mirror of
https://github.com/open-telemetry/opentelemetry-python-contrib.git
synced 2025-08-02 02:52:18 +08:00
[chore] Address TODO to migrate to VCRpy and remove bespoke RequestMocker code in Google GenAI SDK instrumentation (#3344)
* Remove bespoke request mocker. Replace with direct mocking of the underlying API. * Refactor fake credentials to enable reuse. * Add module to test end to end with a real client. * Add redaction and minimal OTel mocking/testing in the e2e test. * Fix wording of the documentation. * Remove vcr migration from TODOs. * Improve redaction and test naming. * Minor tweaks in the code generation. Add casette files. * Reformat with ruff. * Fix lint and gzip issue. * Reformat with ruff. * Prevent fix for Python 3.9 from breaking tests in other versions. * Record update in changelog. * Don't double iterate when redacting by changing the value. Co-authored-by: Aaron Abbott <aaronabbott@google.com> --------- Co-authored-by: Aaron Abbott <aaronabbott@google.com>
This commit is contained in:
Michael Safyan
@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## Unreleased
|
||||
|
||||
- Restructure tests to keep in line with repository conventions ([#3344](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3344))
|
||||
|
||||
## Version 0.1b0 (2025-03-05)
|
||||
|
||||
- Add support for async and streaming.
|
||||
|
||||
@ -13,7 +13,6 @@ Here are some TODO items required to achieve stability for this package:
|
||||
- Additional cleanup/improvement tasks such as:
|
||||
- Adoption of 'wrapt' instead of 'functools.wraps'
|
||||
- Bolstering test coverage
|
||||
- Migrate tests to use VCR.py
|
||||
|
||||
## Future
|
||||
|
||||
|
||||
@ -0,0 +1,20 @@
|
||||
# Copyright The OpenTelemetry Authors
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import google.auth.credentials
|
||||
|
||||
|
||||
class FakeCredentials(google.auth.credentials.AnonymousCredentials):
|
||||
def refresh(self, request):
|
||||
pass
|
||||
@ -17,29 +17,22 @@ import unittest
|
||||
|
||||
import google.genai
|
||||
|
||||
from .auth import FakeCredentials
|
||||
from .instrumentation_context import InstrumentationContext
|
||||
from .otel_mocker import OTelMocker
|
||||
from .requests_mocker import RequestsMocker
|
||||
|
||||
|
||||
class _FakeCredentials(google.auth.credentials.AnonymousCredentials):
|
||||
def refresh(self, request):
|
||||
pass
|
||||
|
||||
|
||||
class TestCase(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self._otel = OTelMocker()
|
||||
self._otel.install()
|
||||
self._requests = RequestsMocker()
|
||||
self._requests.install()
|
||||
self._instrumentation_context = None
|
||||
self._api_key = "test-api-key"
|
||||
self._project = "test-project"
|
||||
self._location = "test-location"
|
||||
self._client = None
|
||||
self._uses_vertex = False
|
||||
self._credentials = _FakeCredentials()
|
||||
self._credentials = FakeCredentials()
|
||||
|
||||
def _lazy_init(self):
|
||||
self._instrumentation_context = InstrumentationContext()
|
||||
@ -51,10 +44,6 @@ class TestCase(unittest.TestCase):
|
||||
self._client = self._create_client()
|
||||
return self._client
|
||||
|
||||
@property
|
||||
def requests(self):
|
||||
return self._requests
|
||||
|
||||
@property
|
||||
def otel(self):
|
||||
return self._otel
|
||||
@ -62,6 +51,15 @@ class TestCase(unittest.TestCase):
|
||||
def set_use_vertex(self, use_vertex):
|
||||
self._uses_vertex = use_vertex
|
||||
|
||||
def reset_client(self):
|
||||
self._client = None
|
||||
|
||||
def reset_instrumentation(self):
|
||||
if self._instrumentation_context is None:
|
||||
return
|
||||
self._instrumentation_context.uninstall()
|
||||
self._instrumentation_context = None
|
||||
|
||||
def _create_client(self):
|
||||
self._lazy_init()
|
||||
if self._uses_vertex:
|
||||
@ -72,10 +70,9 @@ class TestCase(unittest.TestCase):
|
||||
location=self._location,
|
||||
credentials=self._credentials,
|
||||
)
|
||||
return google.genai.Client(api_key=self._api_key)
|
||||
return google.genai.Client(vertexai=False, api_key=self._api_key)
|
||||
|
||||
def tearDown(self):
|
||||
if self._instrumentation_context is not None:
|
||||
self._instrumentation_context.uninstall()
|
||||
self._requests.uninstall()
|
||||
self._otel.uninstall()
|
||||
|
||||
@ -1,238 +0,0 @@
|
||||
# Copyright The OpenTelemetry Authors
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
# This file defines a "RequestMocker" that facilities mocking the "requests"
|
||||
# API. There are a few reasons that we use this approach to testing:
|
||||
#
|
||||
# 1. Security - although "vcrpy" provides a means of filtering data,
|
||||
# it can be error-prone; use of this solution risks exposing API keys,
|
||||
# auth tokens, etc. It can also inadvertently record fields that are
|
||||
# visibility-restricted (such as fields that are returned and available
|
||||
# when recording using privileged API keys where such fields would not
|
||||
# ordinarily be returned to users with non-privileged API keys).
|
||||
#
|
||||
# 2. Reproducibility - although the tests may be reproducible once the
|
||||
# recording is present, updating the recording often has external
|
||||
# dependencies that may be difficult to reproduce.
|
||||
#
|
||||
# 3. Costs - there are both time costs and monetary costs to the external
|
||||
# dependencies required for a record/replay solution.
|
||||
#
|
||||
# Because they APIs that need to be mocked are simple enough and well documented
|
||||
# enough, it seems approachable to mock the requests library, instead.
|
||||
|
||||
import copy
|
||||
import functools
|
||||
import http.client
|
||||
import io
|
||||
import json
|
||||
from typing import Optional
|
||||
|
||||
import requests
|
||||
import requests.sessions
|
||||
|
||||
|
||||
class RequestsCallArgs:
|
||||
def __init__(
|
||||
self,
|
||||
session: requests.sessions.Session,
|
||||
request: requests.PreparedRequest,
|
||||
**kwargs,
|
||||
):
|
||||
self._session = session
|
||||
self._request = request
|
||||
self._kwargs = kwargs
|
||||
|
||||
@property
|
||||
def session(self):
|
||||
return self._session
|
||||
|
||||
@property
|
||||
def request(self):
|
||||
return self._request
|
||||
|
||||
@property
|
||||
def kwargs(self):
|
||||
return self._kwargs
|
||||
|
||||
|
||||
class RequestsCall:
|
||||
def __init__(self, args: RequestsCallArgs, response_generator):
|
||||
self._args = args
|
||||
self._response_generator = response_generator
|
||||
|
||||
@property
|
||||
def args(self):
|
||||
return self._args
|
||||
|
||||
@property
|
||||
def response(self):
|
||||
return self._response_generator(self._args)
|
||||
|
||||
|
||||
def _return_error_status(
|
||||
args: RequestsCallArgs, status_code: int, reason: Optional[str] = None
|
||||
):
|
||||
result = requests.Response()
|
||||
result.url = args.request.url
|
||||
result.status_code = status_code
|
||||
result.reason = reason or http.client.responses.get(status_code)
|
||||
result.request = args.request
|
||||
return result
|
||||
|
||||
|
||||
def _return_404(args: RequestsCallArgs):
|
||||
return _return_error_status(args, 404, "Not Found")
|
||||
|
||||
|
||||
def _to_response_generator(response):
|
||||
if response is None:
|
||||
raise ValueError("response must not be None")
|
||||
if isinstance(response, int):
|
||||
return lambda args: _return_error_status(args, response)
|
||||
if isinstance(response, requests.Response):
|
||||
|
||||
def generate_response_from_response(args):
|
||||
new_response = copy.deepcopy(response)
|
||||
new_response.request = args.request
|
||||
new_response.url = args.request.url
|
||||
return new_response
|
||||
|
||||
return generate_response_from_response
|
||||
if isinstance(response, dict):
|
||||
|
||||
def generate_response_from_dict(args):
|
||||
result = requests.Response()
|
||||
result.status_code = 200
|
||||
result.headers["content-type"] = "application/json"
|
||||
result.encoding = "utf-8"
|
||||
result.raw = io.BytesIO(json.dumps(response).encode())
|
||||
return result
|
||||
|
||||
return generate_response_from_dict
|
||||
raise ValueError(f"Unsupported response type: {type(response)}")
|
||||
|
||||
|
||||
def _to_stream_response_generator(response_generators):
|
||||
if len(response_generators) == 1:
|
||||
return response_generators[0]
|
||||
|
||||
def combined_generator(args):
|
||||
first_response = response_generators[0](args)
|
||||
if first_response.status_code != 200:
|
||||
return first_response
|
||||
result = requests.Response()
|
||||
result.status_code = 200
|
||||
result.headers["content-type"] = "application/json"
|
||||
result.encoding = "utf-8"
|
||||
result.headers["transfer-encoding"] = "chunked"
|
||||
contents = []
|
||||
for generator in response_generators:
|
||||
response = generator(args)
|
||||
if response.status_code != 200:
|
||||
continue
|
||||
response_json = response.json()
|
||||
response_json_str = json.dumps(response_json)
|
||||
contents.append(f"data: {response_json_str}")
|
||||
contents_str = "\r\n".join(contents)
|
||||
full_contents = f"{contents_str}\r\n\r\n"
|
||||
result.raw = io.BytesIO(full_contents.encode())
|
||||
return result
|
||||
|
||||
return combined_generator
|
||||
|
||||
|
||||
class RequestsMocker:
|
||||
def __init__(self):
|
||||
self._original_send = requests.sessions.Session.send
|
||||
self._calls = []
|
||||
self._handlers = []
|
||||
|
||||
def install(self):
|
||||
@functools.wraps(requests.sessions.Session.send)
|
||||
def replacement_send(
|
||||
s: requests.sessions.Session,
|
||||
request: requests.PreparedRequest,
|
||||
**kwargs,
|
||||
):
|
||||
return self._do_send(s, request, **kwargs)
|
||||
|
||||
requests.sessions.Session.send = replacement_send
|
||||
|
||||
def uninstall(self):
|
||||
requests.sessions.Session.send = self._original_send
|
||||
|
||||
def reset(self):
|
||||
self._calls = []
|
||||
self._handlers = []
|
||||
|
||||
def add_response(self, response, if_matches=None):
|
||||
self._handlers.append((if_matches, _to_response_generator(response)))
|
||||
|
||||
@property
|
||||
def calls(self):
|
||||
return self._calls
|
||||
|
||||
def _do_send(
|
||||
self,
|
||||
session: requests.sessions.Session,
|
||||
request: requests.PreparedRequest,
|
||||
**kwargs,
|
||||
):
|
||||
stream = kwargs.get("stream", False)
|
||||
if not stream:
|
||||
return self._do_send_non_streaming(session, request, **kwargs)
|
||||
return self._do_send_streaming(session, request, **kwargs)
|
||||
|
||||
def _do_send_streaming(
|
||||
self,
|
||||
session: requests.sessions.Session,
|
||||
request: requests.PreparedRequest,
|
||||
**kwargs,
|
||||
):
|
||||
args = RequestsCallArgs(session, request, **kwargs)
|
||||
response_generators = []
|
||||
for matcher, response_generator in self._handlers:
|
||||
if matcher is None:
|
||||
response_generators.append(response_generator)
|
||||
elif matcher(args):
|
||||
response_generators.append(response_generator)
|
||||
if not response_generators:
|
||||
response_generators.append(_return_404)
|
||||
response_generator = _to_stream_response_generator(response_generators)
|
||||
call = RequestsCall(args, response_generator)
|
||||
result = call.response
|
||||
self._calls.append(call)
|
||||
return result
|
||||
|
||||
def _do_send_non_streaming(
|
||||
self,
|
||||
session: requests.sessions.Session,
|
||||
request: requests.PreparedRequest,
|
||||
**kwargs,
|
||||
):
|
||||
args = RequestsCallArgs(session, request, **kwargs)
|
||||
response_generator = self._lookup_response_generator(args)
|
||||
call = RequestsCall(args, response_generator)
|
||||
result = call.response
|
||||
self._calls.append(call)
|
||||
return result
|
||||
|
||||
def _lookup_response_generator(self, args: RequestsCallArgs):
|
||||
for matcher, response_generator in self._handlers:
|
||||
if matcher is None:
|
||||
return response_generator
|
||||
if matcher(args):
|
||||
return response_generator
|
||||
return _return_404
|
||||
@ -0,0 +1,163 @@
|
||||
# Copyright The OpenTelemetry Authors
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import unittest
|
||||
import unittest.mock
|
||||
|
||||
from google.genai.models import AsyncModels, Models
|
||||
|
||||
from ..common.base import TestCase as CommonTestCaseBase
|
||||
from .util import convert_to_response, create_response
|
||||
|
||||
|
||||
# Helper used in "_install_mocks" below.
|
||||
def _wrap_output(mock_generate_content):
|
||||
def _wrapped(*args, **kwargs):
|
||||
return convert_to_response(mock_generate_content(*args, **kwargs))
|
||||
|
||||
return _wrapped
|
||||
|
||||
|
||||
# Helper used in "_install_mocks" below.
|
||||
def _wrap_output_stream(mock_generate_content_stream):
|
||||
def _wrapped(*args, **kwargs):
|
||||
for output in mock_generate_content_stream(*args, **kwargs):
|
||||
yield convert_to_response(output)
|
||||
|
||||
return _wrapped
|
||||
|
||||
|
||||
# Helper used in "_install_mocks" below.
|
||||
def _async_wrapper(mock_generate_content):
|
||||
async def _wrapped(*args, **kwargs):
|
||||
return mock_generate_content(*args, **kwargs)
|
||||
|
||||
return _wrapped
|
||||
|
||||
|
||||
# Helper used in "_install_mocks" below.
|
||||
def _async_stream_wrapper(mock_generate_content_stream):
|
||||
async def _wrapped(*args, **kwargs):
|
||||
async def _internal_generator():
|
||||
for result in mock_generate_content_stream(*args, **kwargs):
|
||||
yield result
|
||||
|
||||
return _internal_generator()
|
||||
|
||||
return _wrapped
|
||||
|
||||
|
||||
class TestCase(CommonTestCaseBase):
|
||||
# The "setUp" function is defined by "unittest.TestCase" and thus
|
||||
# this name must be used. Uncertain why pylint doesn't seem to
|
||||
# recognize that this is a unit test class for which this is inherited.
|
||||
def setUp(self): # pylint: disable=invalid-name
|
||||
super().setUp()
|
||||
if self.__class__ == TestCase:
|
||||
raise unittest.SkipTest("Skipping testcase base.")
|
||||
self._generate_content_mock = None
|
||||
self._generate_content_stream_mock = None
|
||||
self._original_generate_content = Models.generate_content
|
||||
self._original_generate_content_stream = Models.generate_content_stream
|
||||
self._original_async_generate_content = AsyncModels.generate_content
|
||||
self._original_async_generate_content_stream = (
|
||||
AsyncModels.generate_content_stream
|
||||
)
|
||||
self._responses = []
|
||||
self._response_index = 0
|
||||
|
||||
@property
|
||||
def mock_generate_content(self):
|
||||
if self._generate_content_mock is None:
|
||||
self._create_and_install_mocks()
|
||||
return self._generate_content_mock
|
||||
|
||||
@property
|
||||
def mock_generate_content_stream(self):
|
||||
if self._generate_content_stream_mock is None:
|
||||
self._create_and_install_mocks()
|
||||
return self._generate_content_stream_mock
|
||||
|
||||
def configure_valid_response(self, **kwargs):
|
||||
self._create_and_install_mocks()
|
||||
response = create_response(**kwargs)
|
||||
self._responses.append(response)
|
||||
|
||||
def _create_and_install_mocks(self):
|
||||
if self._generate_content_mock is not None:
|
||||
return
|
||||
self.reset_client()
|
||||
self.reset_instrumentation()
|
||||
self._generate_content_mock = self._create_nonstream_mock()
|
||||
self._generate_content_stream_mock = self._create_stream_mock()
|
||||
self._install_mocks()
|
||||
|
||||
def _create_nonstream_mock(self):
|
||||
mock = unittest.mock.MagicMock()
|
||||
|
||||
def _default_impl(*args, **kwargs):
|
||||
if not self._responses:
|
||||
return create_response(text="Some response")
|
||||
index = self._response_index % len(self._responses)
|
||||
result = self._responses[index]
|
||||
self._response_index += 1
|
||||
return result
|
||||
|
||||
mock.side_effect = _default_impl
|
||||
return mock
|
||||
|
||||
def _create_stream_mock(self):
|
||||
mock = unittest.mock.MagicMock()
|
||||
|
||||
def _default_impl(*args, **kwargs):
|
||||
for response in self._responses:
|
||||
yield response
|
||||
|
||||
mock.side_effect = _default_impl
|
||||
return mock
|
||||
|
||||
def _install_mocks(self):
|
||||
output_wrapped = _wrap_output(self._generate_content_mock)
|
||||
output_wrapped_stream = _wrap_output_stream(
|
||||
self._generate_content_stream_mock
|
||||
)
|
||||
Models.generate_content = output_wrapped
|
||||
Models.generate_content_stream = output_wrapped_stream
|
||||
AsyncModels.generate_content = _async_wrapper(output_wrapped)
|
||||
AsyncModels.generate_content_stream = _async_stream_wrapper(
|
||||
output_wrapped_stream
|
||||
)
|
||||
|
||||
def tearDown(self):
|
||||
super().tearDown()
|
||||
if self._generate_content_mock is None:
|
||||
assert Models.generate_content == self._original_generate_content
|
||||
assert (
|
||||
Models.generate_content_stream
|
||||
== self._original_generate_content_stream
|
||||
)
|
||||
assert (
|
||||
AsyncModels.generate_content
|
||||
== self._original_async_generate_content
|
||||
)
|
||||
assert (
|
||||
AsyncModels.generate_content_stream
|
||||
== self._original_async_generate_content_stream
|
||||
)
|
||||
Models.generate_content = self._original_generate_content
|
||||
Models.generate_content_stream = self._original_generate_content_stream
|
||||
AsyncModels.generate_content = self._original_async_generate_content
|
||||
AsyncModels.generate_content_stream = (
|
||||
self._original_async_generate_content_stream
|
||||
)
|
||||
@ -0,0 +1,94 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: |-
|
||||
{
|
||||
"contents": [
|
||||
{
|
||||
"parts": [
|
||||
{
|
||||
"text": "Create a poem about Open Telemetry."
|
||||
}
|
||||
],
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
}
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '92'
|
||||
Content-Type:
|
||||
- application/json
|
||||
user-agent:
|
||||
- google-genai-sdk/1.0.0 gl-python/3.12.8
|
||||
x-goog-api-client:
|
||||
- <REDACTED>
|
||||
x-goog-user-project:
|
||||
- <REDACTED>
|
||||
method: POST
|
||||
uri: https://test-location-aiplatform.googleapis.com/v1beta1/projects/test-project/locations/test-location/publishers/google/models/gemini-1.5-flash-002:generateContent
|
||||
response:
|
||||
body:
|
||||
string: |-
|
||||
{
|
||||
"candidates": [
|
||||
{
|
||||
"content": {
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "No more dark, inscrutable ways,\nTo trace a request through hazy days.\nOpen Telemetry, a beacon bright,\nIlluminates the path, both day and night.\n\nFrom metrics gathered, a clear display,\nOf latency's dance, and errors' sway.\nTraces unwind, a silken thread,\nShowing the journey, from start to head.\n\nLogs interweave, a richer hue,\nContextual clues, for me and you.\nNo vendor lock-in, a freedom's call,\nTo choose your tools, to stand up tall.\n\nExporters aplenty, a varied choice,\nTo send your data, amplify your voice.\nJaeger, Zipkin, Prometheus' might,\nAll integrate, a glorious sight.\n\nWith spans and attributes, a detailed scene,\nOf how your system works, both sleek and keen.\nPerformance bottlenecks, now laid bare,\nOpen Telemetry, beyond compare.\n\nSo embrace the light, let darkness flee,\nWith Open Telemetry, set your systems free.\nObserve, and learn, and optimize with grace,\nA brighter future, in this digital space.\n"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finishReason": "STOP",
|
||||
"avgLogprobs": -0.3303731600443522
|
||||
}
|
||||
],
|
||||
"usageMetadata": {
|
||||
"promptTokenCount": 8,
|
||||
"candidatesTokenCount": 240,
|
||||
"totalTokenCount": 248,
|
||||
"promptTokensDetails": [
|
||||
{
|
||||
"modality": "TEXT",
|
||||
"tokenCount": 8
|
||||
}
|
||||
],
|
||||
"candidatesTokensDetails": [
|
||||
{
|
||||
"modality": "TEXT",
|
||||
"tokenCount": 240
|
||||
}
|
||||
]
|
||||
},
|
||||
"modelVersion": "gemini-1.5-flash-002",
|
||||
"createTime": "2025-03-07T22:19:18.083091Z",
|
||||
"responseId": "5nDLZ5OJBdyY3NoPiZGx0Ag"
|
||||
}
|
||||
headers:
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json; charset=UTF-8
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Vary:
|
||||
- Origin
|
||||
- X-Origin
|
||||
- Referer
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
X-Frame-Options:
|
||||
- SAMEORIGIN
|
||||
X-XSS-Protection:
|
||||
- '0'
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@ -0,0 +1,94 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: |-
|
||||
{
|
||||
"contents": [
|
||||
{
|
||||
"parts": [
|
||||
{
|
||||
"text": "Create a poem about Open Telemetry."
|
||||
}
|
||||
],
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
}
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '92'
|
||||
Content-Type:
|
||||
- application/json
|
||||
user-agent:
|
||||
- google-genai-sdk/1.0.0 gl-python/3.12.8
|
||||
x-goog-api-client:
|
||||
- <REDACTED>
|
||||
x-goog-user-project:
|
||||
- <REDACTED>
|
||||
method: POST
|
||||
uri: https://test-location-aiplatform.googleapis.com/v1beta1/projects/test-project/locations/test-location/publishers/google/models/gemini-1.5-flash-002:generateContent
|
||||
response:
|
||||
body:
|
||||
string: |-
|
||||
{
|
||||
"candidates": [
|
||||
{
|
||||
"content": {
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "No more dark logs, a cryptic, hidden trace,\nOf failing systems, lost in time and space.\nOpenTelemetry, a beacon shining bright,\nIlluminating paths, both dark and light.\n\nFrom microservices, a sprawling, tangled mesh,\nTo monolithic beasts, put to the test,\nIt gathers traces, spans, and metrics too,\nA holistic view, for me and you.\n\nWith signals clear, from every single node,\nPerformance bottlenecks, instantly bestowed.\nDistributed tracing, paints a vivid scene,\nWhere latency lurks, and slowdowns intervene.\n\nExporters rise, to send the data forth,\nTo dashboards grand, of proven, measured worth.\nPrometheus, Grafana, Jaeger, fluent streams,\nVisualizing insights, fulfilling data dreams.\n\nFrom Jaeger's diagrams, a branching, flowing art,\nTo Grafana's charts, that play a vital part,\nThe mysteries unravel, hidden deep inside,\nWhere errors slumber, and slow responses hide.\n\nSo hail OpenTelemetry, a gift to all who code,\nA brighter future, on a well-lit road.\nNo more guesswork, no more fruitless chase,\nJust clear observability, in time and space.\n"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finishReason": "STOP",
|
||||
"avgLogprobs": -0.45532724261283875
|
||||
}
|
||||
],
|
||||
"usageMetadata": {
|
||||
"promptTokenCount": 8,
|
||||
"candidatesTokenCount": 256,
|
||||
"totalTokenCount": 264,
|
||||
"promptTokensDetails": [
|
||||
{
|
||||
"modality": "TEXT",
|
||||
"tokenCount": 8
|
||||
}
|
||||
],
|
||||
"candidatesTokensDetails": [
|
||||
{
|
||||
"modality": "TEXT",
|
||||
"tokenCount": 256
|
||||
}
|
||||
]
|
||||
},
|
||||
"modelVersion": "gemini-1.5-flash-002",
|
||||
"createTime": "2025-03-07T22:19:15.268428Z",
|
||||
"responseId": "43DLZ4yxEM6F3NoPzaTkiQU"
|
||||
}
|
||||
headers:
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json; charset=UTF-8
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Vary:
|
||||
- Origin
|
||||
- X-Origin
|
||||
- Referer
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
X-Frame-Options:
|
||||
- SAMEORIGIN
|
||||
X-XSS-Protection:
|
||||
- '0'
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@ -0,0 +1,94 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: |-
|
||||
{
|
||||
"contents": [
|
||||
{
|
||||
"parts": [
|
||||
{
|
||||
"text": "Create a poem about Open Telemetry."
|
||||
}
|
||||
],
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
}
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '92'
|
||||
Content-Type:
|
||||
- application/json
|
||||
user-agent:
|
||||
- google-genai-sdk/1.0.0 gl-python/3.12.8
|
||||
x-goog-api-client:
|
||||
- <REDACTED>
|
||||
x-goog-user-project:
|
||||
- <REDACTED>
|
||||
method: POST
|
||||
uri: https://test-location-aiplatform.googleapis.com/v1beta1/projects/test-project/locations/test-location/publishers/google/models/gemini-1.5-flash-002:generateContent
|
||||
response:
|
||||
body:
|
||||
string: |-
|
||||
{
|
||||
"candidates": [
|
||||
{
|
||||
"content": {
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "No more dark, mysterious traces,\nNo more guessing, in empty spaces.\nOpenTelemetry's light now shines,\nIlluminating all our designs.\n\nFrom microservices, small and fleet,\nTo monolithic beasts, hard to beat,\nIt weaves a net, both fine and strong,\nWhere metrics flow, where logs belong.\n\nTraces dance, a vibrant hue,\nShowing journeys, old and new.\nSpans unfold, a story told,\nOf requests handled, brave and bold.\n\nMetrics hum, a steady beat,\nLatency, errors, can't be beat.\nDistribution charts, a clear display,\nGuiding us along the way.\n\nLogs provide a detailed view,\nOf what happened, me and you.\nContext rich, with helpful clues,\nDebugging woes, it quickly subdues.\n\nWith exporters wise, a thoughtful choice,\nTo Prometheus, Jaeger, or Zipkin's voice,\nOur data flows, a precious stream,\nReal-time insights, a waking dream.\n\nSo hail to OpenTelemetry's might,\nBringing clarity to our darkest night.\nObservability's champion, bold and true,\nA brighter future, for me and you.\n"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finishReason": "STOP",
|
||||
"avgLogprobs": -0.4071464086238575
|
||||
}
|
||||
],
|
||||
"usageMetadata": {
|
||||
"promptTokenCount": 8,
|
||||
"candidatesTokenCount": 253,
|
||||
"totalTokenCount": 261,
|
||||
"promptTokensDetails": [
|
||||
{
|
||||
"modality": "TEXT",
|
||||
"tokenCount": 8
|
||||
}
|
||||
],
|
||||
"candidatesTokensDetails": [
|
||||
{
|
||||
"modality": "TEXT",
|
||||
"tokenCount": 253
|
||||
}
|
||||
]
|
||||
},
|
||||
"modelVersion": "gemini-1.5-flash-002",
|
||||
"createTime": "2025-03-07T22:19:12.443989Z",
|
||||
"responseId": "4HDLZ9WMG6SK698Pr5uZ2Qw"
|
||||
}
|
||||
headers:
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json; charset=UTF-8
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Vary:
|
||||
- Origin
|
||||
- X-Origin
|
||||
- Referer
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
X-Frame-Options:
|
||||
- SAMEORIGIN
|
||||
X-XSS-Protection:
|
||||
- '0'
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@ -0,0 +1,94 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: |-
|
||||
{
|
||||
"contents": [
|
||||
{
|
||||
"parts": [
|
||||
{
|
||||
"text": "Create a poem about Open Telemetry."
|
||||
}
|
||||
],
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
}
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '92'
|
||||
Content-Type:
|
||||
- application/json
|
||||
user-agent:
|
||||
- google-genai-sdk/1.0.0 gl-python/3.12.8
|
||||
x-goog-api-client:
|
||||
- <REDACTED>
|
||||
x-goog-user-project:
|
||||
- <REDACTED>
|
||||
method: POST
|
||||
uri: https://test-location-aiplatform.googleapis.com/v1beta1/projects/test-project/locations/test-location/publishers/google/models/gemini-1.5-flash-002:generateContent
|
||||
response:
|
||||
body:
|
||||
string: |-
|
||||
{
|
||||
"candidates": [
|
||||
{
|
||||
"content": {
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "No more dark, mysterious traces,\nOf failing systems, hidden spaces.\nOpen Telemetry's light shines bright,\nGuiding us through the darkest night.\n\nFrom metrics gathered, finely spun,\nTo logs that tell of tasks undone,\nAnd traces linking every call,\nIt answers questions, standing tall.\n\nDistributed systems, complex and vast,\nTheir hidden flaws, no longer cast\nIn shadows deep, beyond our view,\nOpen Telemetry sees them through.\n\nWith spans and attributes, it weaves a tale,\nOf requests flowing, never frail.\nIt pinpoints bottlenecks, slow and grim,\nAnd helps us optimize, system trim.\n\nAcross languages, a common ground,\nWhere data's shared, and insights found.\nExporters whisper, collectors hum,\nA symphony of data, overcome.\n\nSo raise a glass, to this open source,\nA shining beacon, a powerful force.\nOpen Telemetry, a guiding star,\nRevealing secrets, near and far.\n"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finishReason": "STOP",
|
||||
"avgLogprobs": -0.3586180628193498
|
||||
}
|
||||
],
|
||||
"usageMetadata": {
|
||||
"promptTokenCount": 8,
|
||||
"candidatesTokenCount": 211,
|
||||
"totalTokenCount": 219,
|
||||
"promptTokensDetails": [
|
||||
{
|
||||
"modality": "TEXT",
|
||||
"tokenCount": 8
|
||||
}
|
||||
],
|
||||
"candidatesTokensDetails": [
|
||||
{
|
||||
"modality": "TEXT",
|
||||
"tokenCount": 211
|
||||
}
|
||||
]
|
||||
},
|
||||
"modelVersion": "gemini-1.5-flash-002",
|
||||
"createTime": "2025-03-07T22:19:09.936326Z",
|
||||
"responseId": "3XDLZ4aTOZSpnvgPn-e0qQk"
|
||||
}
|
||||
headers:
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json; charset=UTF-8
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Vary:
|
||||
- Origin
|
||||
- X-Origin
|
||||
- Referer
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
X-Frame-Options:
|
||||
- SAMEORIGIN
|
||||
X-XSS-Protection:
|
||||
- '0'
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@ -0,0 +1,97 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: |-
|
||||
{
|
||||
"contents": [
|
||||
{
|
||||
"parts": [
|
||||
{
|
||||
"text": "Create a poem about Open Telemetry."
|
||||
}
|
||||
],
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
}
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '92'
|
||||
Content-Type:
|
||||
- application/json
|
||||
user-agent:
|
||||
- google-genai-sdk/1.0.0 gl-python/3.12.8
|
||||
x-goog-api-client:
|
||||
- <REDACTED>
|
||||
x-goog-user-project:
|
||||
- <REDACTED>
|
||||
method: POST
|
||||
uri: https://test-location-aiplatform.googleapis.com/v1beta1/projects/test-project/locations/test-location/publishers/google/models/gemini-1.5-flash-002:streamGenerateContent?alt=sse
|
||||
response:
|
||||
body:
|
||||
string: "data: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"No\"}]}}],\"usageMetadata\": {},\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:29.293930Z\",\"responseId\": \"8XDLZ6r4Efa1-O4PwIHamQ4\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" longer dark, the tracing's light,\\nOpen Telemetry, shining\
|
||||
\ bright\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\"\
|
||||
: \"2025-03-07T22:19:29.293930Z\",\"responseId\": \"8XDLZ6r4Efa1-O4PwIHamQ4\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \".\\nA beacon in the coding night,\\nRevealing paths, both\
|
||||
\ dark\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"\
|
||||
2025-03-07T22:19:29.293930Z\",\"responseId\": \"8XDLZ6r4Efa1-O4PwIHamQ4\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" and bright.\\n\\nFrom microservice to sprawling beast,\\\
|
||||
nIts watchful eye, a silent priest.\\nObserving calls, both small and vast,\\\
|
||||
nPerformance\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\"\
|
||||
: \"2025-03-07T22:19:29.293930Z\",\"responseId\": \"8XDLZ6r4Efa1-O4PwIHamQ4\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" flaws, revealed at last.\\n\\nWith metrics gleaned and logs\
|
||||
\ aligned,\\nA clearer picture, you will find.\\nOf latency, and errors dire,\\\
|
||||
n\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:29.293930Z\"\
|
||||
,\"responseId\": \"8XDLZ6r4Efa1-O4PwIHamQ4\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \"And bottlenecks\
|
||||
\ that set afire.\\n\\nIt spans the clouds, a network wide,\\nWhere data streams,\
|
||||
\ a surging tide.\\nCollecting traces, rich and deep,\\nWhile slumbering apps\
|
||||
\ their secrets keep.\\n\\nJaeger, Zip\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:29.293930Z\",\"responseId\": \"8XDLZ6r4Efa1-O4PwIHamQ4\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"kin, the tools it holds,\\nA tapestry of stories told.\\nOf\
|
||||
\ requests flowing, swift and free,\\nOr tangled knots, for all to see.\\\
|
||||
n\\nSo embrace the power, understand,\\nThe vital role, across the\"}]}}],\"\
|
||||
modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:29.293930Z\"\
|
||||
,\"responseId\": \"8XDLZ6r4Efa1-O4PwIHamQ4\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \" land.\\nOpen\
|
||||
\ Telemetry, a guiding star,\\nTo navigate the digital afar.\\n\"}]},\"finishReason\"\
|
||||
: \"STOP\"}],\"usageMetadata\": {\"promptTokenCount\": 8,\"candidatesTokenCount\"\
|
||||
: 212,\"totalTokenCount\": 220,\"promptTokensDetails\": [{\"modality\": \"\
|
||||
TEXT\",\"tokenCount\": 8}],\"candidatesTokensDetails\": [{\"modality\": \"\
|
||||
TEXT\",\"tokenCount\": 212}]},\"modelVersion\": \"gemini-1.5-flash-002\",\"\
|
||||
createTime\": \"2025-03-07T22:19:29.293930Z\",\"responseId\": \"8XDLZ6r4Efa1-O4PwIHamQ4\"\
|
||||
}\r\n\r\n"
|
||||
headers:
|
||||
Content-Disposition:
|
||||
- attachment
|
||||
Content-Type:
|
||||
- text/event-stream
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Vary:
|
||||
- Origin
|
||||
- X-Origin
|
||||
- Referer
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
X-Frame-Options:
|
||||
- SAMEORIGIN
|
||||
X-XSS-Protection:
|
||||
- '0'
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@ -0,0 +1,102 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: |-
|
||||
{
|
||||
"contents": [
|
||||
{
|
||||
"parts": [
|
||||
{
|
||||
"text": "Create a poem about Open Telemetry."
|
||||
}
|
||||
],
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
}
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '92'
|
||||
Content-Type:
|
||||
- application/json
|
||||
user-agent:
|
||||
- google-genai-sdk/1.0.0 gl-python/3.12.8
|
||||
x-goog-api-client:
|
||||
- <REDACTED>
|
||||
x-goog-user-project:
|
||||
- <REDACTED>
|
||||
method: POST
|
||||
uri: https://test-location-aiplatform.googleapis.com/v1beta1/projects/test-project/locations/test-location/publishers/google/models/gemini-1.5-flash-002:streamGenerateContent?alt=sse
|
||||
response:
|
||||
body:
|
||||
string: "data: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"The\"}]}}],\"usageMetadata\": {},\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:26.378633Z\",\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" black box whispers, secrets deep,\\nOf failing systems, promises\
|
||||
\ to keep.\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\"\
|
||||
: \"2025-03-07T22:19:26.378633Z\",\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"\\nBut tracing's light, a guiding hand,\\nReveals the path\"\
|
||||
}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:26.378633Z\"\
|
||||
,\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \", across the\
|
||||
\ land.\\n\\nOpen Telemetry, a beacon bright,\\nIlluminating pathways, day\
|
||||
\ and night.\\nFrom spans and traces, stories told,\"}]}}],\"modelVersion\"\
|
||||
: \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:26.378633Z\"\
|
||||
,\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \"\\nOf requests\
|
||||
\ flowing, brave and bold.\\n\\nThe metrics rise, a vibrant chart,\\nDisplaying\
|
||||
\ latency, a work of art.\\nEach request'\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:26.378633Z\",\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"s journey, clearly shown,\\nWhere bottlenecks slumber, seeds\
|
||||
\ are sown.\\n\\nWith logs appended, context clear,\\nThe root of problems,\
|
||||
\ drawing near.\\nObservability's embrace, so wide,\\nUnraveling mysteries,\"\
|
||||
}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:26.378633Z\"\
|
||||
,\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \" deep inside.\\\
|
||||
n\\nFrom simple apps to complex weaves,\\nOpen Telemetry's power achieves,\\\
|
||||
nA unified vision, strong and true,\\nMonitoring systems, old and new.\\n\\\
|
||||
nNo vendor lock-in, free to roam,\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:26.378633Z\",\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"\\nAcross the clouds, and find your home.\\nA standard rising,\
|
||||
\ strong and bold,\\nA future brighter, to behold.\\n\\nSo let the traces\
|
||||
\ flow and gleam,\\nOpen Telemetry, a vibrant dream.\\nOf healthy systems,\
|
||||
\ running free,\\nFor all to see, for all to be.\"}]}}],\"modelVersion\":\
|
||||
\ \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:26.378633Z\"\
|
||||
,\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \"\\n\"}]},\"\
|
||||
finishReason\": \"STOP\"}],\"usageMetadata\": {\"promptTokenCount\": 8,\"\
|
||||
candidatesTokenCount\": 258,\"totalTokenCount\": 266,\"promptTokensDetails\"\
|
||||
: [{\"modality\": \"TEXT\",\"tokenCount\": 8}],\"candidatesTokensDetails\"\
|
||||
: [{\"modality\": \"TEXT\",\"tokenCount\": 258}]},\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:26.378633Z\",\"responseId\": \"7nDLZ4mOF_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\n"
|
||||
headers:
|
||||
Content-Disposition:
|
||||
- attachment
|
||||
Content-Type:
|
||||
- text/event-stream
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Vary:
|
||||
- Origin
|
||||
- X-Origin
|
||||
- Referer
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
X-Frame-Options:
|
||||
- SAMEORIGIN
|
||||
X-XSS-Protection:
|
||||
- '0'
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@ -0,0 +1,99 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: |-
|
||||
{
|
||||
"contents": [
|
||||
{
|
||||
"parts": [
|
||||
{
|
||||
"text": "Create a poem about Open Telemetry."
|
||||
}
|
||||
],
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
}
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '92'
|
||||
Content-Type:
|
||||
- application/json
|
||||
user-agent:
|
||||
- google-genai-sdk/1.0.0 gl-python/3.12.8
|
||||
x-goog-api-client:
|
||||
- <REDACTED>
|
||||
x-goog-user-project:
|
||||
- <REDACTED>
|
||||
method: POST
|
||||
uri: https://test-location-aiplatform.googleapis.com/v1beta1/projects/test-project/locations/test-location/publishers/google/models/gemini-1.5-flash-002:streamGenerateContent?alt=sse
|
||||
response:
|
||||
body:
|
||||
string: "data: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"No\"}]}}],\"usageMetadata\": {},\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:23.579184Z\",\"responseId\": \"63DLZ_CsI_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" more dark logs, a cryptic, silent scream,\\nNo more the hunt\
|
||||
\ for\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"\
|
||||
2025-03-07T22:19:23.579184Z\",\"responseId\": \"63DLZ_CsI_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" errors, a lost, fading dream.\\nOpen Telemetry, a beacon\
|
||||
\ in\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"\
|
||||
2025-03-07T22:19:23.579184Z\",\"responseId\": \"63DLZ_CsI_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" the night,\\nShining forth its data, clear and burning bright.\\\
|
||||
n\\nFrom traces spanning systems, a flowing, silver thread,\\nMetrics pulse\
|
||||
\ and measure,\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\"\
|
||||
: \"2025-03-07T22:19:23.579184Z\",\"responseId\": \"63DLZ_CsI_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" insights finely spread.\\nLogs enriched with context, a story\
|
||||
\ they unfold,\\nOf requests and responses, both brave and bold.\\n\\nObservability's\
|
||||
\ promise\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\"\
|
||||
: \"2025-03-07T22:19:23.579184Z\",\"responseId\": \"63DLZ_CsI_Hg-O4P7YfKqQ8\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \", a future now at hand,\\nWith vendors interoperable, a collaborative\
|
||||
\ band.\\nNo longer vendor lock-in, a restrictive, iron cage,\\nBut freedom\
|
||||
\ of selection, turning a new page.\\n\\nFrom microservices humming,\"}]}}],\"\
|
||||
modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:23.579184Z\"\
|
||||
,\"responseId\": \"63DLZ_CsI_Hg-O4P7YfKqQ8\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \" a symphony\
|
||||
\ of calls,\\nTo monolithic giants, answering their thralls,\\nOpen Telemetry\
|
||||
\ watches, with keen and watchful eye,\\nDetecting the anomalies, before they\
|
||||
\ rise and fly.\\n\\nSo let the data flow freely, a\"}]}}],\"modelVersion\"\
|
||||
: \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:23.579184Z\"\
|
||||
,\"responseId\": \"63DLZ_CsI_Hg-O4P7YfKqQ8\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \" river strong\
|
||||
\ and deep,\\nIts secrets it will whisper, while the systems sleep.\\nOpen\
|
||||
\ Telemetry's power, a force that we can wield,\\nTo build more stable systems,\
|
||||
\ in the digital field.\\n\"}]},\"finishReason\": \"STOP\"}],\"usageMetadata\"\
|
||||
: {\"promptTokenCount\": 8,\"candidatesTokenCount\": 238,\"totalTokenCount\"\
|
||||
: 246,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 8}],\"\
|
||||
candidatesTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 238}]},\"\
|
||||
modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:23.579184Z\"\
|
||||
,\"responseId\": \"63DLZ_CsI_Hg-O4P7YfKqQ8\"}\r\n\r\n"
|
||||
headers:
|
||||
Content-Disposition:
|
||||
- attachment
|
||||
Content-Type:
|
||||
- text/event-stream
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Vary:
|
||||
- Origin
|
||||
- X-Origin
|
||||
- Referer
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
X-Frame-Options:
|
||||
- SAMEORIGIN
|
||||
X-XSS-Protection:
|
||||
- '0'
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@ -0,0 +1,99 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: |-
|
||||
{
|
||||
"contents": [
|
||||
{
|
||||
"parts": [
|
||||
{
|
||||
"text": "Create a poem about Open Telemetry."
|
||||
}
|
||||
],
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
}
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '92'
|
||||
Content-Type:
|
||||
- application/json
|
||||
user-agent:
|
||||
- google-genai-sdk/1.0.0 gl-python/3.12.8
|
||||
x-goog-api-client:
|
||||
- <REDACTED>
|
||||
x-goog-user-project:
|
||||
- <REDACTED>
|
||||
method: POST
|
||||
uri: https://test-location-aiplatform.googleapis.com/v1beta1/projects/test-project/locations/test-location/publishers/google/models/gemini-1.5-flash-002:streamGenerateContent?alt=sse
|
||||
response:
|
||||
body:
|
||||
string: "data: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"No\"}]}}],\"usageMetadata\": {},\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:20.770456Z\",\"responseId\": \"6HDLZ5iDL86F3NoPzaTkiQU\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \" more dark, mysterious traces,\\nNo more guessing, in time\
|
||||
\ and spaces.\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\"\
|
||||
: \"2025-03-07T22:19:20.770456Z\",\"responseId\": \"6HDLZ5iDL86F3NoPzaTkiQU\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"\\nOpen Telemetry's light shines bright,\\nIlluminating the\
|
||||
\ code'\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\":\
|
||||
\ \"2025-03-07T22:19:20.770456Z\",\"responseId\": \"6HDLZ5iDL86F3NoPzaTkiQU\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"s dark night.\\n\\nFrom spans and metrics, a story told,\\\
|
||||
nOf requests flowing, both brave and bold.\\nTraces weaving, a tapestry grand,\"\
|
||||
}]}}],\"modelVersion\": \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:20.770456Z\"\
|
||||
,\"responseId\": \"6HDLZ5iDL86F3NoPzaTkiQU\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \"\\nShowing\
|
||||
\ performance, across the land.\\n\\nLogs and metrics, a perfect blend,\\\
|
||||
nInformation's flow, without end.\\nObservability's promise\"}]}}],\"modelVersion\"\
|
||||
: \"gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:20.770456Z\"\
|
||||
,\"responseId\": \"6HDLZ5iDL86F3NoPzaTkiQU\"}\r\n\r\ndata: {\"candidates\"\
|
||||
: [{\"content\": {\"role\": \"model\",\"parts\": [{\"text\": \", clear and\
|
||||
\ true,\\nInsights revealed, for me and you.\\n\\nJaeger, Zipkin, a chorus\
|
||||
\ sings,\\nWith exporters ready, for all the things.\\nFrom simple apps to\
|
||||
\ systems vast,\\nOpen Telemetry'\"}]}}],\"modelVersion\": \"gemini-1.5-flash-002\"\
|
||||
,\"createTime\": \"2025-03-07T22:19:20.770456Z\",\"responseId\": \"6HDLZ5iDL86F3NoPzaTkiQU\"\
|
||||
}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"role\": \"model\",\"parts\"\
|
||||
: [{\"text\": \"s power will last.\\n\\nNo vendor lock-in, a freedom sweet,\\\
|
||||
nOpen source glory, can't be beat.\\nSo let us embrace, this modern way,\\\
|
||||
nTo monitor systems, come what may.\\n\\nFrom\"}]}}],\"modelVersion\": \"\
|
||||
gemini-1.5-flash-002\",\"createTime\": \"2025-03-07T22:19:20.770456Z\",\"\
|
||||
responseId\": \"6HDLZ5iDL86F3NoPzaTkiQU\"}\r\n\r\ndata: {\"candidates\": [{\"\
|
||||
content\": {\"role\": \"model\",\"parts\": [{\"text\": \" microservices, small\
|
||||
\ and slight,\\nTo monolithic giants, shining bright,\\nOpen Telemetry shows\
|
||||
\ the path,\\nTo understand, and fix the wrath,\\nOf latency demons, lurking\
|
||||
\ near,\\nBringing clarity, year after year.\\n\"}]},\"finishReason\": \"\
|
||||
STOP\"}],\"usageMetadata\": {\"promptTokenCount\": 8,\"candidatesTokenCount\"\
|
||||
: 242,\"totalTokenCount\": 250,\"promptTokensDetails\": [{\"modality\": \"\
|
||||
TEXT\",\"tokenCount\": 8}],\"candidatesTokensDetails\": [{\"modality\": \"\
|
||||
TEXT\",\"tokenCount\": 242}]},\"modelVersion\": \"gemini-1.5-flash-002\",\"\
|
||||
createTime\": \"2025-03-07T22:19:20.770456Z\",\"responseId\": \"6HDLZ5iDL86F3NoPzaTkiQU\"\
|
||||
}\r\n\r\n"
|
||||
headers:
|
||||
Content-Disposition:
|
||||
- attachment
|
||||
Content-Type:
|
||||
- text/event-stream
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Vary:
|
||||
- Origin
|
||||
- X-Origin
|
||||
- Referer
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
X-Frame-Options:
|
||||
- SAMEORIGIN
|
||||
X-XSS-Protection:
|
||||
- '0'
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@ -16,8 +16,7 @@ import json
|
||||
import os
|
||||
import unittest
|
||||
|
||||
from ..common.base import TestCase
|
||||
from .util import create_valid_response
|
||||
from .base import TestCase
|
||||
|
||||
|
||||
class NonStreamingTestCase(TestCase):
|
||||
@ -36,18 +35,15 @@ class NonStreamingTestCase(TestCase):
|
||||
def expected_function_name(self):
|
||||
raise NotImplementedError("Must implement 'expected_function_name'.")
|
||||
|
||||
def configure_valid_response(self, *args, **kwargs):
|
||||
self.requests.add_response(create_valid_response(*args, **kwargs))
|
||||
|
||||
def test_instrumentation_does_not_break_core_functionality(self):
|
||||
self.configure_valid_response(response_text="Yep, it works!")
|
||||
self.configure_valid_response(text="Yep, it works!")
|
||||
response = self.generate_content(
|
||||
model="gemini-2.0-flash", contents="Does this work?"
|
||||
)
|
||||
self.assertEqual(response.text, "Yep, it works!")
|
||||
|
||||
def test_generates_span(self):
|
||||
self.configure_valid_response(response_text="Yep, it works!")
|
||||
self.configure_valid_response(text="Yep, it works!")
|
||||
response = self.generate_content(
|
||||
model="gemini-2.0-flash", contents="Does this work?"
|
||||
)
|
||||
@ -55,7 +51,7 @@ class NonStreamingTestCase(TestCase):
|
||||
self.otel.assert_has_span_named("generate_content gemini-2.0-flash")
|
||||
|
||||
def test_model_reflected_into_span_name(self):
|
||||
self.configure_valid_response(response_text="Yep, it works!")
|
||||
self.configure_valid_response(text="Yep, it works!")
|
||||
response = self.generate_content(
|
||||
model="gemini-1.5-flash", contents="Does this work?"
|
||||
)
|
||||
@ -63,7 +59,7 @@ class NonStreamingTestCase(TestCase):
|
||||
self.otel.assert_has_span_named("generate_content gemini-1.5-flash")
|
||||
|
||||
def test_generated_span_has_minimal_genai_attributes(self):
|
||||
self.configure_valid_response(response_text="Yep, it works!")
|
||||
self.configure_valid_response(text="Yep, it works!")
|
||||
self.generate_content(
|
||||
model="gemini-2.0-flash", contents="Does this work?"
|
||||
)
|
||||
@ -75,7 +71,7 @@ class NonStreamingTestCase(TestCase):
|
||||
)
|
||||
|
||||
def test_generated_span_has_correct_function_name(self):
|
||||
self.configure_valid_response(response_text="Yep, it works!")
|
||||
self.configure_valid_response(text="Yep, it works!")
|
||||
self.generate_content(
|
||||
model="gemini-2.0-flash", contents="Does this work?"
|
||||
)
|
||||
@ -87,7 +83,7 @@ class NonStreamingTestCase(TestCase):
|
||||
|
||||
def test_generated_span_has_vertex_ai_system_when_configured(self):
|
||||
self.set_use_vertex(True)
|
||||
self.configure_valid_response(response_text="Yep, it works!")
|
||||
self.configure_valid_response(text="Yep, it works!")
|
||||
self.generate_content(
|
||||
model="gemini-2.0-flash", contents="Does this work?"
|
||||
)
|
||||
@ -170,7 +166,7 @@ class NonStreamingTestCase(TestCase):
|
||||
os.environ["OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT"] = (
|
||||
"true"
|
||||
)
|
||||
self.configure_valid_response(response_text="Some response content")
|
||||
self.configure_valid_response(text="Some response content")
|
||||
self.generate_content(model="gemini-2.0-flash", contents="Some input")
|
||||
self.otel.assert_has_event_named("gen_ai.choice")
|
||||
event_record = self.otel.get_event_named("gen_ai.choice")
|
||||
@ -183,7 +179,7 @@ class NonStreamingTestCase(TestCase):
|
||||
os.environ["OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT"] = (
|
||||
"false"
|
||||
)
|
||||
self.configure_valid_response(response_text="Some response content")
|
||||
self.configure_valid_response(text="Some response content")
|
||||
self.generate_content(model="gemini-2.0-flash", contents="Some input")
|
||||
self.otel.assert_has_event_named("gen_ai.choice")
|
||||
event_record = self.otel.get_event_named("gen_ai.choice")
|
||||
|
||||
@ -14,8 +14,7 @@
|
||||
|
||||
import unittest
|
||||
|
||||
from ..common.base import TestCase
|
||||
from .util import create_valid_response
|
||||
from .base import TestCase
|
||||
|
||||
|
||||
class StreamingTestCase(TestCase):
|
||||
@ -34,11 +33,8 @@ class StreamingTestCase(TestCase):
|
||||
def expected_function_name(self):
|
||||
raise NotImplementedError("Must implement 'expected_function_name'.")
|
||||
|
||||
def configure_valid_response(self, *args, **kwargs):
|
||||
self.requests.add_response(create_valid_response(*args, **kwargs))
|
||||
|
||||
def test_instrumentation_does_not_break_core_functionality(self):
|
||||
self.configure_valid_response(response_text="Yep, it works!")
|
||||
self.configure_valid_response(text="Yep, it works!")
|
||||
responses = self.generate_content(
|
||||
model="gemini-2.0-flash", contents="Does this work?"
|
||||
)
|
||||
@ -47,8 +43,8 @@ class StreamingTestCase(TestCase):
|
||||
self.assertEqual(response.text, "Yep, it works!")
|
||||
|
||||
def test_handles_multiple_ressponses(self):
|
||||
self.configure_valid_response(response_text="First response")
|
||||
self.configure_valid_response(response_text="Second response")
|
||||
self.configure_valid_response(text="First response")
|
||||
self.configure_valid_response(text="Second response")
|
||||
responses = self.generate_content(
|
||||
model="gemini-2.0-flash", contents="Does this work?"
|
||||
)
|
||||
|
||||
@ -0,0 +1,504 @@
|
||||
# Copyright The OpenTelemetry Authors
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
"""High level end-to-end test of the generate content instrumentation.
|
||||
|
||||
The primary purpose of this test is to verify that the instrumentation
|
||||
package does not break the underlying GenAI SDK that it instruments.
|
||||
|
||||
This test suite also has some minimal validation of the instrumentation
|
||||
outputs; however, validating the instrumentation output (other than
|
||||
verifying that instrumentation does not break the GenAI SDK) is a
|
||||
secondary goal of this test. Detailed testing of the instrumentation
|
||||
output is the purview of the other tests in this directory."""
|
||||
|
||||
import asyncio
|
||||
import gzip
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
import google.auth
|
||||
import google.auth.credentials
|
||||
import google.genai
|
||||
import pytest
|
||||
import yaml
|
||||
from vcr.record_mode import RecordMode
|
||||
|
||||
from opentelemetry.instrumentation.google_genai import (
|
||||
GoogleGenAiSdkInstrumentor,
|
||||
)
|
||||
|
||||
from ..common.auth import FakeCredentials
|
||||
from ..common.otel_mocker import OTelMocker
|
||||
|
||||
_FAKE_PROJECT = "test-project"
|
||||
_FAKE_LOCATION = "test-location"
|
||||
_FAKE_API_KEY = "test-api-key"
|
||||
_DEFAULT_REAL_LOCATION = "us-central1"
|
||||
|
||||
|
||||
def _get_project_from_env():
|
||||
return (
|
||||
os.getenv("GCLOUD_PROJECT") or os.getenv("GOOGLE_CLOUD_PROJECT") or ""
|
||||
)
|
||||
|
||||
|
||||
def _get_project_from_gcloud_cli():
|
||||
try:
|
||||
gcloud_call_result = subprocess.run(
|
||||
"gcloud config get project",
|
||||
shell=True,
|
||||
capture_output=True,
|
||||
check=True,
|
||||
)
|
||||
except subprocess.CalledProcessError:
|
||||
return None
|
||||
gcloud_output = gcloud_call_result.stdout.decode()
|
||||
return gcloud_output.strip()
|
||||
|
||||
|
||||
def _get_project_from_credentials():
|
||||
_, from_creds = google.auth.default()
|
||||
return from_creds
|
||||
|
||||
|
||||
def _get_real_project():
|
||||
from_env = _get_project_from_env()
|
||||
if from_env:
|
||||
return from_env
|
||||
from_cli = _get_project_from_gcloud_cli()
|
||||
if from_cli:
|
||||
return from_cli
|
||||
return _get_project_from_credentials()
|
||||
|
||||
|
||||
def _get_location_from_env():
|
||||
return (
|
||||
os.getenv("GCLOUD_LOCATION")
|
||||
or os.getenv("GOOGLE_CLOUD_LOCATION")
|
||||
or ""
|
||||
)
|
||||
|
||||
|
||||
def _get_real_location():
|
||||
return _get_location_from_env() or _DEFAULT_REAL_LOCATION
|
||||
|
||||
|
||||
def _get_vertex_api_key_from_env():
|
||||
return os.getenv("GOOGLE_API_KEY")
|
||||
|
||||
|
||||
def _get_gemini_api_key_from_env():
|
||||
return os.getenv("GEMINI_API_KEY")
|
||||
|
||||
|
||||
def _should_redact_header(header_key):
|
||||
if header_key.startswith("x-goog"):
|
||||
return True
|
||||
if header_key.startswith("sec-goog"):
|
||||
return True
|
||||
if header_key in ["server", "server-timing"]:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _redact_headers(headers):
|
||||
for header_key in headers:
|
||||
if _should_redact_header(header_key.lower()):
|
||||
headers[header_key] = "<REDACTED>"
|
||||
|
||||
|
||||
def _before_record_request(request):
|
||||
if request.headers:
|
||||
_redact_headers(request.headers)
|
||||
uri = request.uri
|
||||
project = _get_project_from_env()
|
||||
if project:
|
||||
uri = uri.replace(f"projects/{project}", f"projects/{_FAKE_PROJECT}")
|
||||
location = _get_real_location()
|
||||
if location:
|
||||
uri = uri.replace(
|
||||
f"locations/{location}", f"locations/{_FAKE_LOCATION}"
|
||||
)
|
||||
uri = uri.replace(
|
||||
f"//{location}-aiplatform.googleapis.com",
|
||||
f"//{_FAKE_LOCATION}-aiplatform.googleapis.com",
|
||||
)
|
||||
request.uri = uri
|
||||
return request
|
||||
|
||||
|
||||
def _before_record_response(response):
|
||||
if hasattr(response, "headers") and response.headers:
|
||||
_redact_headers(response.headers)
|
||||
return response
|
||||
|
||||
|
||||
@pytest.fixture(name="vcr_config", scope="module")
|
||||
def fixture_vcr_config():
|
||||
return {
|
||||
"filter_query_parameters": [
|
||||
"key",
|
||||
"apiKey",
|
||||
"quotaUser",
|
||||
"userProject",
|
||||
"token",
|
||||
"access_token",
|
||||
"accessToken",
|
||||
"refesh_token",
|
||||
"refreshToken",
|
||||
"authuser",
|
||||
"bearer",
|
||||
"bearer_token",
|
||||
"bearerToken",
|
||||
"userIp",
|
||||
],
|
||||
"filter_post_data_parameters": ["apikey", "api_key", "key"],
|
||||
"filter_headers": [
|
||||
"x-goog-api-key",
|
||||
"authorization",
|
||||
"server",
|
||||
"Server",
|
||||
"Server-Timing",
|
||||
"Date",
|
||||
],
|
||||
"before_record_request": _before_record_request,
|
||||
"before_record_response": _before_record_response,
|
||||
"ignore_hosts": [
|
||||
"oauth2.googleapis.com",
|
||||
"iam.googleapis.com",
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
class _LiteralBlockScalar(str):
|
||||
"""Formats the string as a literal block scalar, preserving whitespace and
|
||||
without interpreting escape characters"""
|
||||
|
||||
|
||||
def _literal_block_scalar_presenter(dumper, data):
|
||||
"""Represents a scalar string as a literal block, via '|' syntax"""
|
||||
return dumper.represent_scalar("tag:yaml.org,2002:str", data, style="|")
|
||||
|
||||
|
||||
@pytest.fixture(
|
||||
name="internal_setup_yaml_pretty_formatting", scope="module", autouse=True
|
||||
)
|
||||
def fixture_setup_yaml_pretty_formatting():
|
||||
yaml.add_representer(_LiteralBlockScalar, _literal_block_scalar_presenter)
|
||||
|
||||
|
||||
def _process_string_value(string_value):
|
||||
"""Pretty-prints JSON or returns long strings as a LiteralBlockScalar"""
|
||||
try:
|
||||
json_data = json.loads(string_value)
|
||||
return _LiteralBlockScalar(json.dumps(json_data, indent=2))
|
||||
except (ValueError, TypeError):
|
||||
if len(string_value) > 80:
|
||||
return _LiteralBlockScalar(string_value)
|
||||
return string_value
|
||||
|
||||
|
||||
def _convert_body_to_literal(data):
|
||||
"""Searches the data for body strings, attempting to pretty-print JSON"""
|
||||
if isinstance(data, dict):
|
||||
for key, value in data.items():
|
||||
# Handle response body case (e.g., response.body.string)
|
||||
if key == "body" and isinstance(value, dict) and "string" in value:
|
||||
value["string"] = _process_string_value(value["string"])
|
||||
|
||||
# Handle request body case (e.g., request.body)
|
||||
elif key == "body" and isinstance(value, str):
|
||||
data[key] = _process_string_value(value)
|
||||
|
||||
else:
|
||||
_convert_body_to_literal(value)
|
||||
|
||||
elif isinstance(data, list):
|
||||
for idx, choice in enumerate(data):
|
||||
data[idx] = _convert_body_to_literal(choice)
|
||||
|
||||
return data
|
||||
|
||||
|
||||
# Helper for enforcing GZIP compression where it was originally.
|
||||
def _ensure_gzip_single_response(data: bytes):
|
||||
try:
|
||||
# Attempt to decompress, first, to avoid double compression.
|
||||
gzip.decompress(data)
|
||||
return data
|
||||
except gzip.BadGzipFile:
|
||||
# It must not have been compressed in the first place.
|
||||
return gzip.compress(data)
|
||||
|
||||
|
||||
# VCRPy automatically decompresses responses before saving them, but it may forget to
|
||||
# re-encode them when the data is loaded. This can create issues with decompression.
|
||||
# This is why we re-encode on load; to accurately replay what was originally sent.
|
||||
#
|
||||
# https://vcrpy.readthedocs.io/en/latest/advanced.html#decode-compressed-response
|
||||
def _ensure_casette_gzip(loaded_casette):
|
||||
for interaction in loaded_casette["interactions"]:
|
||||
response = interaction["response"]
|
||||
headers = response["headers"]
|
||||
if (
|
||||
"content-encoding" not in headers
|
||||
and "Content-Encoding" not in headers
|
||||
):
|
||||
continue
|
||||
if (
|
||||
"content-encoding" in headers
|
||||
and "gzip" not in headers["content-encoding"]
|
||||
):
|
||||
continue
|
||||
if (
|
||||
"Content-Encoding" in headers
|
||||
and "gzip" not in headers["Content-Encoding"]
|
||||
):
|
||||
continue
|
||||
response["body"]["string"] = _ensure_gzip_single_response(
|
||||
response["body"]["string"].encode()
|
||||
)
|
||||
|
||||
|
||||
def _maybe_ensure_casette_gzip(result):
|
||||
if sys.version_info[0] == 3 and sys.version_info[1] == 9:
|
||||
_ensure_casette_gzip(result)
|
||||
|
||||
|
||||
class _PrettyPrintJSONBody:
|
||||
"""This makes request and response body recordings more readable."""
|
||||
|
||||
@staticmethod
|
||||
def serialize(cassette_dict):
|
||||
cassette_dict = _convert_body_to_literal(cassette_dict)
|
||||
return yaml.dump(
|
||||
cassette_dict, default_flow_style=False, allow_unicode=True
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def deserialize(cassette_string):
|
||||
result = yaml.load(cassette_string, Loader=yaml.Loader)
|
||||
_maybe_ensure_casette_gzip(result)
|
||||
return result
|
||||
|
||||
|
||||
@pytest.fixture(name="fully_initialized_vcr", scope="module", autouse=True)
|
||||
def setup_vcr(vcr):
|
||||
vcr.register_serializer("yaml", _PrettyPrintJSONBody)
|
||||
vcr.serializer = "yaml"
|
||||
return vcr
|
||||
|
||||
|
||||
@pytest.fixture(name="instrumentor")
|
||||
def fixture_instrumentor():
|
||||
return GoogleGenAiSdkInstrumentor()
|
||||
|
||||
|
||||
@pytest.fixture(name="internal_instrumentation_setup", autouse=True)
|
||||
def fixture_setup_instrumentation(instrumentor):
|
||||
instrumentor.instrument()
|
||||
yield
|
||||
instrumentor.uninstrument()
|
||||
|
||||
|
||||
@pytest.fixture(name="otel_mocker", autouse=True)
|
||||
def fixture_otel_mocker():
|
||||
result = OTelMocker()
|
||||
result.install()
|
||||
yield result
|
||||
result.uninstall()
|
||||
|
||||
|
||||
@pytest.fixture(
|
||||
name="setup_content_recording",
|
||||
autouse=True,
|
||||
params=["logcontent", "excludecontent"],
|
||||
)
|
||||
def fixture_setup_content_recording(request):
|
||||
enabled = request.param == "logcontent"
|
||||
os.environ["OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT"] = str(
|
||||
enabled
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture(name="vcr_record_mode")
|
||||
def fixture_vcr_record_mode(vcr):
|
||||
return vcr.record_mode
|
||||
|
||||
|
||||
@pytest.fixture(name="in_replay_mode")
|
||||
def fixture_in_replay_mode(vcr_record_mode):
|
||||
return vcr_record_mode == RecordMode.NONE
|
||||
|
||||
|
||||
@pytest.fixture(name="gcloud_project", autouse=True)
|
||||
def fixture_gcloud_project(in_replay_mode):
|
||||
if in_replay_mode:
|
||||
return _FAKE_PROJECT
|
||||
result = _get_real_project()
|
||||
for env_var in ["GCLOUD_PROJECT", "GOOGLE_CLOUD_PROJECT"]:
|
||||
os.environ[env_var] = result
|
||||
return result
|
||||
|
||||
|
||||
@pytest.fixture(name="gcloud_location")
|
||||
def fixture_gcloud_location(in_replay_mode):
|
||||
if in_replay_mode:
|
||||
return _FAKE_LOCATION
|
||||
return _get_real_location()
|
||||
|
||||
|
||||
@pytest.fixture(name="gcloud_credentials")
|
||||
def fixture_gcloud_credentials(in_replay_mode):
|
||||
if in_replay_mode:
|
||||
return FakeCredentials()
|
||||
creds, _ = google.auth.default()
|
||||
return google.auth.credentials.with_scopes_if_required(
|
||||
creds, ["https://www.googleapis.com/auth/cloud-platform"]
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture(name="gemini_api_key")
|
||||
def fixture_gemini_api_key(in_replay_mode):
|
||||
if in_replay_mode:
|
||||
return _FAKE_API_KEY
|
||||
return os.getenv("GEMINI_API_KEY")
|
||||
|
||||
|
||||
@pytest.fixture(name="gcloud_api_key", autouse=True)
|
||||
def fixture_gcloud_api_key(gemini_api_key):
|
||||
if "GOOGLE_API_KEY" not in os.environ:
|
||||
os.environ["GOOGLE_API_KEY"] = gemini_api_key
|
||||
return os.getenv("GOOGLE_API_KEY")
|
||||
|
||||
|
||||
@pytest.fixture(name="nonvertex_client_factory")
|
||||
def fixture_nonvertex_client_factory(gemini_api_key):
|
||||
def _factory():
|
||||
return google.genai.Client(api_key=gemini_api_key, vertexai=False)
|
||||
|
||||
return _factory
|
||||
|
||||
|
||||
@pytest.fixture(name="vertex_client_factory")
|
||||
def fixture_vertex_client_factory(
|
||||
gcloud_project, gcloud_location, gcloud_credentials
|
||||
):
|
||||
def _factory():
|
||||
return google.genai.Client(
|
||||
vertexai=True,
|
||||
project=gcloud_project,
|
||||
location=gcloud_location,
|
||||
credentials=gcloud_credentials,
|
||||
)
|
||||
|
||||
return _factory
|
||||
|
||||
|
||||
@pytest.fixture(name="genai_sdk_backend", params=["vertexaiapi"])
|
||||
def fixture_genai_sdk_backend(request):
|
||||
return request.param
|
||||
|
||||
|
||||
@pytest.fixture(name="use_vertex", autouse=True)
|
||||
def fixture_use_vertex(genai_sdk_backend):
|
||||
result = bool(genai_sdk_backend == "vertexaiapi")
|
||||
os.environ["GOOGLE_GENAI_USE_VERTEXAI"] = "1" if result else "0"
|
||||
return result
|
||||
|
||||
|
||||
@pytest.fixture(name="client")
|
||||
def fixture_client(
|
||||
vertex_client_factory, nonvertex_client_factory, use_vertex
|
||||
):
|
||||
if use_vertex:
|
||||
return vertex_client_factory()
|
||||
return nonvertex_client_factory()
|
||||
|
||||
|
||||
@pytest.fixture(name="is_async", params=["sync", "async"])
|
||||
def fixture_is_async(request):
|
||||
return request.param == "async"
|
||||
|
||||
|
||||
@pytest.fixture(name="model", params=["gemini-1.5-flash-002"])
|
||||
def fixture_model(request):
|
||||
return request.param
|
||||
|
||||
|
||||
@pytest.fixture(name="generate_content")
|
||||
def fixture_generate_content(client, is_async):
|
||||
def _sync_impl(*args, **kwargs):
|
||||
return client.models.generate_content(*args, **kwargs)
|
||||
|
||||
def _async_impl(*args, **kwargs):
|
||||
return asyncio.run(client.aio.models.generate_content(*args, **kwargs))
|
||||
|
||||
if is_async:
|
||||
return _async_impl
|
||||
return _sync_impl
|
||||
|
||||
|
||||
@pytest.fixture(name="generate_content_stream")
|
||||
def fixture_generate_content_stream(client, is_async):
|
||||
def _sync_impl(*args, **kwargs):
|
||||
results = []
|
||||
for result in client.models.generate_content_stream(*args, **kwargs):
|
||||
results.append(result)
|
||||
return results
|
||||
|
||||
def _async_impl(*args, **kwargs):
|
||||
async def _gather_all():
|
||||
results = []
|
||||
async for (
|
||||
result
|
||||
) in await client.aio.models.generate_content_stream(
|
||||
*args, **kwargs
|
||||
):
|
||||
results.append(result)
|
||||
return results
|
||||
|
||||
return asyncio.run(_gather_all())
|
||||
|
||||
if is_async:
|
||||
return _async_impl
|
||||
return _sync_impl
|
||||
|
||||
|
||||
@pytest.mark.vcr
|
||||
def test_non_streaming(generate_content, model, otel_mocker):
|
||||
response = generate_content(
|
||||
model=model, contents="Create a poem about Open Telemetry."
|
||||
)
|
||||
assert response is not None
|
||||
assert response.text is not None
|
||||
assert len(response.text) > 0
|
||||
otel_mocker.assert_has_span_named(f"generate_content {model}")
|
||||
|
||||
|
||||
@pytest.mark.vcr
|
||||
def test_streaming(generate_content_stream, model, otel_mocker):
|
||||
count = 0
|
||||
for response in generate_content_stream(
|
||||
model=model, contents="Create a poem about Open Telemetry."
|
||||
):
|
||||
assert response is not None
|
||||
assert response.text is not None
|
||||
assert len(response.text) > 0
|
||||
count += 1
|
||||
assert count > 0
|
||||
otel_mocker.assert_has_span_named(f"generate_content {model}")
|
||||
@ -12,27 +12,64 @@
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
from typing import Optional, Union
|
||||
|
||||
def create_valid_response(
|
||||
response_text="The model response", input_tokens=10, output_tokens=20
|
||||
):
|
||||
return {
|
||||
"modelVersion": "gemini-2.0-flash-test123",
|
||||
"usageMetadata": {
|
||||
"promptTokenCount": input_tokens,
|
||||
"candidatesTokenCount": output_tokens,
|
||||
"totalTokenCount": input_tokens + output_tokens,
|
||||
},
|
||||
"candidates": [
|
||||
{
|
||||
"content": {
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": response_text,
|
||||
}
|
||||
],
|
||||
}
|
||||
}
|
||||
],
|
||||
}
|
||||
import google.genai.types as genai_types
|
||||
|
||||
|
||||
def create_response(
|
||||
part: Optional[genai_types.Part] = None,
|
||||
parts: Optional[list[genai_types.Part]] = None,
|
||||
content: Optional[genai_types.Content] = None,
|
||||
candidate: Optional[genai_types.Candidate] = None,
|
||||
candidates: Optional[list[genai_types.Candidate]] = None,
|
||||
text: Optional[str] = None,
|
||||
input_tokens: Optional[int] = None,
|
||||
output_tokens: Optional[int] = None,
|
||||
model_version: Optional[str] = None,
|
||||
usage_metadata: Optional[
|
||||
genai_types.GenerateContentResponseUsageMetadata
|
||||
] = None,
|
||||
**kwargs,
|
||||
) -> genai_types.GenerateContentResponse:
|
||||
# Build up the "candidates" subfield
|
||||
if text is None:
|
||||
text = "Some response text"
|
||||
if part is None:
|
||||
part = genai_types.Part(text=text)
|
||||
if parts is None:
|
||||
parts = [part]
|
||||
if content is None:
|
||||
content = genai_types.Content(parts=parts, role="model")
|
||||
if candidate is None:
|
||||
candidate = genai_types.Candidate(content=content)
|
||||
if candidates is None:
|
||||
candidates = [candidate]
|
||||
|
||||
# Build up the "usage_metadata" subfield
|
||||
if usage_metadata is None:
|
||||
usage_metadata = genai_types.GenerateContentResponseUsageMetadata()
|
||||
if input_tokens is not None:
|
||||
usage_metadata.prompt_token_count = input_tokens
|
||||
if output_tokens is not None:
|
||||
usage_metadata.candidates_token_count = output_tokens
|
||||
return genai_types.GenerateContentResponse(
|
||||
candidates=candidates,
|
||||
usage_metadata=usage_metadata,
|
||||
model_version=model_version,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
|
||||
def convert_to_response(
|
||||
arg: Union[str, genai_types.GenerateContentResponse, dict],
|
||||
) -> genai_types.GenerateContentResponse:
|
||||
if isinstance(arg, str):
|
||||
return create_response(text=arg)
|
||||
if isinstance(arg, genai_types.GenerateContentResponse):
|
||||
return arg
|
||||
if isinstance(arg, dict):
|
||||
return create_response(**arg)
|
||||
raise ValueError(
|
||||
f"Unsure how to convert {arg} of type {arg.__class__.__name__} to response."
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user