Upload 8 files

.streamlit/config.toml

@@ -0,0 +1,19 @@
+[server]
+headless = true
+port = 7860
+enableCORS = false
+enableXsrfProtection = false
+
+[browser]
+gatherUsageStats = false
+serverAddress = "0.0.0.0"
+
+[theme]
+primaryColor = "#1f6feb"
+backgroundColor = "#0e1117"
+secondaryBackgroundColor = "#161b22"
+textColor = "#ffffff"
+
+[client]
+showErrorDetails = false
+toolbarMode = "minimal"

Dockerfile

@@ -6,6 +6,11 @@ ENV PYTHONUNBUFFERED=1 \
     PORT=7860 \
     HOME=/home/user
 
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
 # Create user for HF Spaces (UID 1000 required)
 RUN useradd -m -u 1000 user
 

app.py

@@ -28,6 +28,9 @@ st.markdown("""
     .source-file {background-color: #1f6feb; color: white;}
     .source-web {background-color: #238636; color: white;}
     .source-youtube {background-color: #da3633; color: white;}
+    .source-gdrive {background-color: #34a853; color: white;}
+    .source-onedrive {background-color: #0078d4; color: white;}
+    .source-dropbox {background-color: #0061ff; color: white;}
 </style>
 """, unsafe_allow_html=True)
 
@@ -147,7 +150,7 @@ else:
     st.title(f"🔍 RAG SaaS Platform")
     
     # Main tabs
-    tab1, tab2, tab3, tab4 = st.tabs(["💬 Ask Questions", "📁 Manage Sources", "📊 Metrics", "ℹ️ About"])
+    tab1, tab2, tab3, tab4, tab5 = st.tabs(["💬 Ask Questions", "📁 Manage Sources", "☁️ Cloud Connectors", "📊 Metrics", "ℹ️ About"])
     
     # Tab 1: Ask Questions
     with tab1:
@@ -466,8 +469,110 @@ else:
             except Exception as e:
                 st.error(f"Error loading sources: {e}")
     
-    # Tab 3: Metrics
+    # Tab 3: Cloud Connectors
     with tab3:
+        st.header("☁️ Cloud Connectors")
+        st.write("Connect to your enterprise cloud storage to sync documents directly.")
+        
+        # Connect New Account
+        st.subheader("Connect New Account")
+        col1, col2, col3 = st.columns(3)
+        
+        with col1:
+            if st.button("🔌 Connect Google Drive", use_container_width=True):
+                try:
+                    res = requests.get(f"{api_url}/v1/connectors/gdrive/oauth/start?tenant_id={st.session_state.tenant_id}")
+                    if res.status_code == 200:
+                        st.markdown(f"[Click here to authorize Google Drive]({res.json()['auth_url']})")
+                    else:
+                        st.error("Failed to start GDrive OAuth")
+                except Exception as e:
+                    st.error(f"Error: {e}")
+        
+        with col2:
+            if st.button("🔌 Connect OneDrive", use_container_width=True):
+                try:
+                    res = requests.get(f"{api_url}/v1/connectors/onedrive/oauth/start?tenant_id={st.session_state.tenant_id}")
+                    if res.status_code == 200:
+                        st.markdown(f"[Click here to authorize OneDrive]({res.json()['auth_url']})")
+                    else:
+                        st.error("Failed to start OneDrive OAuth")
+                except Exception as e:
+                    st.error(f"Error: {e}")
+        
+        with col3:
+            if st.button("🔌 Connect Dropbox", use_container_width=True):
+                try:
+                    res = requests.get(f"{api_url}/v1/connectors/dropbox/oauth/start?tenant_id={st.session_state.tenant_id}")
+                    if res.status_code == 200:
+                        st.markdown(f"[Click here to authorize Dropbox]({res.json()['auth_url']})")
+                    else:
+                        st.error("Failed to start Dropbox OAuth")
+                except Exception as e:
+                    st.error(f"Error: {e}")
+        
+        st.divider()
+        
+        # Manage Existing Connectors
+        st.subheader("Your Connected Accounts")
+        try:
+            response = requests.get(
+                f"{api_url}/v1/connectors/",
+                params={"tenant_id": st.session_state.tenant_id}
+            )
+            if response.status_code == 200:
+                connectors = response.json()
+                if connectors:
+                    for conn in connectors:
+                        with st.expander(f"{conn['provider'].upper()} - {conn['display_name']}"):
+                            col_a, col_b, col_c = st.columns([2, 1, 1])
+                            with col_a:
+                                st.write(f"**Status:** {conn['sync_status'].upper()}")
+                                if conn['last_sync']:
+                                    st.write(f"**Last Sync:** {conn['last_sync']}")
+                            
+                            with col_b:
+                                if st.button("🔄 Trigger Sync", key=f"sync_{conn['id']}"):
+                                    sync_res = requests.post(f"{api_url}/v1/connectors/{conn['id']}/sync")
+                                    if sync_res.status_code == 200:
+                                        st.success("Sync triggered!")
+                                    else:
+                                        st.error("Failed to trigger sync")
+                            
+                            with col_c:
+                                if st.button("📁 Manage Targets", key=f"targets_{conn['id']}"):
+                                    st.session_state[f"show_targets_{conn['id']}"] = True
+                            
+                            # Target Selection Mock/Simplified
+                            if st.session_state.get(f"show_targets_{conn['id']}"):
+                                st.info("Loading roots...")
+                                roots_res = requests.get(f"{api_url}/v1/connectors/{conn['id']}/roots")
+                                if roots_res.status_code == 200:
+                                    roots = roots_res.json()
+                                    target_ids = st.multiselect(
+                                        "Select Folders/Drives to sync",
+                                        options=[r['id'] for r in roots],
+                                        format_func=lambda x: next(r['name'] for r in roots if r['id'] == x),
+                                        key=f"ms_{conn['id']}"
+                                    )
+                                    if st.button("Save Targets", key=f"save_{conn['id']}"):
+                                        selected_targets = [{"id": tid, "type": "folder"} for tid in target_ids]
+                                        save_res = requests.post(
+                                            f"{api_url}/v1/connectors/{conn['id']}/targets",
+                                            params={"tenant_id": st.session_state.tenant_id},
+                                            json=selected_targets
+                                        )
+                                        if save_res.status_code == 200:
+                                            st.success("Targets updated!")
+                                            st.session_state[f"show_targets_{conn['id']}"] = False
+                                            st.rerun()
+                else:
+                    st.info("No cloud accounts connected yet.")
+        except Exception as e:
+            st.error(f"Error fetching connectors: {e}")
+
+    # Tab 4: Metrics
+    with tab4:
         st.header("📊 Your Metrics")
         
         # Time range selector
@@ -538,14 +643,15 @@ else:
         except Exception as e:
             st.warning(f"Cache stats unavailable: {e}")
     
-    # Tab 4: About
-    with tab4:
+    # Tab 5: About
+    with tab5:
         st.header("ℹ️ About RAG SaaS Platform")
         
         st.markdown("""
         ### Features
         
         ✅ **Multi-Source Retrieval** - Unified search across documents, URLs, and YouTube videos  
+        ✅ **Enterprise Cloud Connectors** - Native sync with Google Drive, OneDrive, and Dropbox  
         ✅ **Tenant Isolation** - Complete data and metrics separation per tenant  
         ✅ **Optimized Performance** - Model caching with 70-90% latency reduction  
         ✅ **Compliant YouTube** - Captions-first with transcript upload fallback