feat: add new LLM Prompt Performance Eval Template
#6761Comparing
Vigtu:Add-LangWatch-Prompt-Evaluation
(031a124
) withmain
(e82c218
)+14%
- Improvements
- 1
- Regressions
- 0
- Untouched
- 13
- New
- 0
- Dropped
- 0
- Ignored
- 0
Benchmarks
Improved
test_build_flow_invalid_job_id
src/backend/tests/unit/test_chat_endpoint.py::test_build_flow_invalid_job_id+14%
9.1 ms
8 ms
Passed
test_invalid_run_with_input_type_chat
src/backend/tests/unit/test_endpoints.py::test_invalid_run_with_input_type_chat+1%
16.6 ms
16.4 ms
test_build_flow
src/backend/tests/unit/test_chat_endpoint.py::test_build_flow+1%
238.2 ms
235 ms
test_build_flow_invalid_flow_id
src/backend/tests/unit/test_chat_endpoint.py::test_build_flow_invalid_flow_id+1%
490.7 ms
486.4 ms
test_successful_run_with_output_type_any
src/backend/tests/unit/test_endpoints.py::test_successful_run_with_output_type_any0%
139 ms
138.4 ms
test_starter_projects
src/backend/tests/unit/test_endpoints.py::test_starter_projects0%
1.1 s
1.1 s
test_successful_run_with_input_type_any
src/backend/tests/unit/test_endpoints.py::test_successful_run_with_input_type_any0%
145.5 ms
145.7 ms
test_get_all
src/backend/tests/unit/test_endpoints.py::test_get_all0%
616 ms
617 ms
test_build_flow_polling
src/backend/tests/unit/test_chat_endpoint.py::test_build_flow_polling0%
246.8 ms
247.2 ms
test_build_flow_from_request_data
src/backend/tests/unit/test_chat_endpoint.py::test_build_flow_from_request_data-1%
248.6 ms
251.5 ms
test_successful_run_with_output_type_debug
src/backend/tests/unit/test_endpoints.py::test_successful_run_with_output_type_debug-2%
140.6 ms
143 ms
test_build_flow_start_with_inputs
src/backend/tests/unit/test_chat_endpoint.py::test_build_flow_start_with_inputs-2%
230.9 ms
235.8 ms
test_successful_run_with_input_type_text
src/backend/tests/unit/test_endpoints.py::test_successful_run_with_input_type_text-2%
142.4 ms
145.9 ms
test_build_flow_start_only
src/backend/tests/unit/test_chat_endpoint.py::test_build_flow_start_only-4%
235.3 ms
245 ms
Commits
Click on a commit to change the comparison rangeBase
main
e82c218
+46%
Merge branch 'main' into Add-LangWatch-Prompt-Evaluation
97544dd
1 day ago
by Vigtu-32%
fix: correct template {data}
031a124
1 day ago
by Vigtu