feat: improve logging and add optional perf logging #248
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
moshemorad
pushed a commit
that referenced
this pull request
Jan 27, 2025
Mostly minor changes: - Remove the use of `Console` from server.py. This cascades into other changes downstream - Add latency logs behind a `LOG_PERFORMANCE` env var: - Add a wrapper for all API calls to measure the latency at API level - Add detailed performance monitoring to the tool_calling_llm core `call()` function - Align the http server (uvicorn) logging pattern with the other logging calls Example of perf metrics for tool_calling_llm: ``` 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(TOTAL) 8167ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(get_all_tools_openai_format) +0ms 0ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(start iteration 0) +0ms 0ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(count tokens) +6ms 6ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(llm.completion) +1831ms 1837ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(pre-tool-calls) +0ms 1837ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(tool completed fetch_finding_by_id) +570ms 2407ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(end iteration 0) +0ms 2407ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(start iteration 1) +0ms 2407ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(count tokens) +7ms 2415ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(llm.completion) +5752ms 8167ms ```
moshemorad
pushed a commit
that referenced
this pull request
Jan 27, 2025
Mostly minor changes: - Remove the use of `Console` from server.py. This cascades into other changes downstream - Add latency logs behind a `LOG_PERFORMANCE` env var: - Add a wrapper for all API calls to measure the latency at API level - Add detailed performance monitoring to the tool_calling_llm core `call()` function - Align the http server (uvicorn) logging pattern with the other logging calls Example of perf metrics for tool_calling_llm: ``` 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(TOTAL) 8167ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(get_all_tools_openai_format) +0ms 0ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(start iteration 0) +0ms 0ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(count tokens) +6ms 6ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(llm.completion) +1831ms 1837ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(pre-tool-calls) +0ms 1837ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(tool completed fetch_finding_by_id) +570ms 2407ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(end iteration 0) +0ms 2407ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(start iteration 1) +0ms 2407ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(count tokens) +7ms 2415ms 2025-01-14 09:41:17.177 INFO tool_calling_llm.call(llm.completion) +5752ms 8167ms ```
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Mostly minor changes:
Consolefrom server.py. This cascades into other changes downstreamLOG_PERFORMANCEenv var:call()functionExample of perf metrics for tool_calling_llm: