Update app.py

app.py

@@ -701,7 +701,7 @@ def _make_boolean(text: str) -> str:
     return f'"{text}"'
 
 def _clean_database_keywords(boolean_query: str) -> str:
-    return re.sub(r'\s+', ' ', re.sub(r'(AND|OR|NOT)|[()"]', ' ', boolean_query, flags=re.IGNORECASE)).strip()
+    return re.sub(r'\s+', ' ', re.sub(r'\b(AND|OR|NOT)\b|[()"]', ' ', boolean_query, flags=re.IGNORECASE)).strip()
 
 async def _build_search_plan(query: str, year: int = 2026) -> dict:
     prompt = f"""You are a search expert for Khalifa University Library.
@@ -728,7 +728,7 @@ Query: "{query}"""
         corrected = result.get("corrected", query).strip() or query
         natural = result.get("natural", corrected).strip() or corrected
         boolean = (result.get("boolean") or "").strip()
-        has_operators = bool(re.search(r'(AND|OR)', boolean)) if boolean else False
+        has_operators = bool(re.search(r'\b(AND|OR)\b', boolean)) if boolean else False
         has_parens = "(" in boolean if boolean else False
         if not has_operators or not has_parens:
             boolean = _make_boolean(corrected)
@@ -756,6 +756,103 @@ Query: "{query}"""
             "open_access": False,
         }
 
+
+
+def get_behavior_instructions() -> str:
+    base = get_config("bot_personality", "You are a helpful, friendly, and knowledgeable library assistant at Khalifa University, Abu Dhabi, UAE. KU = Khalifa University, NOT Kuwait University. Be concise (2-4 sentences). Always include relevant URLs.")
+    extra = get_config("custom_instructions", "")
+    return (base + ("\n" + extra if extra else "")).strip()
+
+
+def _looks_social_or_greeting(question: str) -> bool:
+    return bool(SOCIAL_RE.search((question or "").strip()))
+
+
+async def _interpret_semantics(question: str, history=None) -> dict:
+    q = (question or "").strip()
+    ql = q.lower()
+    canonical_terms = []
+    grounding_keys = []
+    social = False
+
+    def add(key: str, *terms: str):
+        if key and key not in grounding_keys:
+            grounding_keys.append(key)
+        for t in terms:
+            if t and t not in canonical_terms:
+                canonical_terms.append(t)
+
+    if _looks_social_or_greeting(q):
+        social = True
+        return {"intent_hint": "general", "canonical_terms": canonical_terms, "grounding_keys": grounding_keys, "social": True}
+
+    if _looks_library_hours_question(q):
+        add("circulation", "library hours", "opening hours", "closing hours")
+        return {"intent_hint": "library_info", "canonical_terms": canonical_terms, "grounding_keys": grounding_keys, "social": False}
+
+    if _looks_nonlibrary_ku_question(q):
+        return {"intent_hint": "general", "canonical_terms": canonical_terms, "grounding_keys": grounding_keys, "social": False}
+
+    # Staff / role semantics
+    if re.search(r"\b(systems? librarian|system librarian|website|digital services|library systems?|technology help)\b", ql):
+        add("systems_help", "Walter Brian Hall", "Systems Librarian", "website", "technology")
+    if re.search(r"\b(database access|e-?resources?|remote access|off campus|off-campus|login issue|access problem|vendor issue)\b", ql):
+        add("database_access", "Rani Anand", "E-Resources", "database access")
+    if re.search(r"\b(orcid|open access|apc|article processing charge|research impact|bibliometric|bibliometrics|scival|scopus metrics?)\b", ql):
+        add("orcid_oa", "Nikesh Narayanan", "ORCID", "Open Access", "research impact")
+    if re.search(r"\b(medical librarian|pubmed help|embase|cinahl|cochrane|uptodate|systematic review|clinical databases?)\b", ql):
+        add("medical_help", "Jason Fetty", "Medical Librarian", "PubMed", "systematic review")
+    if re.search(r"\b(acquisitions?|collection development|suggest a book|request a title|new title request)\b", ql):
+        add("acquisitions", "Alia Al-Harrasi", "Acquisitions", "collection development")
+    if re.search(r"\b(circulation|borrow|renew|due date|fine|hold request|my library account|public services?)\b", ql):
+        add("circulation", "borrowing", "renewal", "My Library Account")
+    if re.search(r"\b(ask a librarian|research help|research consultation|reference help|consultation)\b", ql):
+        add("research_help", "Ask a Librarian", "research consultation")
+
+    # Service / resource semantics
+    if re.search(r"\b(inter\s*library loan|interlibrary loan|\bill\b|document delivery|full text unavailable|no full text|can't get (an )?article|cannot get (an )?article|article not available)\b", ql):
+        add("ill", "Interlibrary Loan", "ILL", "document delivery")
+        add("fulltext", "full text", "LibKey Nomad", "article access")
+    if re.search(r"\b(primo|catalog|discovery|holdings|publication finder|does the library have)\b", ql):
+        add("primo", "PRIMO", "catalog", "Publication Finder")
+
+    # Database recommendation semantics
+    if re.search(r"\b(standards?|astm|ieee standards?|asme|asce)\b", ql):
+        add("standards", "ASTM Compass", "IEEE standards", "ASME", "ASCE")
+    if re.search(r"\b(dissertations?|theses|khazna)\b", ql):
+        add("theses", "ProQuest Dissertations & Theses", "Khazna")
+    if re.search(r"\b(impact factor|journal metrics?|jcr|citescore|sjr)\b", ql):
+        add("metrics", "Journal Citation Reports", "CiteScore")
+    if re.search(r"\b(chemistry|chemical)\b", ql):
+        add("chemistry", "ACS", "SciFindern", "Reaxys")
+    if re.search(r"\b(physics|optics?|photonics?)\b", ql):
+        add("physics", "APS", "AIP", "IOPScience")
+    if re.search(r"\b(engineering|civil engineering|mechanical engineering|electrical engineering|computer science|ai)\b", ql):
+        add("engineering", "IEEE Xplore", "ACM", "Knovel", "ASCE", "ASME")
+
+    # Name/title style library questions
+    if re.search(r"\b(who is|who handles|who can help|whom should i contact|contact for)\b", ql) and (_looks_library_question(q) or grounding_keys):
+        if not grounding_keys:
+            add("research_help", "staff directory", "library staff")
+
+    # Decide intent
+    if _looks_medical_search(q):
+        intent = "search_medical"
+    elif _looks_research_question(q):
+        intent = "search_academic"
+    elif grounding_keys or _looks_library_question(q):
+        intent = "library_info"
+    elif _looks_current_question(q):
+        intent = "general_recent"
+    else:
+        intent = "general"
+
+    return {
+        "intent_hint": intent,
+        "canonical_terms": canonical_terms,
+        "grounding_keys": grounding_keys,
+        "social": social,
+    }
 def _looks_library_question(question: str) -> bool:
     return bool(LIBRARY_CUE_RE.search(question))
 
@@ -766,7 +863,7 @@ def _looks_research_question(question: str) -> bool:
     q = question.lower()
     if RESEARCH_CUE_RE.search(q):
         return True
-    return bool(re.search(r'impact of|effects? of|causes? of|relationship between|literature on', q))
+    return bool(re.search(r'\bimpact of\b|\beffects? of\b|\bcauses? of\b|\brelationship between\b|\bliterature on\b', q))
 
 def _looks_medical_search(question: str) -> bool:
     q = question.lower()