apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-26 09:16:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: enhance performance logging and caching in various components

Browse source 
- Introduced slow callback logging in FastAPI to identify blocking calls.
- Added performance logging for agent creation and tool loading processes.
- Implemented caching for MCP tools to reduce redundant server calls.
- Enhanced sandbox management with in-process caching for improved efficiency.
- Refactored several functions for better readability and performance tracking.
- Updated tests to ensure proper functionality of new features and optimizations.
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-02-26 13:00:31 -08:00
parent 2e99f1e853
commit aabc24f82c
22 changed files with 637 additions and 200 deletions
Download patch file Download diff file Expand all files Collapse all files

40
surfsense_backend/app/indexing_pipeline/exceptions.py
View file

@ -12,7 +12,7 @@ from litellm.exceptions import (
Timeout,
UnprocessableEntityError,
)
from sqlalchemy.exc import IntegrityError
from sqlalchemy.exc import IntegrityError as IntegrityError
# Tuples for use directly in except clauses.
RETRYABLE_LLM_ERRORS = (
@ -36,29 +36,33 @@ PERMANENT_LLM_ERRORS = (
# (LiteLLMEmbeddings, CohereEmbeddings, GeminiEmbeddings all normalize to RuntimeError).
EMBEDDING_ERRORS = (
RuntimeError, # local device failure or API backend normalization
OSError, # model files missing or corrupted (local backends)
MemoryError, # document too large for available RAM
OSError, # model files missing or corrupted (local backends)
MemoryError, # document too large for available RAM
)
class PipelineMessages:
RATE_LIMIT = "LLM rate limit exceeded. Will retry on next sync."
LLM_TIMEOUT = "LLM request timed out. Will retry on next sync."
LLM_UNAVAILABLE = "LLM service temporarily unavailable. Will retry on next sync."
LLM_BAD_GATEWAY = "LLM gateway error. Will retry on next sync."
LLM_SERVER_ERROR = "LLM internal server error. Will retry on next sync."
LLM_CONNECTION = "Could not reach the LLM service. Check network connectivity."
RATE_LIMIT = "LLM rate limit exceeded. Will retry on next sync."
LLM_TIMEOUT = "LLM request timed out. Will retry on next sync."
LLM_UNAVAILABLE = "LLM service temporarily unavailable. Will retry on next sync."
LLM_BAD_GATEWAY = "LLM gateway error. Will retry on next sync."
LLM_SERVER_ERROR = "LLM internal server error. Will retry on next sync."
LLM_CONNECTION = "Could not reach the LLM service. Check network connectivity."
LLM_AUTH = "LLM authentication failed. Check your API key."
LLM_PERMISSION = "LLM request denied. Check your account permissions."
LLM_NOT_FOUND = "LLM model not found. Check your model configuration."
LLM_BAD_REQUEST = "LLM rejected the request. Document content may be invalid."
LLM_UNPROCESSABLE = "Document exceeds the LLM context window even after optimization."
LLM_RESPONSE = "LLM returned an invalid response."
LLM_AUTH = "LLM authentication failed. Check your API key."
LLM_PERMISSION = "LLM request denied. Check your account permissions."
LLM_NOT_FOUND = "LLM model not found. Check your model configuration."
LLM_BAD_REQUEST = "LLM rejected the request. Document content may be invalid."
LLM_UNPROCESSABLE = (
"Document exceeds the LLM context window even after optimization."
)
LLM_RESPONSE = "LLM returned an invalid response."
EMBEDDING_FAILED = "Embedding failed. Check your embedding model configuration or service."
EMBEDDING_MODEL = "Embedding model files are missing or corrupted."
EMBEDDING_MEMORY = "Not enough memory to embed this document."
EMBEDDING_FAILED = (
"Embedding failed. Check your embedding model configuration or service."
)
EMBEDDING_MODEL = "Embedding model files are missing or corrupted."
EMBEDDING_MEMORY = "Not enough memory to embed this document."
CHUNKING_OVERFLOW = "Document structure is too deeply nested to chunk."