feature_collection.patch

diff --git a/src/rag/milvus.py b/src/rag/milvus.py
index de589d4..c1b9b98 100644
--- a/src/rag/milvus.py
+++ b/src/rag/milvus.py
@@ -9,7 +9,7 @@ from typing import Any, Dict, Iterable, List, Optional, Sequence, Set
 from langchain_milvus.vectorstores import Milvus as LangchainMilvus
 from langchain_openai import OpenAIEmbeddings
 from openai import OpenAI
-from pymilvus import CollectionSchema, DataType, FieldSchema, MilvusClient
+from pymilvus import CollectionSchema, DataType, FieldSchema, MilvusClient, utility
 
 from src.config.loader import get_bool_env, get_int_env, get_str_env
 from src.rag.retriever import Chunk, Document, Resource, Retriever
@@ -397,6 +397,36 @@ class MilvusRetriever(Retriever):
         except Exception as e:
             raise ConnectionError(f"Failed to connect to Milvus: {str(e)}")
 
+    def _connect_with_collection(self, collection_name) -> None:
+        """Create the underlying Milvus client (idempotent)."""
+        try:
+            # Check if using Milvus Lite (file-based) vs server-based Milvus
+            if self._is_milvus_lite():
+                # Use MilvusClient for Milvus Lite (local file database)
+                self.client = MilvusClient(self.uri)
+                # Ensure collection exists
+                self._ensure_collection_exists()
+            else:
+                connection_args = {
+                    "uri": self.uri,
+                }
+                # Add user/password only if provided
+                if self.user:
+                    connection_args["user"] = self.user
+                if self.password:
+                    connection_args["password"] = self.password
+
+                # Create LangChain client (it will handle collection creation automatically)
+                self.client = LangchainMilvus(
+                    embedding_function=self.embedding_model,
+                    collection_name=collection_name,
+                    connection_args=connection_args,
+                    # optional (if collection already exists with different schema, be careful)
+                    drop_old=False,
+                )
+        except Exception as e:
+            raise ConnectionError(f"Failed to connect to Milvus: {str(e)}")
+
     def _is_milvus_lite(self) -> bool:
         """Return True if the URI points to a local Milvus Lite file.
         Milvus Lite uses local file paths (often ``*.db``) without an HTTP/HTTPS
@@ -476,26 +506,12 @@ class MilvusRetriever(Retriever):
             else:
                 # Use similarity_search_by_vector for lightweight listing.
                 # If a query is provided embed it; else use a zero vector.
-                docs: Iterable[Any] = self.client.similarity_search(
-                    query,
-                    k=100,
-                    expr="source == 'examples'",  # Limit to 100 results
-                )
-                for d in docs:
-                    meta = getattr(d, "metadata", {}) or {}
-                    # check if the resource is in the list of resources
-                    if resources and any(
-                        r.uri == meta.get(self.url_field, "")
-                        or r.uri == f"milvus://{meta.get(self.id_field, '')}"
-                        for r in resources
-                    ):
-                        continue
+                connections = utility.list_collections(using=f"{self.uri}-{self.user}")
+                for connection in connections:
                     resources.append(
                         Resource(
-                            uri=meta.get(self.url_field, "")
-                            or f"milvus://{meta.get(self.id_field, '')}",
-                            title=meta.get(self.title_field, "")
-                            or meta.get(self.id_field, "Unnamed"),
+                            uri=f"milvus://{connection}",
+                            title=connection,
                             description="Stored Milvus document",
                         )
                     )
@@ -621,38 +637,32 @@ class MilvusRetriever(Retriever):
 
             else:
                 # For LangChain Milvus, use similarity search
-                search_results = self.client.similarity_search_with_score(
-                    query=query, k=self.top_k
-                )
+                if not resources:
+                    return []
 
                 documents = {}
+                for resource in resources:
+                    self._connect_with_collection(resource.title)
+                    search_results = self.client.similarity_search_with_score(
+                        query=query, k=self.top_k
+                    )
 
-                for doc, score in search_results:
-                    metadata = doc.metadata or {}
-                    doc_id = metadata.get(self.id_field, "")
-                    title = metadata.get(self.title_field, "")
-                    url = metadata.get(self.url_field, "")
-                    content = doc.page_content
-
-                    # Skip if resource filtering is requested and this doc is not in the list
-                    if resources:
-                        doc_in_resources = False
-                        for resource in resources:
-                            if (url and url in resource.uri) or doc_id in resource.uri:
-                                doc_in_resources = True
-                                break
-                        if not doc_in_resources:
-                            continue
-
-                    # Create or update document
-                    if doc_id not in documents:
-                        documents[doc_id] = Document(
-                            id=doc_id, url=url, title=title, chunks=[]
-                        )
+                    for doc, score in search_results:
+                        metadata = doc.metadata or {}
+                        doc_id = metadata.get(self.id_field, "")
+                        title = metadata.get(self.title_field, "")
+                        url = metadata.get(self.url_field, "")
+                        content = doc.page_content
+
+                        # Create or update document
+                        if doc_id not in documents:
+                            documents[doc_id] = Document(
+                                id=doc_id, url=url, title=title, chunks=[]
+                            )
 
-                    # Add chunk to document
-                    chunk = Chunk(content=content, similarity=score)
-                    documents[doc_id].chunks.append(chunk)
+                        # Add chunk to document
+                        chunk = Chunk(content=content, similarity=score)
+                        documents[doc_id].chunks.append(chunk)
 
                 return list(documents.values())
 
diff --git a/web/src/components/deer-flow/theme-provider-wrapper.tsx b/web/src/components/deer-flow/theme-provider-wrapper.tsx
index 6da0db8..1a99bcf 100644
--- a/web/src/components/deer-flow/theme-provider-wrapper.tsx
+++ b/web/src/components/deer-flow/theme-provider-wrapper.tsx
@@ -18,9 +18,9 @@ export function ThemeProviderWrapper({
   return (
     <ThemeProvider
       attribute="class"
-      defaultTheme={"dark"}
+      defaultTheme={"light"}
       enableSystem={isChatPage}
-      forcedTheme={isChatPage ? undefined : "dark"}
+      forcedTheme={isChatPage ? undefined : "light"}
       disableTransitionOnChange
     >
       {children}
diff --git a/web/src/core/api/resolve-service-url.ts b/web/src/core/api/resolve-service-url.ts
index a87b777..d93e987 100644
--- a/web/src/core/api/resolve-service-url.ts
+++ b/web/src/core/api/resolve-service-url.ts
@@ -4,9 +4,13 @@
 import { env } from "~/env";
 
 export function resolveServiceURL(path: string) {
-  let BASE_URL = env.NEXT_PUBLIC_API_URL ?? "http://localhost:8000/api/";
+  let BASE_URL = env.NEXT_PUBLIC_API_URL ?? "/api/";
   if (!BASE_URL.endsWith("/")) {
     BASE_URL += "/";
   }
+
+  const origin = window.location.origin;
+  BASE_URL = origin + BASE_URL;
+
   return new URL(path, BASE_URL).toString();
 }