LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2025-11-29 16:43:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1764 from arc53/feat/better-logs

Browse Source 
fix: enhance error logging with exception info across multiple modules
This commit is contained in:
Alex
2025-05-05 15:13:21 +03:00
committed by GitHub
parent cf333873fd 481df4d604
commit 7daed3daaf
14 changed files with 37 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
application/agents/llm_handler.py
View File

@@ -1,5 +1,6 @@
import json
import logging
import logging
from abc import ABC, abstractmethod
from application.logging import build_stack_data
@@ -137,6 +138,7 @@ class OpenAILLMHandler(LLMHandler):
messages = self.prepare_messages_with_attachments(agent, messages, attachments)
except Exception as e:
logging.error(f"Error executing tool: {str(e)}", exc_info=True)
messages.append(
{
"role": "tool",
@@ -229,6 +231,7 @@ class OpenAILLMHandler(LLMHandler):
)
except Exception as e:
logging.error(f"Error executing tool: {str(e)}", exc_info=True)
messages.append(
{
"role": "assistant",

7
application/api/answer/routes.py
View File

@@ -105,7 +105,7 @@ def get_agent_key(agent_id, user_id):
raise Exception("Unauthorized access to the agent", 403)
except Exception as e:
logger.error(f"Error in get_agent_key: {str(e)}")
logger.error(f"Error in get_agent_key: {str(e)}", exc_info=True)
raise
@@ -351,8 +351,7 @@ def complete_stream(
data = json.dumps({"type": "end"})
yield f"data: {data}\n\n"
except Exception as e:
logger.error(f"Error in stream: {str(e)}")
logger.error(traceback.format_exc())
logger.error(f"Error in stream: {str(e)}", exc_info=True)
data = json.dumps(
{
"type": "error",
@@ -882,6 +881,6 @@ def get_attachments_content(attachment_ids, user):
if attachment_doc:
attachments.append(attachment_doc)
except Exception as e:
logger.error(f"Error retrieving attachment {attachment_id}: {e}")
logger.error(f"Error retrieving attachment {attachment_id}: {e}", exc_info=True)
return attachments

8
application/api/user/routes.py
View File

@@ -2755,7 +2755,7 @@ class GetChunks(Resource):
)
except Exception as e:
current_app.logger.error(f"Error getting chunks: {e}")
current_app.logger.error(f"Error getting chunks: {e}", exc_info=True)
return make_response(jsonify({"success": False}), 500)
@@ -2809,7 +2809,7 @@ class AddChunk(Resource):
201,
)
except Exception as e:
current_app.logger.error(f"Error adding chunk: {e}")
current_app.logger.error(f"Error adding chunk: {e}", exc_info=True)
return make_response(jsonify({"success": False}), 500)
@@ -2849,7 +2849,7 @@ class DeleteChunk(Resource):
404,
)
except Exception as e:
current_app.logger.error(f"Error deleting chunk: {e}")
current_app.logger.error(f"Error deleting chunk: {e}", exc_info=True)
return make_response(jsonify({"success": False}), 500)
@@ -2931,7 +2931,7 @@ class UpdateChunk(Resource):
200,
)
except Exception as e:
current_app.logger.error(f"Error updating chunk: {e}")
current_app.logger.error(f"Error updating chunk: {e}", exc_info=True)
return make_response(jsonify({"success": False}), 500)

8
application/cache.py
View File

@@ -61,14 +61,14 @@ def gen_cache(func):
if cached_response:
return cached_response.decode("utf-8")
except Exception as e:
logger.error(f"Error getting cached response: {e}")
logger.error(f"Error getting cached response: {e}", exc_info=True)
result = func(self, model, messages, stream, tools, *args, **kwargs)
if redis_client and isinstance(result, str):
try:
redis_client.set(cache_key, result, ex=1800)
except Exception as e:
logger.error(f"Error setting cache: {e}")
logger.error(f"Error setting cache: {e}", exc_info=True)
return result
@@ -100,7 +100,7 @@ def stream_cache(func):
time.sleep(0.03) # Simulate streaming delay
return
except Exception as e:
logger.error(f"Error getting cached stream: {e}")
logger.error(f"Error getting cached stream: {e}", exc_info=True)
stream_cache_data = []
for chunk in func(self, model, messages, stream, tools, *args, **kwargs):
@@ -112,6 +112,6 @@ def stream_cache(func):
redis_client.set(cache_key, json.dumps(stream_cache_data), ex=1800)
logger.info(f"Stream cache saved for key: {cache_key}")
except Exception as e:
logger.error(f"Error setting stream cache: {e}")
logger.error(f"Error setting stream cache: {e}", exc_info=True)
return wrapper

4
application/llm/google_ai.py
View File

@@ -78,7 +78,7 @@ class GoogleLLM(BaseLLM):
logging.info(f"GoogleLLM: Successfully uploaded file, got URI: {file_uri}")
files.append({"file_uri": file_uri, "mime_type": mime_type})
except Exception as e:
logging.error(f"GoogleLLM: Error uploading file: {e}")
logging.error(f"GoogleLLM: Error uploading file: {e}", exc_info=True)
if 'content' in attachment:
prepared_messages[user_message_index]["content"].append({
"type": "text",
@@ -131,7 +131,7 @@ class GoogleLLM(BaseLLM):
return file_uri
except Exception as e:
logging.error(f"Error uploading file to Google AI: {e}")
logging.error(f"Error uploading file to Google AI: {e}", exc_info=True)
raise
def _clean_messages_google(self, messages):

6
application/llm/openai.py
View File

@@ -213,7 +213,7 @@ class OpenAILLM(BaseLLM):
}
})
except Exception as e:
logging.error(f"Error processing image attachment: {e}")
logging.error(f"Error processing image attachment: {e}", exc_info=True)
if 'content' in attachment:
prepared_messages[user_message_index]["content"].append({
"type": "text",
@@ -228,7 +228,7 @@ class OpenAILLM(BaseLLM):
"file": {"file_id": file_id}
})
except Exception as e:
logging.error(f"Error uploading PDF to OpenAI: {e}")
logging.error(f"Error uploading PDF to OpenAI: {e}", exc_info=True)
if 'content' in attachment:
prepared_messages[user_message_index]["content"].append({
"type": "text",
@@ -301,7 +301,7 @@ class OpenAILLM(BaseLLM):
return file_id
except Exception as e:
logging.error(f"Error uploading file to OpenAI: {e}")
logging.error(f"Error uploading file to OpenAI: {e}", exc_info=True)
raise

2
application/logging.py
View File

@@ -151,4 +151,4 @@ def _log_to_mongodb(
logging.debug(f"Logged activity to MongoDB: {activity_id}")
except Exception as e:
logging.error(f"Failed to log to MongoDB: {e}")
logging.error(f"Failed to log to MongoDB: {e}", exc_info=True)

4
application/parser/embedding_pipeline.py
View File

@@ -19,7 +19,7 @@ def add_text_to_store_with_retry(store, doc, source_id):
doc.metadata["source_id"] = str(source_id)
store.add_texts([doc.page_content], metadatas=[doc.metadata])
except Exception as e:
logging.error(f"Failed to add document with retry: {e}")
logging.error(f"Failed to add document with retry: {e}", exc_info=True)
raise
@@ -75,7 +75,7 @@ def embed_and_store_documents(docs, folder_name, source_id, task_status):
# Add document to vector store
add_text_to_store_with_retry(store, doc, source_id)
except Exception as e:
logging.error(f"Error embedding document {idx}: {e}")
logging.error(f"Error embedding document {idx}: {e}", exc_info=True)
logging.info(f"Saving progress at document {idx} out of {total_docs}")
store.save_local(folder_name)
break

5
application/parser/remote/crawler_loader.py
View File

@@ -1,3 +1,4 @@
import logging
import requests
from urllib.parse import urlparse, urljoin
from bs4 import BeautifulSoup
@@ -42,7 +43,7 @@ class CrawlerLoader(BaseRemote):
)
)
except Exception as e:
print(f"Error processing URL {current_url}: {e}")
logging.error(f"Error processing URL {current_url}: {e}", exc_info=True)
continue
# Parse the HTML content to extract all links
@@ -61,4 +62,4 @@ class CrawlerLoader(BaseRemote):
if self.limit is not None and len(visited_urls) >= self.limit:
break
return loaded_content
return loaded_content

3
application/parser/remote/sitemap_loader.py
View File

@@ -1,3 +1,4 @@
import logging
import requests
import re # Import regular expression library
import xml.etree.ElementTree as ET
@@ -32,7 +33,7 @@ class SitemapLoader(BaseRemote):
documents.extend(loader.load())
processed_urls += 1 # Increment the counter after processing each URL
except Exception as e:
print(f"Error processing URL {url}: {e}")
logging.error(f"Error processing URL {url}: {e}", exc_info=True)
continue
return documents

5
application/parser/remote/web_loader.py
View File

@@ -1,3 +1,4 @@
import logging
from application.parser.remote.base import BaseRemote
from application.parser.schema.base import Document
from langchain_community.document_loaders import WebBaseLoader
@@ -39,6 +40,6 @@ class WebLoader(BaseRemote):
)
)
except Exception as e:
print(f"Error processing URL {url}: {e}")
logging.error(f"Error processing URL {url}: {e}", exc_info=True)
continue
return documents
return documents

3
application/retriever/classic_rag.py
View File

@@ -1,3 +1,4 @@
import logging
from application.core.settings import settings
from application.llm.llm_creator import LLMCreator
from application.retriever.base import BaseRetriever
@@ -72,7 +73,7 @@ class ClassicRAG(BaseRetriever):
print(f"Rephrased query: {rephrased_query}")
return rephrased_query if rephrased_query else self.original_question
except Exception as e:
print(f"Error rephrasing query: {e}")
logging.error(f"Error rephrasing query: {e}", exc_info=True)
return self.original_question
def _get_data(self):

5
application/vectorstore/mongodb.py
View File

@@ -1,3 +1,4 @@
import logging
from application.core.settings import settings
from application.vectorstore.base import BaseVectorStore
from application.vectorstore.document_class import Document
@@ -146,7 +147,7 @@ class MongoDBVectorStore(BaseVectorStore):
return chunks
except Exception as e:
print(f"Error getting chunks: {e}")
logging.error(f"Error getting chunks: {e}", exc_info=True)
return []
def add_chunk(self, text, metadata=None):
@@ -172,5 +173,5 @@ class MongoDBVectorStore(BaseVectorStore):
result = self._collection.delete_one({"_id": object_id})
return result.deleted_count > 0
except Exception as e:
print(f"Error deleting chunk: {e}")
logging.error(f"Error deleting chunk: {e}", exc_info=True)
return False

4
application/worker.py
View File

@@ -75,7 +75,7 @@ def extract_zip_recursive(zip_path, extract_to, current_depth=0, max_depth=5):
zip_ref.extractall(extract_to)
os.remove(zip_path) # Remove the zip file after extracting
except Exception as e:
logging.error(f"Error extracting zip file {zip_path}: {e}")
logging.error(f"Error extracting zip file {zip_path}: {e}", exc_info=True)
return
# Check for nested zip files and extract them
@@ -403,7 +403,7 @@ def sync(
doc_id,
)
except Exception as e:
logging.error(f"Error during sync: {e}")
logging.error(f"Error during sync: {e}", exc_info=True)
return {"status": "error", "error": str(e)}
return {"status": "success"}