lmnr 0.4.12b3__py3-none-any.whl → 0.4.13__py3-none-any.whl

{lmnr-0.4.12b3.dist-info → lmnr-0.4.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lmnr
-Version: 0.4.12b3
+Version: 0.4.13
 Summary: Python SDK for Laminar AI
 License: Apache-2.0
 Author: lmnr.ai
@@ -14,7 +14,6 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: argparse (>=1.0,<2.0)
 Requires-Dist: asyncio (>=3.0,<4.0)
 Requires-Dist: backoff (>=2.0,<3.0)
-Requires-Dist: colorama (>=0.4,<0.5)
 Requires-Dist: deprecated (>=1.0,<2.0)
 Requires-Dist: jinja2 (>=3.0,<4.0)
 Requires-Dist: opentelemetry-api (>=1.27.0,<2.0.0)
@@ -60,63 +59,37 @@ Description-Content-Type: text/markdown
 
 # Laminar Python
 
-OpenTelemetry log sender for [Laminar](https://github.com/lmnr-ai/lmnr) for Python code.
+Python SDK for [Laminar](https://www.lmnr.ai).
+
+[Laminar](https://www.lmnr.ai) is an open-source platform for engineering LLM products. Trace, evaluate, annotate, and analyze LLM data. Bring LLM applications to production with confidence.
+
+Check our [open-source repo](https://github.com/lmnr-ai/lmnr) and don't forget to star it ⭐
 
  <a href="https://pypi.org/project/lmnr/"> ![PyPI - Version](https://img.shields.io/pypi/v/lmnr?label=lmnr&logo=pypi&logoColor=3775A9) </a>
 ![PyPI - Downloads](https://img.shields.io/pypi/dm/lmnr)
 ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/lmnr)
 
 
-
 ## Quickstart
 
 First, install the package:
 
 ```sh
-python3 -m venv .myenv
-source .myenv/bin/activate  # or use your favorite env management tool
-
 pip install lmnr
 ```
 
-Then, you can initialize Laminar in your main file and instrument your code.
+And then in the code
 
 ```python
-import os
-from openai import OpenAI
 from lmnr import Laminar as L
 
-L.initialize(
-    project_api_key=os.environ["LMNR_PROJECT_API_KEY"],
-)
-
-client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
-
-def poem_writer(topic: str):
-    prompt = f"write a poem about {topic}"
-
-    # OpenAI calls are automatically instrumented
-    response = client.chat.completions.create(
-        model="gpt-4o",
-        messages=[
-            {"role": "system", "content": "You are a helpful assistant."},
-            {"role": "user", "content": prompt},
-        ],
-    )
-    poem = response.choices[0].message.content
-    return poem
-
-if __name__ == "__main__":
-    print(poem_writer("laminar flow"))
-
+L.initialize(project_api_key="<PROJECT_API_KEY>")
 ```
 
-Note that you need to only initialize Laminar once in your application.
+This will automatically instrument most of the LLM, Vector DB, and related
+calls with OpenTelemetry-compatible instrumentation.
 
-### Project API key
-
-Get the key from the settings page of your Laminar project ([Learn more](https://docs.lmnr.ai/api-reference/introduction#authentication)).
-You can either pass it to `.initialize()` or set it to `.env` at the root of your package with the key `LMNR_PROJECT_API_KEY`.
+Note that you need to only initialize Laminar once in your application.
 
 ## Instrumentation
 
@@ -197,7 +170,7 @@ L.initialize(project_api_key=os.environ["LMNR_PROJECT_API_KEY"], instruments={In
 
 If you want to fully disable any kind of autoinstrumentation, pass an empty set as `instruments=set()` to `.initialize()`. 
 
-Majority of the autoinstrumentations are provided by Traceloop's [OpenLLMetry](https://github.com/traceloop/openllmetry).
+Autoinstrumentations are provided by Traceloop's [OpenLLMetry](https://github.com/traceloop/openllmetry).
 
 ## Sending events
 
@@ -225,6 +198,67 @@ L.event("topic alignment", topic in poem)
 L.evaluate_event("excessive_wordiness", "check_wordy", {"text_input": poem})
 ```
 
+## Evaluations
+
+### Quickstart
+
+Install the package:
+
+```sh
+pip install lmnr
+```
+
+Create a file named `my_first_eval.py` with the following code:
+
+```python
+from lmnr import evaluate
+
+def write_poem(data):
+    return f"This is a good poem about {data['topic']}"
+
+def contains_poem(output, target):
+    return 1 if output in target['poem'] else 0
+
+# Evaluation data
+data = [
+    {"data": {"topic": "flowers"}, "target": {"poem": "This is a good poem about flowers"}},
+    {"data": {"topic": "cars"}, "target": {"poem": "I like cars"}},
+]
+
+evaluate(
+    data=data,
+    executor=write_poem,
+    evaluators={
+        "containsPoem": contains_poem
+    }
+)
+```
+
+Run the following commands:
+
+```sh
+export LMNR_PROJECT_API_KEY=<YOUR_PROJECT_API_KEY>  # get from Laminar project settings
+lmnr eval my_first_eval.py  # run in the virtual environment where lmnr is installed
+```
+
+Visit the URL printed in the console to see the results.
+
+### Overview
+
+Bring rigor to the development of your LLM applications with evaluations.
+
+You can run evaluations locally by providing executor (part of the logic used in your application) and evaluators (numeric scoring functions) to `evaluate` function.
+
+`evaluate` takes in the following parameters:
+- `data` – an array of `EvaluationDatapoint` objects, where each `EvaluationDatapoint` has two keys: `target` and `data`, each containing a key-value object. Alternatively, you can pass in dictionaries, and we will instantiate `EvaluationDatapoint`s with pydantic if possible
+- `executor` – the logic you want to evaluate. This function must take `data` as the first argument, and produce any output. It can be both a function or an `async` function.
+- `evaluators` – Dictionary which maps evaluator names to evaluators. Functions that take output of executor as the first argument, `target` as the second argument and produce a numeric scores. Each function can produce either a single number or `dict[str, int|float]` of scores. Each evaluator can be both a function or an `async` function.
+- `name` – optional name for the evaluation. Automatically generated if not provided.
+
+\* If you already have the outputs of executors you want to evaluate, you can specify the executor as an identity function, that takes in `data` and returns only needed value(s) from it.
+
+[Read docs](https://docs.lmnr.ai/evaluations/introduction) to learn more about evaluations.
+
 ## Laminar pipelines as prompt chain managers
 
 You can create Laminar pipelines in the UI and manage chains of LLM calls there.
@@ -259,65 +293,3 @@ PipelineRunResponse(
 )
 ```
 
-## Running offline evaluations on your data
-
-You can evaluate your code with your own data and send it to Laminar using the `Evaluation` class.
-
-Evaluation takes in the following parameters:
-- `name` – the name of your evaluation. If no such evaluation exists in the project, it will be created. Otherwise, data will be pushed to the existing evaluation
-- `data` – an array of `EvaluationDatapoint` objects, where each `EvaluationDatapoint` has two keys: `target` and `data`, each containing a key-value object. Alternatively, you can pass in dictionaries, and we will instantiate `EvaluationDatapoint`s with pydantic if possible
-- `executor` – the logic you want to evaluate. This function must take `data` as the first argument, and produce any output. *
-- `evaluators` – evaluaton logic. List of functions that take output of executor as the first argument, `target` as the second argument and produce a numeric scores. Each function can produce either a single number or `dict[str, int|float]` of scores.
-
-\* If you already have the outputs of executors you want to evaluate, you can specify the executor as an identity function, that takes in `data` and returns only needed value(s) from it.
-
-### Example
-
-```python
-from openai import AsyncOpenAI
-import asyncio
-import os
-
-openai_client = AsyncOpenAI(api_key=os.environ["OPENAI_API_KEY"])
-
-async def get_capital(data):
-    country = data["country"]
-    response = await openai_client.chat.completions.create(
-        model="gpt-4o-mini",
-        messages=[
-            {"role": "system", "content": "You are a helpful assistant."},
-            {
-                "role": "user",
-                "content": f"What is the capital of {country}? Just name the "
-                "city and nothing else",
-            },
-        ],
-    )
-    return response.choices[0].message.content.strip()
-
-
-# Evaluation data
-data = [
-    {"data": {"country": "Canada"}, "target": {"capital": "Ottawa"}},
-    {"data": {"country": "Germany"}, "target": {"capital": "Berlin"}},
-    {"data": {"country": "Tanzania"}, "target": {"capital": "Dodoma"}},
-]
-
-
-def evaluator_A(output, target):
-    return 1 if output == target["capital"] else 0
-
-
-# Create an Evaluation instance
-e = Evaluation(
-    name="py-evaluation-async",
-    data=data,
-    executor=get_capital,
-    evaluators=[evaluator_A],
-    project_api_key=os.environ["LMNR_PROJECT_API_KEY"],
-)
-
-# Run the evaluation
-asyncio.run(e.run())
-```
-

{lmnr-0.4.12b3.dist-info → lmnr-0.4.13.dist-info}/RECORD

@@ -1,21 +1,19 @@
 lmnr/__init__.py,sha256=5Ks8UIicCzCBgwSz0MOX3I7jVruPMUO3SmxIwUoODzQ,231
 lmnr/cli.py,sha256=Ptvm5dsNLKUY5lwnN8XkT5GtCYjzpRNi2WvefknB3OQ,1079
 lmnr/sdk/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lmnr/sdk/decorators.py,sha256=O8S4PI6LUfdWPkbroigl5khtnkyhp24J8qzSdlvCs44,2227
-lmnr/sdk/evaluations.py,sha256=Ip0XJsdNEPcq4LhPaYF7DOS0y1sDXpPuDf7Vf2YUkJc,11940
-lmnr/sdk/laminar.py,sha256=vG9JkaonK8XBLSFVf4sKV50silbg7UVVLTbWFB3SANw,19011
+lmnr/sdk/decorators.py,sha256=ii7Bqp6flaanIFSK6M1_ZZV-izp4o3hkR1MmY7wnFQQ,2227
+lmnr/sdk/evaluations.py,sha256=4VEfhL8DsrQLX96jHrGmBKHxCnbfM-4-6MFOR-XQozM,13525
+lmnr/sdk/laminar.py,sha256=jH0-J7S5k8duwivE2giYuh6mx64PswoEWHUdH4GFqoM,18305
 lmnr/sdk/log.py,sha256=EgAMY77Zn1bv1imCqrmflD3imoAJ2yveOkIcrIP3e98,1170
-lmnr/sdk/types.py,sha256=nSN6Z4CDVFJ0o-vjzIT1qzwRiJ70pReGpqdNOcjXKic,4062
-lmnr/sdk/utils.py,sha256=ZsGJ86tq8lIbvOhSb1gJWH5K3GylO_lgX68FN6rG2nM,3358
+lmnr/sdk/types.py,sha256=KUCVIdkyr9pN2KKp-H1O-FU8x5_yKeC3cUP3Je3hY6g,5117
+lmnr/sdk/utils.py,sha256=s81p6uJehgJSaLWy3sR5fTpEDH7vzn3i_UujUHChl6M,3346
 lmnr/traceloop_sdk/.flake8,sha256=bCxuDlGx3YQ55QHKPiGJkncHanh9qGjQJUujcFa3lAU,150
 lmnr/traceloop_sdk/.python-version,sha256=9OLQBQVbD4zE4cJsPePhnAfV_snrPSoqEQw-PXgPMOs,6
-lmnr/traceloop_sdk/__init__.py,sha256=-wa25NtU7BeTgqjT6rpVIEdaVP4aOjLgbYrc3B3-JaM,3932
-lmnr/traceloop_sdk/config/__init__.py,sha256=EGN3ixOt_ORbMxqaQdLaC14kmO-gyG4mnGJ2GfN-R-E,364
+lmnr/traceloop_sdk/__init__.py,sha256=hp3q1OsFaGgaQCEanJrL38BJN32hWqCNVCSjYpndEsY,2957
+lmnr/traceloop_sdk/config/__init__.py,sha256=DliMGp2NjYAqRFLKpWQPUKjGMHRO8QsVfazBA1qENQ8,248
 lmnr/traceloop_sdk/decorators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lmnr/traceloop_sdk/decorators/base.py,sha256=wcqXF0iVQgRXMyWTcJ5QvL_6q2y_gttwsX8dllmAtWM,4891
+lmnr/traceloop_sdk/decorators/base.py,sha256=-b8Q738m3StdLTgHARx8zw78m9htynKkZFFTYURQnOA,5524
 lmnr/traceloop_sdk/instruments.py,sha256=oMvIASueW3GeChpjIdH-DD9aFBVB8OtHZ0HawppTrlI,942
-lmnr/traceloop_sdk/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lmnr/traceloop_sdk/metrics/metrics.py,sha256=AlQ2a2os1WcZbfBd155u_UzBbPrbuPia6O_HbojV9Wc,5055
 lmnr/traceloop_sdk/tests/__init__.py,sha256=RYnG0-8zbXL0-2Ste1mEBf5sN4d_rQjGTCgPBuaZC74,20
 lmnr/traceloop_sdk/tests/cassettes/test_association_properties/test_langchain_and_external_association_properties.yaml,sha256=26g0wRA0juicHg_XrhcE8H4vhs1lawDs0o0aLFn-I7w,3103
 lmnr/traceloop_sdk/tests/cassettes/test_association_properties/test_langchain_association_properties.yaml,sha256=FNlSWlYCsWc3w7UPZzfGjDnxS3gAOhL-kpsu4BTxsDE,3061
@@ -37,17 +35,17 @@ lmnr/traceloop_sdk/tests/test_sdk_initialization.py,sha256=fRaf6lrxFzJIN94P1Tav_
 lmnr/traceloop_sdk/tests/test_tasks.py,sha256=xlEx8BKp4yG83SCjK5WkPGfyC33JSrx4h8VyjVwGbgw,906
 lmnr/traceloop_sdk/tests/test_workflows.py,sha256=RVcfY3WAFIDZC15-aSua21aoQyYeWE7KypDyUsm-2EM,9372
 lmnr/traceloop_sdk/tracing/__init__.py,sha256=Ckq7zCM26VdJVB5tIZv0GTPyMZKyfso_KWD5yPHaqdo,66
+lmnr/traceloop_sdk/tracing/attributes.py,sha256=PXwS1GCZKdjQSypl__BSkQNZhh21RyzwTPnDOh61bnQ,250
 lmnr/traceloop_sdk/tracing/content_allow_list.py,sha256=3feztm6PBWNelc8pAZUcQyEGyeSpNiVKjOaDk65l2ps,846
 lmnr/traceloop_sdk/tracing/context_manager.py,sha256=csVlB6kDmbgSPsROHwnddvGGblx55v6lJMRj0wsSMQM,304
-lmnr/traceloop_sdk/tracing/manual.py,sha256=RPwEreHHdzmw7g15u4G21GqhHOvRp7d72ylQNLG1jRM,1841
-lmnr/traceloop_sdk/tracing/tracing.py,sha256=5e8AsiFKaIO6zqAbMfhw242glVsQUkxbNhTWP7QDqSg,40108
+lmnr/traceloop_sdk/tracing/tracing.py,sha256=pB8vImUZRMaahkHLaQP73cbMtYDyvpvEdWsa49520Yo,36061
 lmnr/traceloop_sdk/utils/__init__.py,sha256=pNhf0G3vTd5ccoc03i1MXDbricSaiqCbi1DLWhSekK8,604
 lmnr/traceloop_sdk/utils/in_memory_span_exporter.py,sha256=H_4TRaThMO1H6vUQ0OpQvzJk_fZH0OOsRAM1iZQXsR8,2112
 lmnr/traceloop_sdk/utils/json_encoder.py,sha256=dK6b_axr70IYL7Vv-bu4wntvDDuyntoqsHaddqX7P58,463
 lmnr/traceloop_sdk/utils/package_check.py,sha256=TZSngzJOpFhfUZLXIs38cpMxQiZSmp0D-sCrIyhz7BA,251
 lmnr/traceloop_sdk/version.py,sha256=OlatFEFA4ttqSSIiV8jdE-sq3KG5zu2hnC4B4mzWF3s,23
-lmnr-0.4.12b3.dist-info/LICENSE,sha256=67b_wJHVV1CBaWkrKFWU1wyqTPSdzH77Ls-59631COg,10411
-lmnr-0.4.12b3.dist-info/METADATA,sha256=VnqchbOU6e4xrMuioUj2uJPWDNWGkcz5nmOM-Fua0UI,11992
-lmnr-0.4.12b3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-lmnr-0.4.12b3.dist-info/entry_points.txt,sha256=K1jE20ww4jzHNZLnsfWBvU3YKDGBgbOiYG5Y7ivQcq4,37
-lmnr-0.4.12b3.dist-info/RECORD,,
+lmnr-0.4.13.dist-info/LICENSE,sha256=67b_wJHVV1CBaWkrKFWU1wyqTPSdzH77Ls-59631COg,10411
+lmnr-0.4.13.dist-info/METADATA,sha256=TgaQ5yPkKErpY9WrLywc84BJyAxsffR1Rf0_N_qeOvA,11233
+lmnr-0.4.13.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+lmnr-0.4.13.dist-info/entry_points.txt,sha256=K1jE20ww4jzHNZLnsfWBvU3YKDGBgbOiYG5Y7ivQcq4,37
+lmnr-0.4.13.dist-info/RECORD,,

lmnr/traceloop_sdk/metrics/metrics.py

@@ -1,176 +0,0 @@
-from collections.abc import Sequence
-from typing import Dict
-
-from opentelemetry.exporter.otlp.proto.grpc.metric_exporter import (
-    OTLPMetricExporter as GRPCExporter,
-)
-from opentelemetry.exporter.otlp.proto.http.metric_exporter import (
-    OTLPMetricExporter as HTTPExporter,
-)
-from opentelemetry.semconv_ai import Meters
-from opentelemetry.sdk.metrics import MeterProvider
-from opentelemetry.sdk.metrics.export import (
-    PeriodicExportingMetricReader,
-    MetricExporter,
-)
-from opentelemetry.sdk.metrics.view import View, ExplicitBucketHistogramAggregation
-from opentelemetry.sdk.resources import Resource
-
-from opentelemetry import metrics
-
-
-class MetricsWrapper(object):
-    resource_attributes: dict = {}
-    endpoint: str = None
-    # if it needs headers?
-    headers: Dict[str, str] = {}
-    __metrics_exporter: MetricExporter = None
-    __metrics_provider: MeterProvider = None
-
-    def __new__(cls, exporter: MetricExporter = None) -> "MetricsWrapper":
-        if not hasattr(cls, "instance"):
-            obj = cls.instance = super(MetricsWrapper, cls).__new__(cls)
-            if not MetricsWrapper.endpoint:
-                return obj
-
-            obj.__metrics_exporter = (
-                exporter
-                if exporter
-                else init_metrics_exporter(
-                    MetricsWrapper.endpoint, MetricsWrapper.headers
-                )
-            )
-
-            obj.__metrics_provider = init_metrics_provider(
-                obj.__metrics_exporter, MetricsWrapper.resource_attributes
-            )
-
-        return cls.instance
-
-    @staticmethod
-    def set_static_params(
-        resource_attributes: dict,
-        endpoint: str,
-        headers: Dict[str, str],
-    ) -> None:
-        MetricsWrapper.resource_attributes = resource_attributes
-        MetricsWrapper.endpoint = endpoint
-        MetricsWrapper.headers = headers
-
-
-def init_metrics_exporter(endpoint: str, headers: Dict[str, str]) -> MetricExporter:
-    if "http" in endpoint.lower() or "https" in endpoint.lower():
-        return HTTPExporter(endpoint=f"{endpoint}/v1/metrics", headers=headers)
-    else:
-        return GRPCExporter(endpoint=endpoint, headers=headers)
-
-
-def init_metrics_provider(
-    exporter: MetricExporter, resource_attributes: dict = None
-) -> MeterProvider:
-    resource = (
-        Resource.create(resource_attributes)
-        if resource_attributes
-        else Resource.create()
-    )
-    reader = PeriodicExportingMetricReader(exporter)
-    provider = MeterProvider(
-        metric_readers=[reader],
-        resource=resource,
-        views=metric_views(),
-    )
-
-    metrics.set_meter_provider(provider)
-    return provider
-
-
-def metric_views() -> Sequence[View]:
-    return [
-        View(
-            instrument_name=Meters.LLM_TOKEN_USAGE,
-            aggregation=ExplicitBucketHistogramAggregation(
-                [
-                    0.01,
-                    0.02,
-                    0.04,
-                    0.08,
-                    0.16,
-                    0.32,
-                    0.64,
-                    1.28,
-                    2.56,
-                    5.12,
-                    10.24,
-                    20.48,
-                    40.96,
-                    81.92,
-                ]
-            ),
-        ),
-        View(
-            instrument_name=Meters.LLM_OPERATION_DURATION,
-            aggregation=ExplicitBucketHistogramAggregation(
-                [
-                    1,
-                    4,
-                    16,
-                    64,
-                    256,
-                    1024,
-                    4096,
-                    16384,
-                    65536,
-                    262144,
-                    1048576,
-                    4194304,
-                    16777216,
-                    67108864,
-                ]
-            ),
-        ),
-        View(
-            instrument_name=Meters.PINECONE_DB_QUERY_DURATION,
-            aggregation=ExplicitBucketHistogramAggregation(
-                [
-                    0.01,
-                    0.02,
-                    0.04,
-                    0.08,
-                    0.16,
-                    0.32,
-                    0.64,
-                    1.28,
-                    2.56,
-                    5.12,
-                    10.24,
-                    20.48,
-                    40.96,
-                    81.92,
-                ]
-            ),
-        ),
-        View(
-            instrument_name=Meters.PINECONE_DB_QUERY_SCORES,
-            aggregation=ExplicitBucketHistogramAggregation(
-                [
-                    -1,
-                    -0.875,
-                    -0.75,
-                    -0.625,
-                    -0.5,
-                    -0.375,
-                    -0.25,
-                    -0.125,
-                    0,
-                    0.125,
-                    0.25,
-                    0.375,
-                    0.5,
-                    0.625,
-                    0.75,
-                    0.875,
-                    1,
-                ]
-            ),
-        ),
-    ]

lmnr/traceloop_sdk/tracing/manual.py

@@ -1,57 +0,0 @@
-from contextlib import contextmanager
-from opentelemetry.semconv_ai import SpanAttributes
-from opentelemetry.trace import Span
-from pydantic import BaseModel
-from lmnr.traceloop_sdk.tracing.context_manager import get_tracer
-
-
-class LLMMessage(BaseModel):
-    role: str
-    content: str
-
-
-class LLMUsage(BaseModel):
-    prompt_tokens: int
-    completion_tokens: int
-    total_tokens: int
-
-
-class LLMSpan:
-    _span: Span = None
-
-    def __init__(self, span: Span):
-        self._span = span
-        pass
-
-    def report_request(self, model: str, messages: list[LLMMessage]):
-        self._span.set_attribute(SpanAttributes.LLM_REQUEST_MODEL, model)
-        for idx, message in enumerate(messages):
-            self._span.set_attribute(
-                f"{SpanAttributes.LLM_PROMPTS}.{idx}.role", message.role
-            )
-            self._span.set_attribute(
-                f"{SpanAttributes.LLM_PROMPTS}.{idx}.content", message.content
-            )
-
-    def report_response(self, model: str, completions: list[str]):
-        self._span.set_attribute(SpanAttributes.LLM_RESPONSE_MODEL, model)
-        for idx, completion in enumerate(completions):
-            self._span.set_attribute(
-                f"{SpanAttributes.LLM_COMPLETIONS}.{idx}.role", "assistant"
-            )
-            self._span.set_attribute(
-                f"{SpanAttributes.LLM_COMPLETIONS}.{idx}", completion
-            )
-
-
-@contextmanager
-def track_llm_call(vendor: str, type: str):
-    with get_tracer() as tracer:
-        with tracer.start_as_current_span(name=f"{vendor}.{type}") as span:
-            span.set_attribute(SpanAttributes.LLM_SYSTEM, vendor)
-            span.set_attribute(SpanAttributes.LLM_REQUEST_TYPE, type)
-            llm_span = LLMSpan(span)
-            try:
-                yield llm_span
-            finally:
-                span.end()