Update app.py

app.py

@@ -874,10 +874,86 @@ def build_vectorstore(docs, force_rebuild=False):
 
 
 # ===== TOOL: SEARCH PRIMO =====
+def _boolean_to_primo_params(boolean_query: str) -> str:
+    """
+    Convert Boolean string to PRIMO multi-query parameter format.
+    ("artificial intelligence" OR "machine learning") AND ("cancer diagnosis")
+    → query=any,contains,artificial intelligence OR machine learning,AND
+      &query=any,contains,cancer diagnosis
+    Each top-level AND group becomes a separate query= parameter.
+    """
+    from urllib.parse import quote
+
+    # Strip outer parens groups split by top-level AND
+    # First flatten quotes and clean
+    cleaned = boolean_query.strip()
+
+    # Split on top-level AND (not inside parentheses)
+    groups = []
+    depth = 0
+    current = []
+    i = 0
+    tokens = re.split(r'(\(|\)|\bAND\b|\bOR\b)', cleaned)
+    # Simpler approach: split on AND at depth 0
+    chunk = ""
+    depth = 0
+    for char in cleaned:
+        if char == '(':
+            depth += 1
+            chunk += char
+        elif char == ')':
+            depth -= 1
+            chunk += char
+        else:
+            chunk += char
+        # Check for AND at depth 0
+        if depth == 0 and chunk.upper().endswith(' AND '):
+            groups.append(chunk[:-5].strip())
+            chunk = ""
+    if chunk.strip():
+        groups.append(chunk.strip())
+
+    if not groups:
+        groups = [cleaned]
+
+    # Clean each group: remove outer parens, strip quotes, normalise OR
+    primo_params = []
+    for i, group in enumerate(groups):
+        # Remove outer parentheses
+        g = group.strip()
+        if g.startswith('(') and g.endswith(')'):
+            g = g[1:-1].strip()
+        # Remove double quotes (PRIMO doesn't need them in query= param)
+        g = g.replace('"', '')
+        # Normalise spacing around OR
+        g = re.sub(r'\s+OR\s+', ' OR ', g).strip()
+        if not g:
+            continue
+        # All except the last get ,AND suffix
+        suffix = ',AND' if i < len(groups) - 1 else ''
+        primo_params.append(f"query=any,contains,{quote(g, safe=' OR')}{suffix}")
+
+    return '&'.join(primo_params) if primo_params else f"query=any,contains,{quote(cleaned)}"
+
+
 async def tool_search_primo(query, limit=5, peer_reviewed=False, open_access=False, year_from=None, year_to=None):
+    """
+    query can be either:
+    - a Boolean string: ("AI" OR "ML") AND ("cancer") — converted to multi-query PRIMO format
+    - a plain keyword string: "machine learning cancer" — sent as single query
+    """
     api_key = os.environ.get("PRIMO_API_KEY")
     if not api_key: return {"error": "PRIMO_API_KEY not configured", "results": []}
 
+    # Build PRIMO query params — multi-query format preserves all concepts
+    if re.search(r'\b(AND|OR)\b', query) and '(' in query:
+        # Boolean string — convert to multi-query format
+        query_params = _boolean_to_primo_params(query)
+    else:
+        # Plain keywords — single query, URL encoded
+        from urllib.parse import quote
+        query_params = f"query=any,contains,{quote(query.strip())}"
+
     vid = "971KUOSTAR_INST:KU"
     facets = ""
     if peer_reviewed: facets += "&qInclude=facet_tlevel,exact,peer_reviewed"
@@ -888,7 +964,7 @@ async def tool_search_primo(query, limit=5, peer_reviewed=False, open_access=Fal
         facets += f"&multiFacets=facet_searchcreationdate,include,{yf}%7C,%7C{yt}"
 
     base = "https://api-eu.hosted.exlibrisgroup.com/primo/v1/search"
-    qs = f"?vid={vid}&tab=Everything&scope=MyInst_and_CI&q=any,contains,{query}&lang=en&sort=rank&limit={limit}&offset=0&apikey={api_key}{facets}"
+    qs = f"?vid={vid}&tab=Everything&scope=MyInst_and_CI&{query_params}&lang=en&sort=rank&limit={limit}&offset=0&mode=advanced&apikey={api_key}{facets}"
 
     async with httpx.AsyncClient(timeout=15) as client:
         for region in ["api-eu", "api-na", "api-ap"]: