fix: replace deleted utils.traceroot_wrapper with logging and fix line lengths

Author: MkDev11

backend/app/utils/toolkit/rag_toolkit.py

@@ -5,14 +5,15 @@
 - File/URL retrieval via information_retrieval
 - Configurable collection_name and storage_path for flexibility
 
-The toolkit is generic and portable - task isolation and other application-specific
-concerns are handled at the orchestration layer (e.g., in get_toolkits()).
+The toolkit is generic and portable - task isolation and other
+application-specific concerns are handled at the orchestration layer.
 
 # TODO: Support configurable embedding models (currently OpenAI only)
 # TODO: Add support for other vector storage backends
 """
 
 import hashlib
+import logging
 import os
 from pathlib import Path
 from typing import List, Optional, Union
@@ -27,9 +28,8 @@
 from app.component.environment import env
 from app.service.task import Agents
 from app.utils.toolkit.abstract_toolkit import AbstractToolkit
-from utils import traceroot_wrapper as traceroot
 
-logger = traceroot.get_logger("rag_toolkit")
+logger = logging.getLogger("rag_toolkit")
 
 # Default paths and constants
 DEFAULT_RAG_STORAGE_PATH = "~/.eigent/rag_storage"
@@ -64,17 +64,21 @@ def __init__(
         Args:
             api_task_id (str): Task ID for eigent integration.
             agent_name (str | None): Optional agent name override.
-            collection_name (str | None): Name for the vector collection. If not provided,
-                defaults to a generic name.
-            storage_path (str | Path | None): Path for vector storage. If not provided, uses
-                a default path.
+            collection_name (str | None): Name for the vector collection.
+                If not provided, defaults to a generic name.
+            storage_path (str | Path | None): Path for vector storage.
+                If not provided, uses a default path.
         """
         self.api_task_id = api_task_id
         if agent_name is not None:
             self.agent_name = agent_name
 
         # Use provided paths or defaults
-        self._storage_path = Path(storage_path) if storage_path else Path(os.path.expanduser(DEFAULT_RAG_STORAGE_PATH))
+        self._storage_path = (
+            Path(storage_path)
+            if storage_path
+            else Path(os.path.expanduser(DEFAULT_RAG_STORAGE_PATH))
+        )
         self._storage_path.mkdir(parents=True, exist_ok=True)
 
         self._collection_name = collection_name or DEFAULT_COLLECTION_NAME
@@ -85,8 +89,10 @@ def __init__(
             storage_type=StorageType.QDRANT,
         )
 
-        # Wrap CAMEL's RetrievalToolkit using composition (for file/URL retrieval)
-        self._retrieval_toolkit = RetrievalToolkit(auto_retriever=auto_retriever)
+        # Wrap CAMEL's RetrievalToolkit using composition
+        self._retrieval_toolkit = RetrievalToolkit(
+            auto_retriever=auto_retriever
+        )
 
         # Lazy-initialized components for raw text support
         self._embedding_model = None
@@ -98,7 +104,9 @@ def _get_embedding_model(self):
         if self._embedding_model is None:
             api_key = env("OPENAI_API_KEY")
             if not api_key:
-                raise ValueError("OPENAI_API_KEY is required for RAG embeddings")
+                raise ValueError(
+                    "OPENAI_API_KEY is required for RAG embeddings"
+                )
             self._embedding_model = OpenAIEmbedding(api_key=api_key)
         return self._embedding_model
 
@@ -128,16 +136,16 @@ def information_retrieval(
         top_k: int = 5,
         similarity_threshold: float = 0.5,
     ) -> str:
-        """Retrieves information from a local vector storage based on the query.
+        """Retrieves information from local vector storage.
 
         This method connects to a task-isolated vector storage and retrieves
         relevant information. Content is automatically indexed on first use.
 
         Args:
             query: The question or query for which an answer is required.
-            contents: Local file paths, remote URLs, or string contents to search.
+            contents: Local file paths, remote URLs, or string contents.
             top_k: Number of top results to return (default: 5).
-            similarity_threshold: Minimum similarity score for results (default: 0.5).
+            similarity_threshold: Min similarity score (default: 0.5).
 
         Returns:
             The information retrieved in response to the query.
@@ -155,7 +163,9 @@ def information_retrieval(
                 top_k=top_k,
                 similarity_threshold=similarity_threshold,
             )
-            logger.info(f"Retrieved information for query in collection {self._collection_name}")
+            logger.info(
+                f"Retrieved info for query in {self._collection_name}"
+            )
             return result
         except Exception as e:
             logger.error(f"Failed to retrieve information: {e}", exc_info=True)
@@ -169,8 +179,8 @@ def add_document(
     ) -> str:
         """Add a raw text document to the knowledge base.
 
-        This method allows adding text content directly without requiring a file.
-        Useful for adding API responses, conversation snippets, or any text data.
+        This method allows adding text content directly without a file.
+        Useful for API responses, conversation snippets, or text data.
 
         Args:
             content: The text content to add to the knowledge base.
@@ -206,8 +216,10 @@ def add_document(
             retriever = self._get_vector_retriever()
             retriever.process(content=content, extra_info=doc_metadata)
 
-            logger.info(f"Added document {doc_id} to collection {self._collection_name}")
-            return f"Successfully added document (ID: {doc_id}) to knowledge base"
+            logger.info(f"Added doc {doc_id} to {self._collection_name}")
+            return (
+                f"Successfully added document (ID: {doc_id}) to knowledge base"
+            )
 
         except Exception as e:
             logger.error(f"Failed to add document: {e}", exc_info=True)
@@ -218,14 +230,14 @@ def query_knowledge_base(
         query: str,
         top_k: int = 5,
     ) -> str:
-        """Query the knowledge base for relevant information from added documents.
+        """Query knowledge base for relevant information.
 
         This queries documents previously added via add_document().
         For querying files/URLs, use information_retrieval() instead.
 
         Args:
-            query (str): The question or search query to find relevant documents.
-            top_k (int): Maximum number of relevant chunks to return (default: 5).
+            query (str): The question or search query.
+            top_k (int): Max relevant chunks to return (default: 5).
 
         Returns:
             Retrieved relevant text chunks from the knowledge base,
@@ -257,7 +269,9 @@ def query_knowledge_base(
                         result_text += f" (Source: {source})"
                 formatted_results.append(result_text)
 
-            logger.info(f"Retrieved {len(results)} results for query in collection {self._collection_name}")
+            logger.info(
+                f"Retrieved {len(results)} results in {self._collection_name}"
+            )
             return "\n\n".join(formatted_results)
 
         except Exception as e:
@@ -278,9 +292,14 @@ def list_knowledge_bases(self) -> str:
                         collections.append(item.name)
 
             if not collections:
-                return "No knowledge bases found. Use add_document or information_retrieval to create one."
+                return (
+                    "No knowledge bases found. Use add_document or "
+                    "information_retrieval to create one."
+                )
 
-            return "Available knowledge bases:\n" + "\n".join(f"- {c}" for c in sorted(collections))
+            return "Available knowledge bases:\n" + "\n".join(
+                f"- {c}" for c in sorted(collections)
+            )
 
         except Exception as e:
             logger.error(f"Failed to list knowledge bases: {e}", exc_info=True)
@@ -314,7 +333,7 @@ def get_can_use_tools(
             storage_path (str | Path | None): Path for vector storage.
 
         Raises:
-            ValueError: If collection_name is None (must be explicitly specified).
+            ValueError: If collection_name is None.
         """
         # RAG requires OpenAI API key for embeddings
         if not env("OPENAI_API_KEY"):
@@ -323,7 +342,9 @@ def get_can_use_tools(
 
         # Require explicit collection_name for task isolation
         if collection_name is None:
-            raise ValueError("collection_name must be explicitly specified for RAG toolkit")
+            raise ValueError(
+                "collection_name must be explicitly specified for RAG toolkit"
+            )
 
         toolkit = RAGToolkit(
             api_task_id=api_task_id,