Better wrap traceable (#12303)

If user function is wrapped as a traceable function, this will help hand
off the trace between the two.

Also update handling fields to reflect optional values
pull/12309/head
William FH 12 months ago committed by GitHub
parent 5a71b81609
commit 1d568e1add
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -237,7 +237,7 @@ class LogStreamCallbackHandler(BaseTracer):
name=run.name,
type=run.run_type,
tags=run.tags or [],
metadata=run.extra.get("metadata", {}),
metadata=(run.extra or {}).get("metadata", {}),
start_time=run.start_time.isoformat(timespec="milliseconds"),
streamed_output_str=[],
final_output=None,
@ -266,7 +266,9 @@ class LogStreamCallbackHandler(BaseTracer):
{
"op": "add",
"path": f"/logs/{index}/end_time",
"value": run.end_time.isoformat(timespec="milliseconds"),
"value": run.end_time.isoformat(timespec="milliseconds")
if run.end_time is not None
else None,
},
)
)

@ -3,7 +3,7 @@ from __future__ import annotations
import datetime
import warnings
from typing import Any, Dict, List, Optional
from typing import Any, Dict, List, Optional, Type
from uuid import UUID
from langsmith.schemas import RunBase as BaseRunV2
@ -13,7 +13,7 @@ from langchain.pydantic_v1 import BaseModel, Field, root_validator
from langchain.schema import LLMResult
def RunTypeEnum() -> RunTypeEnumDep:
def RunTypeEnum() -> Type[RunTypeEnumDep]:
"""RunTypeEnum."""
warnings.warn(
"RunTypeEnum is deprecated. Please directly use a string instead"
@ -106,6 +106,7 @@ class Run(BaseRunV2):
child_execution_order: int
child_runs: List[Run] = Field(default_factory=list)
tags: Optional[List[str]] = Field(default_factory=list)
events: List[Dict[str, Any]] = Field(default_factory=list)
@root_validator(pre=True)
def assign_name(cls, values: dict) -> dict:
@ -115,6 +116,8 @@ class Run(BaseRunV2):
values["name"] = values["serialized"]["name"]
elif "id" in values["serialized"]:
values["name"] = values["serialized"]["id"][-1]
if values.get("events") is None:
values["events"] = []
return values

@ -27,7 +27,9 @@ if TYPE_CHECKING:
PRINT_WARNINGS = True
def _serialize_io(run_inputs: dict) -> dict:
def _serialize_io(run_inputs: Optional[dict]) -> dict:
if not run_inputs:
return {}
from google.protobuf.json_format import MessageToJson
from google.protobuf.message import Message
@ -79,7 +81,9 @@ class RunProcessor:
span_id=str(run.id) if run.id is not None else None,
name=run.name,
start_time_ms=int(run.start_time.timestamp() * 1000),
end_time_ms=int(run.end_time.timestamp() * 1000),
end_time_ms=int(run.end_time.timestamp() * 1000)
if run.end_time is not None
else None,
status_code=self.trace_tree.StatusCode.SUCCESS
if run.error is None
else self.trace_tree.StatusCode.ERROR,
@ -95,7 +99,7 @@ class RunProcessor:
base_span = self._convert_run_to_wb_span(run)
if base_span.attributes is None:
base_span.attributes = {}
base_span.attributes["llm_output"] = run.outputs.get("llm_output", {})
base_span.attributes["llm_output"] = (run.outputs or {}).get("llm_output", {})
base_span.results = [
self.trace_tree.Result(

@ -1,7 +1,7 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Dict, Iterable, Iterator, List, Optional, Union
from typing import TYPE_CHECKING, Dict, Iterable, Iterator, List, Optional, Union, cast
from langchain.chat_loaders.base import BaseChatLoader
from langchain.load import load
@ -79,7 +79,7 @@ class LangSmithRunChatLoader(BaseChatLoader):
"""
if llm_run.run_type != "llm":
raise ValueError(f"Expected run of type llm. Got: {llm_run.run_type}")
return llm_run.extra.get("invocation_params", {}).get("functions")
return (llm_run.extra or {}).get("invocation_params", {}).get("functions")
def lazy_load(self) -> Iterator[ChatSession]:
"""
@ -90,13 +90,15 @@ class LangSmithRunChatLoader(BaseChatLoader):
:return: Iterator of chat sessions containing messages.
"""
from langsmith.schemas import Run
for run_obj in self.runs:
try:
if hasattr(run_obj, "id"):
run = run_obj
else:
run = self.client.read_run(run_obj)
session = self._load_single_chat_session(run)
session = self._load_single_chat_session(cast(Run, run))
yield session
except ValueError as e:
logger.warning(f"Could not load run {run_obj}: {repr(e)}")

@ -19,7 +19,9 @@ from typing import (
cast,
)
from langsmith import Client, RunEvaluator
from langsmith.client import Client
from langsmith.evaluation import RunEvaluator
from langsmith.run_helpers import as_runnable, is_traceable_function
from langsmith.schemas import Dataset, DataType, Example
from langchain._api import warn_deprecated
@ -152,6 +154,9 @@ def _wrap_in_chain_factory(
lcf = llm_or_chain_factory
return lambda: lcf
elif callable(llm_or_chain_factory):
if is_traceable_function(llm_or_chain_factory):
runnable_ = as_runnable(cast(Callable, llm_or_chain_factory))
return lambda: runnable_
try:
_model = llm_or_chain_factory() # type: ignore[call-arg]
except TypeError:
@ -166,6 +171,9 @@ def _wrap_in_chain_factory(
# It's not uncommon to do an LLM constructor instead of raw LLM,
# so we'll unpack it for the user.
return _model
elif is_traceable_function(cast(Callable, _model)):
runnable_ = as_runnable(cast(Callable, _model))
return lambda: runnable_
elif not isinstance(_model, Runnable):
# This is unlikely to happen - a constructor for a model function
return lambda: RunnableLambda(constructor)
@ -879,7 +887,8 @@ def _prepare_eval_run(
f"Project {project_name} already exists. Please use a different name."
)
print(
f"View the evaluation results for project '{project_name}' at:\n{project.url}",
f"View the evaluation results for project '{project_name}'"
f" at:\n{project.url}?eval=true",
flush=True,
)
examples = list(client.list_examples(dataset_id=dataset.id))
@ -909,7 +918,7 @@ def _prepare_run_on_dataset(
)
wrapped_model = _wrap_in_chain_factory(llm_or_chain_factory)
run_evaluators = _setup_evaluation(
wrapped_model, examples, evaluation, dataset.data_type
wrapped_model, examples, evaluation, dataset.data_type or DataType.kv
)
_validate_example_inputs(examples[0], wrapped_model, input_mapper)
progress_bar = progress.ProgressBarCallback(len(examples))

@ -3729,7 +3729,6 @@ optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*"
files = [
{file = "jsonpointer-2.4-py2.py3-none-any.whl", hash = "sha256:15d51bba20eea3165644553647711d150376234112651b4f1811022aecad7d7a"},
{file = "jsonpointer-2.4.tar.gz", hash = "sha256:585cee82b70211fa9e6043b7bb89db6e1aa49524340dde8ad6b63206ea689d88"},
]
[[package]]
@ -4098,13 +4097,13 @@ all = ["datasets (>=2.12.0,<3.0.0)", "evaluate (>=0.4.0,<0.5.0)", "faiss-cpu (>=
[[package]]
name = "langsmith"
version = "0.0.44"
version = "0.0.52"
description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
optional = false
python-versions = ">=3.8.1,<4.0"
files = [
{file = "langsmith-0.0.44-py3-none-any.whl", hash = "sha256:5e7e5b45360ce89a2d5d6066a3b9fdd31b1f874a0cf19b1666c9792fecef0a1b"},
{file = "langsmith-0.0.44.tar.gz", hash = "sha256:74a262ba23a958ca1a4863d5386c151be462e40ccfcb8b39d0a5d8c9eaa40164"},
{file = "langsmith-0.0.52-py3-none-any.whl", hash = "sha256:d02a0ade5a53b36143084e57003ed38ccbdf5fc15a5a0eb14f8989ceaee0b807"},
{file = "langsmith-0.0.52.tar.gz", hash = "sha256:1dc29082d257deea1859cb22c53d9481ca5c4a37f3af40c0f9d300fb8adc91db"},
]
[package.dependencies]
@ -4537,16 +4536,6 @@ files = [
{file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5bbe06f8eeafd38e5d0a4894ffec89378b6c6a625ff57e3028921f8ff59318ac"},
{file = "MarkupSafe-2.1.3-cp311-cp311-win32.whl", hash = "sha256:dd15ff04ffd7e05ffcb7fe79f1b98041b8ea30ae9234aed2a9168b5797c3effb"},
{file = "MarkupSafe-2.1.3-cp311-cp311-win_amd64.whl", hash = "sha256:134da1eca9ec0ae528110ccc9e48041e0828d79f24121a1a146161103c76e686"},
{file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f698de3fd0c4e6972b92290a45bd9b1536bffe8c6759c62471efaa8acb4c37bc"},
{file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:aa57bd9cf8ae831a362185ee444e15a93ecb2e344c8e52e4d721ea3ab6ef1823"},
{file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffcc3f7c66b5f5b7931a5aa68fc9cecc51e685ef90282f4a82f0f5e9b704ad11"},
{file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47d4f1c5f80fc62fdd7777d0d40a2e9dda0a05883ab11374334f6c4de38adffd"},
{file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1f67c7038d560d92149c060157d623c542173016c4babc0c1913cca0564b9939"},
{file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:9aad3c1755095ce347e26488214ef77e0485a3c34a50c5a5e2471dff60b9dd9c"},
{file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:14ff806850827afd6b07a5f32bd917fb7f45b046ba40c57abdb636674a8b559c"},
{file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8f9293864fe09b8149f0cc42ce56e3f0e54de883a9de90cd427f191c346eb2e1"},
{file = "MarkupSafe-2.1.3-cp312-cp312-win32.whl", hash = "sha256:715d3562f79d540f251b99ebd6d8baa547118974341db04f5ad06d5ea3eb8007"},
{file = "MarkupSafe-2.1.3-cp312-cp312-win_amd64.whl", hash = "sha256:1b8dd8c3fd14349433c79fa8abeb573a55fc0fdd769133baac1f5e07abf54aeb"},
{file = "MarkupSafe-2.1.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8e254ae696c88d98da6555f5ace2279cf7cd5b3f52be2b5cf97feafe883b58d2"},
{file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb0932dc158471523c9637e807d9bfb93e06a95cbf010f1a38b98623b929ef2b"},
{file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9402b03f1a1b4dc4c19845e5c749e3ab82d5078d16a2a4c2cd2df62d57bb0707"},
@ -7650,7 +7639,6 @@ files = [
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
{file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
{file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
{file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
{file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@ -7658,15 +7646,8 @@ files = [
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
{file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
{file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
{file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
{file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
{file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
{file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
{file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
{file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@ -7683,7 +7664,6 @@ files = [
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
{file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
{file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
{file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
{file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@ -7691,7 +7671,6 @@ files = [
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
{file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
{file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
{file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
{file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@ -8655,11 +8634,6 @@ files = [
{file = "scikit_learn-1.3.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f66eddfda9d45dd6cadcd706b65669ce1df84b8549875691b1f403730bdef217"},
{file = "scikit_learn-1.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c6448c37741145b241eeac617028ba6ec2119e1339b1385c9720dae31367f2be"},
{file = "scikit_learn-1.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:c413c2c850241998168bbb3bd1bb59ff03b1195a53864f0b80ab092071af6028"},
{file = "scikit_learn-1.3.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ef540e09873e31569bc8b02c8a9f745ee04d8e1263255a15c9969f6f5caa627f"},
{file = "scikit_learn-1.3.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:9147a3a4df4d401e618713880be023e36109c85d8569b3bf5377e6cd3fecdeac"},
{file = "scikit_learn-1.3.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d2cd3634695ad192bf71645702b3df498bd1e246fc2d529effdb45a06ab028b4"},
{file = "scikit_learn-1.3.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c275a06c5190c5ce00af0acbb61c06374087949f643ef32d355ece12c4db043"},
{file = "scikit_learn-1.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:0e1aa8f206d0de814b81b41d60c1ce31f7f2c7354597af38fae46d9c47c45122"},
{file = "scikit_learn-1.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:52b77cc08bd555969ec5150788ed50276f5ef83abb72e6f469c5b91a0009bbca"},
{file = "scikit_learn-1.3.1-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:a683394bc3f80b7c312c27f9b14ebea7766b1f0a34faf1a2e9158d80e860ec26"},
{file = "scikit_learn-1.3.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a15d964d9eb181c79c190d3dbc2fff7338786bf017e9039571418a1d53dab236"},
@ -10973,4 +10947,4 @@ text-helpers = ["chardet"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.8.1,<4.0"
content-hash = "a36eb1f9d28e59ddc0cc5f3eee584ee4e054c8a87bf7c3c9a258b4a319aa1744"
content-hash = "36c742f7330bc9670d998bdc3ec6bf4babd4fe4712191afc9fa12b2bd71ccbf9"

@ -114,7 +114,7 @@ cassio = {version = "^0.1.0", optional = true}
rdflib = {version = "^6.3.2", optional = true}
sympy = {version = "^1.12", optional = true}
rapidfuzz = {version = "^3.1.1", optional = true}
langsmith = "~0.0.43"
langsmith = "~0.0.52"
rank-bm25 = {version = "^0.2.2", optional = true}
amadeus = {version = ">=8.1.0", optional = true}
geopandas = {version = "^0.13.1", optional = true}

@ -2867,6 +2867,7 @@ def test_metadata_is_merged() -> None:
with collect_runs() as cb:
foo.invoke("hi", {"metadata": {"my_other_key": "my_other_value"}})
run = cb.traced_runs[0]
assert run.extra is not None
assert run.extra["metadata"] == expected_metadata
@ -3526,6 +3527,7 @@ def test_seq_batch_return_exceptions(mocker: MockerFixture) -> None:
parent_run_qux = parent_runs[3]
assert parent_run_qux.inputs["input"] == "qux"
assert parent_run_qux.error is None
assert parent_run_qux.outputs is not None
assert parent_run_qux.outputs["output"] == "quxaaaa"
assert len(parent_run_qux.child_runs) == 4
assert [r.error for r in parent_run_qux.child_runs] == [None, None, None, None]
@ -3648,6 +3650,7 @@ async def test_seq_abatch_return_exceptions(mocker: MockerFixture) -> None:
parent_run_qux = parent_runs[3]
assert parent_run_qux.inputs["input"] == "qux"
assert parent_run_qux.error is None
assert parent_run_qux.outputs is not None
assert parent_run_qux.outputs["output"] == "quxaaaa"
assert len(parent_run_qux.child_runs) == 4
assert [r.error for r in parent_run_qux.child_runs] == [None, None, None, None]

@ -331,14 +331,17 @@ async def test_arun_on_dataset(monkeypatch: pytest.MonkeyPatch) -> None:
project_name="test_project",
client=client,
)
expected = {
str(example.id): {
"output": {
"result": f"Result for example {uuid.UUID(str(example.id))}"
},
"input": {"input": example.inputs["input"]},
"reference": {"output": example.outputs["output"]},
"reference": {
"output": example.outputs["output"]
if example.outputs is not None
else None
},
"feedback": [],
}
for example in examples

@ -23,5 +23,5 @@ def test_evaluate_run() -> None:
run = MagicMock()
example = MagicMock()
res = evaluator.evaluate_run(run, example)
assert res.comment.startswith("Error evaluating run ")
assert str(res.comment).startswith("Error evaluating run ")
assert res.key == string_evaluator.evaluation_name

Loading…
Cancel
Save