource_noise(topic)
|
| 241 |
-
if cleaned:
|
| 242 |
-
groups = [[cleaned]]
|
| 243 |
-
return groups
|
| 244 |
-
|
| 245 |
-
|
| 246 |
-
def build_boolean_query(topic: str) -> str:
|
| 247 |
-
groups = _build_concept_groups(topic)
|
| 248 |
-
parts = []
|
| 249 |
-
for group in groups[:4]:
|
| 250 |
-
tokens = [_quote_term(term) for term in group if term]
|
| 251 |
-
tokens = [t for t in tokens if t]
|
| 252 |
-
if not tokens:
|
| 253 |
-
continue
|
| 254 |
-
if len(tokens) == 1:
|
| 255 |
-
parts.append(f"({tokens[0]})")
|
| 256 |
-
else:
|
| 257 |
-
parts.append("(" + " OR ".join(tokens) + ")")
|
| 258 |
-
return " AND ".join(parts) if parts else f'({_quote_term(topic)})'
|
| 259 |
-
|
| 260 |
-
|
| 261 |
-
def build_pubmed_url(query: str, year_from: Optional[str] = None, year_to: Optional[str] = None) -> str:
|
| 262 |
-
url = f"https://pubmed.ncbi.nlm.nih.gov/?term={quote(strip_resource_noise(query) or query)}"
|
| 263 |
-
if year_from or year_to:
|
| 264 |
-
yf = year_from or "1900"
|
| 265 |
-
yt = year_to or "3000"
|
| 266 |
-
url += f"&filter=datesearch.y_custom&dates.from={yf}&dates.to={yt}"
|
| 267 |
-
return url
|
| 268 |
-
|
| 269 |
-
|
| 270 |
-
def build_primo_discovery_url(boolean_query: str, resource_type: str = "both", peer_reviewed: bool = False,
|
| 271 |
-
open_access: bool = False, year_from: Optional[str] = None, year_to: Optional[str] = None) -> str:
|
| 272 |
-
facets = []
|
| 273 |
-
if resource_type == "articles":
|
| 274 |
-
facets.append("rtype,include,articles")
|
| 275 |
-
tab = "CentralIndex"
|
| 276 |
-
scope = "CentralIndex"
|
| 277 |
-
elif resource_type == "books":
|
| 278 |
-
facets.append("rtype,include,books")
|
| 279 |
-
tab = "Everything"
|
| 280 |
-
scope = "MyInst_and_CI"
|
| 281 |
-
else:
|
| 282 |
-
tab = "Everything"
|
| 283 |
-
scope = "MyInst_and_CI"
|
| 284 |
-
if peer_reviewed:
|
| 285 |
-
facets.append("tlevel,include,peer_reviewed")
|
| 286 |
-
if open_access:
|
| 287 |
-
facets.append("tlevel,include,online_resources")
|
| 288 |
-
if year_from or year_to:
|
| 289 |
-
yf = year_from or "0001"
|
| 290 |
-
yt = year_to or "9999"
|
| 291 |
-
facets.append(f"searchcreationdate,include,{yf}|,|{yt}")
|
| 292 |
-
url = f"{PRIMO_BASE_URL}&query=any,contains,{quote(boolean_query)}&lang=en&mode=advanced&offset=0&tab={tab}&search_scope={scope}"
|
| 293 |
-
for facet in facets:
|
| 294 |
-
url += f"&facet={quote(facet)}"
|
| 295 |
-
return url
|
| 296 |
-
|
| 297 |
-
|
| 298 |
-
def build_search_plan(question: str, peer_reviewed: bool = False, open_access: bool = False,
|
| 299 |
-
year_from: Optional[str] = None, year_to: Optional[str] = None,
|
| 300 |
-
resource_type: Optional[str] = None) -> dict:
|
| 301 |
-
corrected_question = _light_correct_question(question)
|
| 302 |
-
topic = extract_topic_from_question(corrected_question)
|
| 303 |
-
resource = derive_resource_type(corrected_question, resource_type)
|
| 304 |
-
medical = is_medical_query(corrected_question, topic)
|
| 305 |
-
bool_query = build_boolean_query(topic)
|
| 306 |
-
all_url = build_primo_discovery_url(bool_query, "both", peer_reviewed, open_access, year_from, year_to)
|
| 307 |
-
art_url = build_primo_discovery_url(bool_query, "articles", peer_reviewed, open_access, year_from, year_to)
|
| 308 |
-
book_url = build_primo_discovery_url(bool_query, "books", peer_reviewed, open_access, year_from, year_to)
|
| 309 |
-
return {
|
| 310 |
-
"question": corrected_question,
|
| 311 |
-
"topic": topic,
|
| 312 |
-
"display_topic": topic,
|
| 313 |
-
"resource_type": resource,
|
| 314 |
-
"is_medical": medical,
|
| 315 |
-
"ai_tool_query": corrected_question,
|
| 316 |
-
"primo_boolean_query": bool_query,
|
| 317 |
-
"primo_all_url": all_url,
|
| 318 |
-
"primo_articles_url": art_url,
|
| 319 |
-
"primo_books_url": book_url,
|
| 320 |
-
"primo_ai_url": f"{PRIMO_AI_URL}{quote(corrected_question)}",
|
| 321 |
-
"pubmed_url": build_pubmed_url(topic, year_from, year_to) if medical else "",
|
| 322 |
-
"openalex_url": f"https://openalex.org/works?page=1&sort=relevance_score:desc&search.semantic={quote(corrected_question.strip().replace(' ', '+'))}",
|
| 323 |
-
}
|
| 324 |
-
|
| 325 |
-
|
| 326 |
-
@router.post("/plan")
|
| 327 |
-
async def search_plan_endpoint(req: SearchPlanRequest):
|
| 328 |
-
return build_search_plan(
|
| 329 |
-
req.question,
|
| 330 |
-
peer_reviewed=req.peer_reviewed,
|
| 331 |
-
open_access=req.open_access,
|
| 332 |
-
year_from=req.year_from,
|
| 333 |
-
year_to=req.year_to,
|
| 334 |
-
resource_type=req.resource_type,
|
| 335 |
-
)
|
| 336 |
-
|
| 337 |
-
|
| 338 |
@router.post("")
|
| 339 |
async def search_endpoint(req: SearchRequest):
|
| 340 |
_safe_metrics_increment("search_requests")
|
|
@@ -347,65 +94,80 @@ async def search_endpoint(req: SearchRequest):
|
|
| 347 |
return await search_scholar(req)
|
| 348 |
|
| 349 |
|
|
|
|
|
|
|
| 350 |
async def search_primo(req: SearchRequest, api_key: str):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 351 |
if not api_key:
|
| 352 |
logger.warning("PRIMO_API_KEY not configured")
|
| 353 |
_safe_metrics_bucket("errors", "primo_missing_api_key")
|
| 354 |
return {"error": "PRIMO_API_KEY not configured", "results": [], "source": "PRIMO"}
|
| 355 |
|
| 356 |
-
|
| 357 |
-
|
| 358 |
-
|
| 359 |
-
|
| 360 |
-
|
| 361 |
-
|
| 362 |
-
|
| 363 |
-
|
| 364 |
-
|
| 365 |
-
|
| 366 |
-
|
| 367 |
-
|
| 368 |
-
|
| 369 |
-
|
| 370 |
-
|
| 371 |
-
|
| 372 |
-
|
| 373 |
-
|
| 374 |
-
|
| 375 |
-
|
| 376 |
-
|
| 377 |
-
|
| 378 |
-
|
| 379 |
-
|
| 380 |
-
|
| 381 |
-
|
| 382 |
-
|
| 383 |
-
|
| 384 |
-
|
| 385 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 386 |
|
| 387 |
try:
|
| 388 |
async with httpx.AsyncClient(timeout=20) as client:
|
| 389 |
-
r = await client.get(
|
| 390 |
-
if r.status_code == 400 and use_boolean:
|
| 391 |
-
logger.warning("PRIMO rejected boolean query; falling back to clean keywords")
|
| 392 |
-
r = await client.get(make_url(clean_query), headers={"Accept": "application/json"})
|
| 393 |
-
actual_query = clean_query
|
| 394 |
logger.info("PRIMO status=%s", r.status_code)
|
| 395 |
if r.status_code != 200:
|
| 396 |
_safe_metrics_bucket("errors", f"primo_{r.status_code}")
|
| 397 |
return {"error": f"PRIMO API error: {r.status_code}", "results": [], "source": "PRIMO"}
|
|
|
|
| 398 |
data = r.json()
|
| 399 |
docs = data.get("docs", [])
|
| 400 |
-
display_query = req.boolean_query.strip() if req.boolean_query else clean_query
|
| 401 |
-
discovery_url = build_primo_discovery_url(
|
| 402 |
-
display_query,
|
| 403 |
-
req.resource_type,
|
| 404 |
-
req.peer_reviewed,
|
| 405 |
-
req.open_access,
|
| 406 |
-
req.year_from,
|
| 407 |
-
req.year_to,
|
| 408 |
-
)
|
| 409 |
results = []
|
| 410 |
for doc in docs[: req.limit]:
|
| 411 |
pnx = doc.get("pnx", {})
|
|
@@ -416,10 +178,18 @@ async def search_primo(req: SearchRequest, api_key: str):
|
|
| 416 |
"date": (d.get("date") or [""])[0],
|
| 417 |
"type": (d.get("type") or [""])[0],
|
| 418 |
"source": (d.get("source") or [""])[0],
|
| 419 |
-
"primo_url":
|
|
|
|
|
|
|
|
|
|
| 420 |
"_source": "PRIMO",
|
| 421 |
})
|
| 422 |
-
return {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 423 |
except httpx.TimeoutException:
|
| 424 |
_safe_metrics_bucket("errors", "primo_timeout")
|
| 425 |
return {"error": "PRIMO API timed out β please try again", "results": [], "source": "PRIMO"}
|
|
@@ -429,18 +199,58 @@ async def search_primo(req: SearchRequest, api_key: str):
|
|
| 429 |
return {"error": str(exc), "results": [], "source": "PRIMO"}
|
| 430 |
|
| 431 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 432 |
async def search_pubmed(req: SearchRequest):
|
| 433 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 434 |
term = clean_query
|
| 435 |
if req.peer_reviewed:
|
| 436 |
term = f"({term}) AND Journal Article[pt]"
|
|
|
|
| 437 |
query_encoded = quote(term)
|
|
|
|
|
|
|
| 438 |
date_params = ""
|
| 439 |
if req.year_from or req.year_to:
|
| 440 |
yf = req.year_from or "1900"
|
| 441 |
yt = req.year_to or "3000"
|
| 442 |
date_params = f"&mindate={yf}&maxdate={yt}&datetype=pdat"
|
| 443 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 444 |
try:
|
| 445 |
async with httpx.AsyncClient(timeout=15) as client:
|
| 446 |
search_url = (
|
|
@@ -451,9 +261,11 @@ async def search_pubmed(req: SearchRequest):
|
|
| 451 |
if r.status_code != 200:
|
| 452 |
_safe_metrics_bucket("errors", "pubmed_search_failed")
|
| 453 |
return {"error": "PubMed search failed", "results": [], "source": "PubMed"}
|
|
|
|
| 454 |
ids = r.json().get("esearchresult", {}).get("idlist", [])
|
| 455 |
if not ids:
|
| 456 |
return {"total": 0, "results": [], "source": "PubMed"}
|
|
|
|
| 457 |
fetch_url = (
|
| 458 |
f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi"
|
| 459 |
f"?db=pubmed&id={','.join(ids)}&retmode=json"
|
|
@@ -462,6 +274,7 @@ async def search_pubmed(req: SearchRequest):
|
|
| 462 |
if r2.status_code != 200:
|
| 463 |
_safe_metrics_bucket("errors", "pubmed_fetch_failed")
|
| 464 |
return {"error": "PubMed fetch failed", "results": [], "source": "PubMed"}
|
|
|
|
| 465 |
data = r2.json().get("result", {})
|
| 466 |
results = []
|
| 467 |
for pid in ids:
|
|
@@ -483,12 +296,15 @@ async def search_pubmed(req: SearchRequest):
|
|
| 483 |
"_source": "PubMed",
|
| 484 |
})
|
| 485 |
return {"total": len(ids), "results": results, "source": "PubMed"}
|
|
|
|
| 486 |
except Exception as exc:
|
| 487 |
logger.error("PubMed search error: %s", exc)
|
| 488 |
_safe_metrics_bucket("errors", "pubmed_exception")
|
| 489 |
return {"error": str(exc), "results": [], "source": "PubMed"}
|
| 490 |
|
| 491 |
|
|
|
|
|
|
|
| 492 |
async def search_scholar(req: SearchRequest):
|
| 493 |
try:
|
| 494 |
params = {
|
|
@@ -497,10 +313,14 @@ async def search_scholar(req: SearchRequest):
|
|
| 497 |
"fields": "title,authors,year,venue,externalIds,citationCount",
|
| 498 |
}
|
| 499 |
async with httpx.AsyncClient(timeout=15) as client:
|
| 500 |
-
r = await client.get(
|
|
|
|
|
|
|
|
|
|
| 501 |
if r.status_code != 200:
|
| 502 |
_safe_metrics_bucket("errors", f"semantic_{r.status_code}")
|
| 503 |
return {"error": f"Semantic Scholar API: {r.status_code}", "results": [], "source": "Semantic Scholar"}
|
|
|
|
| 504 |
data = r.json()
|
| 505 |
results = []
|
| 506 |
for paper in data.get("data", []):
|
|
@@ -520,6 +340,7 @@ async def search_scholar(req: SearchRequest):
|
|
| 520 |
"_source": "Semantic Scholar",
|
| 521 |
})
|
| 522 |
return {"total": data.get("total", 0), "results": results, "source": "Semantic Scholar"}
|
|
|
|
| 523 |
except Exception as exc:
|
| 524 |
logger.error("Semantic Scholar search error: %s", exc)
|
| 525 |
_safe_metrics_bucket("errors", "semantic_exception")
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
search.py β LibBee v3
|
| 3 |
+
Key fixes:
|
| 4 |
+
- PRIMO: resource type (articles/books) sent as rtype FACET, not q= keyword
|
| 5 |
+
- PRIMO: year filter sent as facet_searchcreationdate FACET, not keyword
|
| 6 |
+
- PubMed: year filter wired to mindate/maxdate params (was silently ignored before)
|
| 7 |
+
- PubMed: peer_reviewed mapped to free full text filter
|
| 8 |
+
- query sent to both APIs is clean topic keywords only β no rtype noise
|
| 9 |
+
"""
|
| 10 |
import logging
|
| 11 |
+
from typing import Optional
|
|
|
|
| 12 |
from urllib.parse import quote
|
| 13 |
|
| 14 |
import httpx
|
|
|
|
| 20 |
logger = logging.getLogger(__name__)
|
| 21 |
router = APIRouter()
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
class SearchRequest(BaseModel):
|
| 25 |
query: str
|
|
|
|
| 29 |
open_access: bool = False
|
| 30 |
year_from: Optional[str] = None
|
| 31 |
year_to: Optional[str] = None
|
| 32 |
+
# resource_type controls rtype FACET β NOT injected into q= keyword query
|
| 33 |
+
resource_type: str = "articles" # "articles" | "books" | "both"
|
| 34 |
|
| 35 |
@field_validator("query")
|
| 36 |
@classmethod
|
|
|
|
| 60 |
@field_validator("resource_type")
|
| 61 |
@classmethod
|
| 62 |
def valid_resource_type(cls, v: str) -> str:
|
| 63 |
+
allowed = {"articles", "books", "both"}
|
| 64 |
+
if v not in allowed:
|
| 65 |
return "articles"
|
| 66 |
return v
|
| 67 |
|
| 68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
def _safe_metrics_increment(key: str) -> None:
|
| 70 |
try:
|
| 71 |
from app import metrics_service
|
|
|
|
| 82 |
return
|
| 83 |
|
| 84 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
@router.post("")
|
| 86 |
async def search_endpoint(req: SearchRequest):
|
| 87 |
_safe_metrics_increment("search_requests")
|
|
|
|
| 94 |
return await search_scholar(req)
|
| 95 |
|
| 96 |
|
| 97 |
+
# ββ PRIMO ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 98 |
+
|
| 99 |
async def search_primo(req: SearchRequest, api_key: str):
|
| 100 |
+
"""
|
| 101 |
+
Send clean topic keywords to q=any,contains.
|
| 102 |
+
Resource type, peer review, open access, and year are all FACETS β never keywords.
|
| 103 |
+
|
| 104 |
+
PRIMO facet reference:
|
| 105 |
+
facet_rtype,include,articles β journal articles
|
| 106 |
+
facet_rtype,include,books β books / ebooks
|
| 107 |
+
facet_tlevel,include,peer_reviewed
|
| 108 |
+
facet_tlevel,include,online_resources (open access proxy)
|
| 109 |
+
facet_searchcreationdate,include,YYYY|,|YYYY
|
| 110 |
+
"""
|
| 111 |
if not api_key:
|
| 112 |
logger.warning("PRIMO_API_KEY not configured")
|
| 113 |
_safe_metrics_bucket("errors", "primo_missing_api_key")
|
| 114 |
return {"error": "PRIMO_API_KEY not configured", "results": [], "source": "PRIMO"}
|
| 115 |
|
| 116 |
+
# ββ The query sent to PRIMO must be ONLY topic keywords ββββββββββββββββββ
|
| 117 |
+
# Strip any residual resource-type words that may have slipped through
|
| 118 |
+
# topic extraction (belt-and-braces defence).
|
| 119 |
+
clean_query = _strip_resource_noise(req.query)
|
| 120 |
+
if not clean_query:
|
| 121 |
+
clean_query = req.query # fallback if stripping removes everything
|
| 122 |
+
|
| 123 |
+
query_encoded = quote(clean_query)
|
| 124 |
+
|
| 125 |
+
url = (
|
| 126 |
+
f"https://api-eu.hosted.exlibrisgroup.com/primo/v1/search"
|
| 127 |
+
f"?vid=971KUOSTAR_INST:KU&tab=Everything&scope=MyInst_and_CI"
|
| 128 |
+
f"&q=any,contains,{query_encoded}&lang=en&sort=rank&limit={req.limit}"
|
| 129 |
+
f"&offset=0&mode=advanced&apikey={api_key}"
|
| 130 |
+
)
|
| 131 |
+
|
| 132 |
+
# ββ Build facets β resource type, quality, year βββββββββββββββββββββββββββ
|
| 133 |
+
facets = []
|
| 134 |
+
|
| 135 |
+
# Resource type β rtype facet (NOT a keyword)
|
| 136 |
+
if req.resource_type == "articles":
|
| 137 |
+
facets.append("facet_rtype,include,articles")
|
| 138 |
+
elif req.resource_type == "books":
|
| 139 |
+
facets.append("facet_rtype,include,books")
|
| 140 |
+
# "both" β no rtype facet (search everything)
|
| 141 |
+
|
| 142 |
+
if req.peer_reviewed:
|
| 143 |
+
facets.append("facet_tlevel,include,peer_reviewed")
|
| 144 |
+
|
| 145 |
+
if req.open_access:
|
| 146 |
+
facets.append("facet_tlevel,include,online_resources")
|
| 147 |
+
|
| 148 |
+
if req.year_from or req.year_to:
|
| 149 |
+
yf = req.year_from or "0001"
|
| 150 |
+
yt = req.year_to or "9999"
|
| 151 |
+
facets.append(f"facet_searchcreationdate,include,{yf}|,|{yt}")
|
| 152 |
+
|
| 153 |
+
for facet in facets:
|
| 154 |
+
url += f"&multiFacets={quote(facet)}"
|
| 155 |
+
|
| 156 |
+
logger.info(
|
| 157 |
+
"PRIMO query=%r resource_type=%s peer_reviewed=%s year=%s-%s",
|
| 158 |
+
clean_query, req.resource_type, req.peer_reviewed, req.year_from, req.year_to,
|
| 159 |
+
)
|
| 160 |
|
| 161 |
try:
|
| 162 |
async with httpx.AsyncClient(timeout=20) as client:
|
| 163 |
+
r = await client.get(url, headers={"Accept": "application/json"})
|
|
|
|
|
|
|
|
|
|
|
|
|
| 164 |
logger.info("PRIMO status=%s", r.status_code)
|
| 165 |
if r.status_code != 200:
|
| 166 |
_safe_metrics_bucket("errors", f"primo_{r.status_code}")
|
| 167 |
return {"error": f"PRIMO API error: {r.status_code}", "results": [], "source": "PRIMO"}
|
| 168 |
+
|
| 169 |
data = r.json()
|
| 170 |
docs = data.get("docs", [])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 171 |
results = []
|
| 172 |
for doc in docs[: req.limit]:
|
| 173 |
pnx = doc.get("pnx", {})
|
|
|
|
| 178 |
"date": (d.get("date") or [""])[0],
|
| 179 |
"type": (d.get("type") or [""])[0],
|
| 180 |
"source": (d.get("source") or [""])[0],
|
| 181 |
+
"primo_url": (
|
| 182 |
+
f"https://khalifa.primo.exlibrisgroup.com/discovery/search"
|
| 183 |
+
f"?query=any,contains,{query_encoded}&vid=971KUOSTAR_INST:KU"
|
| 184 |
+
),
|
| 185 |
"_source": "PRIMO",
|
| 186 |
})
|
| 187 |
+
return {
|
| 188 |
+
"total": data.get("info", {}).get("total", 0),
|
| 189 |
+
"results": results,
|
| 190 |
+
"source": "PRIMO",
|
| 191 |
+
}
|
| 192 |
+
|
| 193 |
except httpx.TimeoutException:
|
| 194 |
_safe_metrics_bucket("errors", "primo_timeout")
|
| 195 |
return {"error": "PRIMO API timed out β please try again", "results": [], "source": "PRIMO"}
|
|
|
|
| 199 |
return {"error": str(exc), "results": [], "source": "PRIMO"}
|
| 200 |
|
| 201 |
|
| 202 |
+
def _strip_resource_noise(query: str) -> str:
|
| 203 |
+
"""
|
| 204 |
+
Remove resource-type and filter words that should be facets, not q= keywords.
|
| 205 |
+
Called as a belt-and-braces guard before sending to PRIMO/PubMed.
|
| 206 |
+
"""
|
| 207 |
+
noise = re.compile(
|
| 208 |
+
r"\b(articles?|papers?|books?|ebooks?|journals?|publications?|monographs?"
|
| 209 |
+
r"|peer[- ]reviewed|open[- ]access|studies|study|research)\b",
|
| 210 |
+
re.IGNORECASE,
|
| 211 |
+
)
|
| 212 |
+
cleaned = noise.sub(" ", query)
|
| 213 |
+
# Collapse leftover AND/OR operators with no operands
|
| 214 |
+
cleaned = re.sub(r"\s+(AND|OR)\s+(AND|OR)\s+", " AND ", cleaned, flags=re.IGNORECASE)
|
| 215 |
+
cleaned = re.sub(r"^\s*(AND|OR)\s+", "", cleaned, flags=re.IGNORECASE)
|
| 216 |
+
cleaned = re.sub(r"\s+(AND|OR)\s*$", "", cleaned, flags=re.IGNORECASE)
|
| 217 |
+
return re.sub(r"\s+", " ", cleaned).strip()
|
| 218 |
+
|
| 219 |
+
|
| 220 |
+
import re # noqa: E402 (needed for _strip_resource_noise above)
|
| 221 |
+
|
| 222 |
+
|
| 223 |
+
# ββ PubMed βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 224 |
+
|
| 225 |
async def search_pubmed(req: SearchRequest):
|
| 226 |
+
"""
|
| 227 |
+
Year filters use mindate/maxdate params β NOT injected into the search term.
|
| 228 |
+
Peer-reviewed filter uses [pt] (publication type) in the term.
|
| 229 |
+
"""
|
| 230 |
+
# Build clean term β topic keywords only
|
| 231 |
+
clean_query = _strip_resource_noise(req.query)
|
| 232 |
+
if not clean_query:
|
| 233 |
+
clean_query = req.query
|
| 234 |
+
|
| 235 |
+
# Add peer-reviewed as a PubMed publication-type filter (appended to term)
|
| 236 |
term = clean_query
|
| 237 |
if req.peer_reviewed:
|
| 238 |
term = f"({term}) AND Journal Article[pt]"
|
| 239 |
+
|
| 240 |
query_encoded = quote(term)
|
| 241 |
+
|
| 242 |
+
# Date params (separate from search term β correct PubMed approach)
|
| 243 |
date_params = ""
|
| 244 |
if req.year_from or req.year_to:
|
| 245 |
yf = req.year_from or "1900"
|
| 246 |
yt = req.year_to or "3000"
|
| 247 |
date_params = f"&mindate={yf}&maxdate={yt}&datetype=pdat"
|
| 248 |
+
|
| 249 |
+
logger.info(
|
| 250 |
+
"PubMed term=%r peer_reviewed=%s year=%s-%s",
|
| 251 |
+
term, req.peer_reviewed, req.year_from, req.year_to,
|
| 252 |
+
)
|
| 253 |
+
|
| 254 |
try:
|
| 255 |
async with httpx.AsyncClient(timeout=15) as client:
|
| 256 |
search_url = (
|
|
|
|
| 261 |
if r.status_code != 200:
|
| 262 |
_safe_metrics_bucket("errors", "pubmed_search_failed")
|
| 263 |
return {"error": "PubMed search failed", "results": [], "source": "PubMed"}
|
| 264 |
+
|
| 265 |
ids = r.json().get("esearchresult", {}).get("idlist", [])
|
| 266 |
if not ids:
|
| 267 |
return {"total": 0, "results": [], "source": "PubMed"}
|
| 268 |
+
|
| 269 |
fetch_url = (
|
| 270 |
f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi"
|
| 271 |
f"?db=pubmed&id={','.join(ids)}&retmode=json"
|
|
|
|
| 274 |
if r2.status_code != 200:
|
| 275 |
_safe_metrics_bucket("errors", "pubmed_fetch_failed")
|
| 276 |
return {"error": "PubMed fetch failed", "results": [], "source": "PubMed"}
|
| 277 |
+
|
| 278 |
data = r2.json().get("result", {})
|
| 279 |
results = []
|
| 280 |
for pid in ids:
|
|
|
|
| 296 |
"_source": "PubMed",
|
| 297 |
})
|
| 298 |
return {"total": len(ids), "results": results, "source": "PubMed"}
|
| 299 |
+
|
| 300 |
except Exception as exc:
|
| 301 |
logger.error("PubMed search error: %s", exc)
|
| 302 |
_safe_metrics_bucket("errors", "pubmed_exception")
|
| 303 |
return {"error": str(exc), "results": [], "source": "PubMed"}
|
| 304 |
|
| 305 |
|
| 306 |
+
# ββ Semantic Scholar βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 307 |
+
|
| 308 |
async def search_scholar(req: SearchRequest):
|
| 309 |
try:
|
| 310 |
params = {
|
|
|
|
| 313 |
"fields": "title,authors,year,venue,externalIds,citationCount",
|
| 314 |
}
|
| 315 |
async with httpx.AsyncClient(timeout=15) as client:
|
| 316 |
+
r = await client.get(
|
| 317 |
+
"https://api.semanticscholar.org/graph/v1/paper/search",
|
| 318 |
+
params=params,
|
| 319 |
+
)
|
| 320 |
if r.status_code != 200:
|
| 321 |
_safe_metrics_bucket("errors", f"semantic_{r.status_code}")
|
| 322 |
return {"error": f"Semantic Scholar API: {r.status_code}", "results": [], "source": "Semantic Scholar"}
|
| 323 |
+
|
| 324 |
data = r.json()
|
| 325 |
results = []
|
| 326 |
for paper in data.get("data", []):
|
|
|
|
| 340 |
"_source": "Semantic Scholar",
|
| 341 |
})
|
| 342 |
return {"total": data.get("total", 0), "results": results, "source": "Semantic Scholar"}
|
| 343 |
+
|
| 344 |
except Exception as exc:
|
| 345 |
logger.error("Semantic Scholar search error: %s", exc)
|
| 346 |
_safe_metrics_bucket("errors", "semantic_exception")
|