ragflow in the repository, with codex-created yandex disk plugin JUST IN CASE, also llamaindex enrichment with yandex disk predefined data

services/rag/llamaindex/retrieval.py

@@ -14,7 +14,7 @@ from llama_index.core.retrievers import VectorIndexRetriever
 from loguru import logger
 from pathlib import Path
 
-from vector_storage import get_vector_store_and_index
+from vector_storage import get_qdrant_connection_config, get_vector_store_and_index
 
 # Import the new configuration module
 from config import setup_global_models
@@ -23,8 +23,9 @@ from config import setup_global_models
 def initialize_retriever(
     collection_name: str = "documents_llamaindex",
     similarity_top_k: int = 5,
-    host: str = "localhost",
-    port: int = 6333
+    host: str | None = None,
+    port: int | None = None,
+    grpc_port: int | None = None,
 ) -> RetrieverQueryEngine:
     """
     Initialize the retriever query engine with the vector store.
@@ -32,8 +33,9 @@ def initialize_retriever(
     Args:
         collection_name: Name of the Qdrant collection
         similarity_top_k: Number of top similar documents to retrieve
-        host: Qdrant host address
-        port: Qdrant REST API port
+        host: Qdrant host address (defaults to QDRANT_HOST from .env)
+        port: Qdrant REST API port (defaults to QDRANT_REST_PORT from .env)
+        grpc_port: Qdrant gRPC API port (defaults to QDRANT_GRPC_PORT from .env)
 
     Returns:
         RetrieverQueryEngine configured with the vector store
@@ -44,8 +46,23 @@ def initialize_retriever(
         # Set up the global models to prevent defaulting to OpenAI
         setup_global_models()
 
+        qdrant_config = get_qdrant_connection_config()
+        resolved_host = host or str(qdrant_config["host"])
+        resolved_port = port or int(qdrant_config["port"])
+        resolved_grpc_port = grpc_port or int(qdrant_config["grpc_port"])
+
+        logger.info(
+            f"Retriever Qdrant connection: host={resolved_host}, "
+            f"rest_port={resolved_port}, grpc_port={resolved_grpc_port}"
+        )
+
         # Get the vector store and index from the existing configuration
-        vector_store, index = get_vector_store_and_index()
+        vector_store, index = get_vector_store_and_index(
+            collection_name=collection_name,
+            host=resolved_host,
+            port=resolved_port,
+            grpc_port=resolved_grpc_port,
+        )
 
         # Create a retriever from the index
         retriever = VectorIndexRetriever(
@@ -310,4 +327,4 @@ if __name__ == "__main__":
 
     except Exception as e:
         logger.error(f"Error in test run: {e}")
-        print(f"Error: {e}")
+        print(f"Error: {e}")