Merge pull request MODSetter#339 from MODSetter/dev

[Feature] Add Luma connector

Author: MODSetter

README.md

@@ -10,7 +10,7 @@
 
 
 # SurfSense
-While tools like NotebookLM and Perplexity are impressive and highly effective for conducting research on any topic/query, SurfSense elevates this capability by integrating with your personal knowledge base. It is a highly customizable AI research agent, connected to external sources such as Search Engines (Tavily, LinkUp), Slack, Linear, Jira, ClickUp, Confluence, Gmail, Notion, YouTube, GitHub, Discord, Airtable, Google Calendar and more to come.
+While tools like NotebookLM and Perplexity are impressive and highly effective for conducting research on any topic/query, SurfSense elevates this capability by integrating with your personal knowledge base. It is a highly customizable AI research agent, connected to external sources such as Search Engines (Tavily, LinkUp), Slack, Linear, Jira, ClickUp, Confluence, Gmail, Notion, YouTube, GitHub, Discord, Airtable, Google Calendar, Luma and more to come.
 
 <div align="center">
 <a href="https://trendshift.io/repositories/13606" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13606" alt="MODSetter%2FSurfSense | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -74,6 +74,7 @@ Open source and easy to deploy locally.
 - Discord
 - Airtable
 - Google Calendar
+- Luma
 - and more to come.....
 
 ## 📄 **Supported File Extensions**

surfsense_backend/alembic/versions/21_add_luma_connector_enums.py

@@ -0,0 +1,60 @@
+"""Add Luma connector enums
+
+Revision ID: 21
+Revises: 20
+Create Date: 2025-09-27 20:00:00.000000
+
+"""
+
+from collections.abc import Sequence
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "21"
+down_revision: str | None = "20"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    """Safely add 'LUMA_CONNECTOR' to enum types if missing."""
+
+    # Add to searchsourceconnectortype enum
+    op.execute(
+        """
+    DO $$
+    BEGIN
+        IF NOT EXISTS (
+            SELECT 1 FROM pg_type t
+            JOIN pg_enum e ON t.oid = e.enumtypid
+            WHERE t.typname = 'searchsourceconnectortype' AND e.enumlabel = 'LUMA_CONNECTOR'
+        ) THEN
+            ALTER TYPE searchsourceconnectortype ADD VALUE 'LUMA_CONNECTOR';
+        END IF;
+    END
+    $$;
+    """
+    )
+
+    # Add to documenttype enum
+    op.execute(
+        """
+    DO $$
+    BEGIN
+        IF NOT EXISTS (
+            SELECT 1 FROM pg_type t
+            JOIN pg_enum e ON t.oid = e.enumtypid
+            WHERE t.typname = 'documenttype' AND e.enumlabel = 'LUMA_CONNECTOR'
+        ) THEN
+            ALTER TYPE documenttype ADD VALUE 'LUMA_CONNECTOR';
+        END IF;
+    END
+    $$;
+    """
+    )
+
+
+def downgrade() -> None:
+    """Remove 'LUMA_CONNECTOR' from enum types."""
+    pass

surfsense_backend/app/agents/researcher/nodes.py

@@ -413,6 +413,42 @@ async def fetch_documents_by_ids(
                     else:
                         url = ""
 
+                elif doc_type == "LUMA_CONNECTOR":
+                    # Extract Luma-specific metadata
+                    event_id = metadata.get("event_id", "")
+                    event_name = metadata.get("event_name", "Untitled Event")
+                    event_url = metadata.get("event_url", "")
+                    start_time = metadata.get("start_time", "")
+                    location_name = metadata.get("location_name", "")
+                    meeting_url = metadata.get("meeting_url", "")
+
+                    title = f"Luma: {event_name}"
+                    if start_time:
+                        # Format the start time for display
+                        try:
+                            if "T" in start_time:
+                                from datetime import datetime
+
+                                start_dt = datetime.fromisoformat(
+                                    start_time.replace("Z", "+00:00")
+                                )
+                                formatted_time = start_dt.strftime("%Y-%m-%d %H:%M")
+                                title += f" ({formatted_time})"
+                        except Exception:
+                            pass
+
+                    description = (
+                        doc.content[:100] + "..."
+                        if len(doc.content) > 100
+                        else doc.content
+                    )
+                    if location_name:
+                        description += f" | Venue: {location_name}"
+                    elif meeting_url:
+                        description += " | Online Event"
+
+                    url = event_url if event_url else ""
+
                 elif doc_type == "EXTENSION":
                     # Extract Extension-specific metadata
                     webpage_title = metadata.get("VisitedWebPageTitle", doc.title)
@@ -487,6 +523,7 @@ async def fetch_documents_by_ids(
                 "CONFLUENCE_CONNECTOR": "Confluence (Selected)",
                 "CLICKUP_CONNECTOR": "ClickUp (Selected)",
                 "AIRTABLE_CONNECTOR": "Airtable (Selected)",
+                "LUMA_CONNECTOR": "Luma Events (Selected)",
             }
 
             source_object = {
@@ -1197,6 +1234,33 @@ async def fetch_relevant_documents(
                             }
                         )
 
+                elif connector == "LUMA_CONNECTOR":
+                    (
+                        source_object,
+                        luma_chunks,
+                    ) = await connector_service.search_luma(
+                        user_query=reformulated_query,
+                        user_id=user_id,
+                        search_space_id=search_space_id,
+                        top_k=top_k,
+                        search_mode=search_mode,
+                    )
+
+                    # Add to sources and raw documents
+                    if source_object:
+                        all_sources.append(source_object)
+                    all_raw_documents.extend(luma_chunks)
+
+                    # Stream found document count
+                    if streaming_service and writer:
+                        writer(
+                            {
+                                "yield_value": streaming_service.format_terminal_info_delta(
+                                    f"🎯 Found {len(luma_chunks)} Luma events related to your query"
+                                )
+                            }
+                        )
+
             except Exception as e:
                 logging.error("Error in search_airtable: %s", traceback.format_exc())
                 error_message = f"Error searching connector {connector}: {e!s}"

surfsense_backend/app/agents/researcher/qna_agent/prompts.py

@@ -38,6 +38,7 @@ def get_qna_citation_system_prompt(chat_history: str | None = None):
 - AIRTABLE_CONNECTOR: "Airtable records, tables, and database content" (personal data management and organization)
 - TAVILY_API: "Tavily search API results" (personalized search results)
 - LINKUP_API: "Linkup search API results" (personalized search results)
+- LUMA_CONNECTOR: "Luma events"
 </knowledge_sources>
 
 <instructions>

surfsense_backend/app/agents/researcher/sub_section_writer/prompts.py

@@ -38,6 +38,7 @@ def get_citation_system_prompt(chat_history: str | None = None):
 - AIRTABLE_CONNECTOR: "Airtable records, tables, and database content" (personal data management and organization)
 - TAVILY_API: "Tavily search API results" (personalized search results)
 - LINKUP_API: "Linkup search API results" (personalized search results)
+- LUMA_CONNECTOR: "Luma events"
 </knowledge_sources>
 <instructions>
 1. Review the chat history to understand the conversation context and any previous topics discussed.

surfsense_backend/app/agents/researcher/utils.py

@@ -50,6 +50,7 @@ def get_connector_emoji(connector_name: str) -> str:
         "LINKUP_API": "🔗",
         "GOOGLE_CALENDAR_CONNECTOR": "📅",
         "AIRTABLE_CONNECTOR": "🗃️",
+        "LUMA_CONNECTOR": "✨",
     }
     return connector_emojis.get(connector_name, "🔎")
 
@@ -72,6 +73,7 @@ def get_connector_friendly_name(connector_name: str) -> str:
         "TAVILY_API": "Tavily Search",
         "LINKUP_API": "Linkup Search",
         "AIRTABLE_CONNECTOR": "Airtable",
+        "LUMA_CONNECTOR": "Luma",
     }
     return connector_friendly_names.get(connector_name, connector_name)