Simplify GCP integration docs (#67)

Author: michaelsafyan

openllmetry/integrations/gcp.mdx

@@ -1,111 +1,45 @@
 ---
-title: "LLM Observability with Google Cloud Trace and OpenLLMetry"
+title: "LLM Observability with Google Cloud and OpenLLMetry"
 sidebarTitle: "Google Cloud"
 ---
 
 [Google Cloud](https://cloud.google.com/?hl=en), also known as Google Cloud Platform (GCP), is a cloud
 provider including [over 150+ products and services](https://cloud.google.com/products?hl=en). Among
-these products and services is [Cloud Trace](https://cloud.google.com/trace/docs), which is a part of the
-[Google Cloud Observability](https://cloud.google.com/stackdriver/docs) suite alongside
-[Cloud Monitoring](https://cloud.google.com/monitoring/docs) and [Cloud Logging](https://cloud.google.com/logging/docs).
+these products and services are [Cloud Trace](https://cloud.google.com/trace/docs),
+[Cloud Monitoring](https://cloud.google.com/monitoring/docs), and [Cloud Logging](https://cloud.google.com/logging/docs)
+which together comprise [Google Cloud Observability](https://cloud.google.com/stackdriver/docs).
 
 Traceloop's OpenLLMetry library enables instrumenting LLM frameworks in an OTel-aligned manner and
-supports writing that instrumentation data as distributed traces to Cloud Trace. Traceloop's OpenLLMetry
-library can be additionally configured to also write to Cloud Monitoring and to Cloud Logging.
+supports writing that instrumentation data to Google Cloud, primarily as distributed traces in Cloud Trace.
 
-## Minimal Integration: Cloud Trace only
+## Integration Instructions
 
-### Dependencies
+### Step 1. Install Python Dependencies
 
-- [`opentelemetry-exporter-gcp-trace`](https://pypi.org/project/opentelemetry-exporter-gcp-trace/)
-- [`traceloop-sdk`](https://pypi.org/project/traceloop-sdk/)
-
-### OpenLLMetry Configuration
-
-```python
-
-# ...
-from opentelemetry.exporter.cloud_trace import CloudTraceSpanExporter
-from traceloop.sdk import Traceloop
-
-# ...
-trace_exporter = CloudTraceSpanExporter()
-Traceloop.init(
-    app_name='your-app-name',
-    exporter=trace_exporter)
-```
-
-## Integration with Cloud Trace and Cloud Monitoring
-
-### Dependencies
-
-- [`opentelemetry-exporter-gcp-trace`](https://pypi.org/project/opentelemetry-exporter-gcp-trace/)
-- [`opentelemetry-exporter-gcp-monitoring`](https://pypi.org/project/opentelemetry-exporter-gcp-monitoring/)
-- [`traceloop-sdk`](https://pypi.org/project/traceloop-sdk/)
-
-### OpenLLMetry Configuration
-
-```python
-
-# ...
-from opentelemetry.exporter.cloud_trace import CloudTraceSpanExporter
-from opentelemetry.exporter.cloud_monitoring import CloudMonitoringMetricsExporter
-from traceloop.sdk import Traceloop
-
-# ...
-trace_exporter = CloudTraceSpanExporter()
-metrics_exporter = CloudMonitoringMetricsExporter()
-Traceloop.init(
-    app_name='your-app-name',
-    exporter=trace_exporter,
-    metrics_exporter=metrics_exporter)
+```bash
+pip install \
+   opentelemetry-exporter-gcp-trace \
+   opentelemetry-exporter-gcp-monitoring \
+   opentelemetry-exporter-gcp-logging \
+   traceloop-sdk
 ```
 
-## Integration with Cloud Trace, Cloud Monitoring, and Cloud Logging
-
-As of 2024-12-05, there is no direct Python OTel exporter for Cloud Logging. However,
-it is possible to work around this by routing to the [OTel Collector](https://opentelemetry.io/docs/collector/)
-and using the [`googlecloudexporter`](https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/main/exporter/googlecloudexporter/README.md)
-in the OTel Collector to route logs to Google Cloud Logging. Alternatively, you
-can use the Python [`ConsoleLogExporter`](https://github.com/open-telemetry/opentelemetry-python/blob/415c94fb9834ce38459e58d5ee192a98494c4c76/opentelemetry-sdk/src/opentelemetry/sdk/_logs/_internal/export/__init__.py#L86)
-to log to a file in conjunction with automatic file-based log routing such as via
-the [Ops Agent](https://cloud.google.com/stackdriver/docs/solutions/agents/ops-agent),
-direct use of [FluentBit](https://fluentbit.io/), or other routing solutions.
-
-### Dependencies
-
-#### OTel Dependencies
-
-This is assuming that you write to Cloud Logging via the OTel Collector:
+### Step 2. Initialize OpenLLMetry
 
- - [`opentelemetry-collector-contrib`](https://hub.docker.com/r/otel/opentelemetry-collector-contrib)
- - [`googlecloudexporter`](https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/main/exporter/googlecloudexporter/README.md)
-
-#### Python Dependencies
-
-- [`opentelemetry-exporter-gcp-trace`](https://pypi.org/project/opentelemetry-exporter-gcp-trace/)
-- [`opentelemetry-exporter-gcp-monitoring`](https://pypi.org/project/opentelemetry-exporter-gcp-monitoring/)
-- [`opentelemetry-exporter-otlp-proto-grpc`](https://pypi.org/project/opentelemetry-exporter-otlp-proto-grpc/)
-- [`traceloop-sdk`](https://pypi.org/project/traceloop-sdk/)
-
-### OpenLLMetry Configuration
+In your application code, invoke `Traceloop.init` as shown:
 
 ```python
 
 # ...
-from opentelemetry.exporter.otlp.proto.grpc._log_exporter import OTLPLogExporter
+from opentelemetry.exporter.cloud_logging import CloudLoggingExporter
 from opentelemetry.exporter.cloud_trace import CloudTraceSpanExporter
 from opentelemetry.exporter.cloud_monitoring import CloudMonitoringMetricsExporter
 from traceloop.sdk import Traceloop
 
 # ...
 trace_exporter = CloudTraceSpanExporter()
 metrics_exporter = CloudMonitoringMetricsExporter()
-
-# Will use the 'OTEL_EXPORTER_OTLP_LOGS_*' environment
-# variables (such as 'OTEL_EXPORTER_OTLP_LOGS_ENDPOINT')
-# to select how to connect to the OTel Collector.   
-logs_exporter = OTLPLogExporter()
+logs_exporter = CloudLoggingExporter()
 
 Traceloop.init(
     app_name='your-app-name',
@@ -118,17 +52,6 @@ Traceloop.init(
 
 ### Large Span Attributes
 
-Although [OTel Semantic Conventions](https://opentelemetry.io/docs/concepts/semantic-conventions/)
-[for GenAI](https://opentelemetry.io/docs/specs/semconv/gen-ai/) has been moving
-from prompt/response logging in span attributes to recording prompts/responses in
-events (logs) -- see [related pull request](https://github.com/open-telemetry/semantic-conventions/pull/980)
---, some versions of OpenLLMetry and related instrumentation packages follow older
-experimental conventions of recording prompts/responses in span attributes which do
-not fit within [Cloud Trace limits](https://cloud.google.com/trace/docs/quotas).
-
-The [`e2e-gen-ai-app-starter-pack`](https://github.com/GoogleCloudPlatform/generative-ai/tree/b96a0c9ccce165908d5e7262fedcafd9f6fde082/gemini/sample-apps/e2e-gen-ai-app-starter-pack)
-code sample provided by Google illustrates a potential workaround; that app, [calls
-`Traceloop.init`](https://github.com/GoogleCloudPlatform/generative-ai/blob/b96a0c9ccce165908d5e7262fedcafd9f6fde082/gemini/sample-apps/e2e-gen-ai-app-starter-pack/app/server.py#L64)
-with a custom [`CloudTraceLoggingSpanExporter`](https://github.com/GoogleCloudPlatform/generative-ai/blob/b96a0c9ccce165908d5e7262fedcafd9f6fde082/gemini/sample-apps/e2e-gen-ai-app-starter-pack/app/utils/tracing.py#L26)
-which inherits from the official `CloudTraceSpanExporter` and adds additional capabilities
-for handling large span attributes.
+You can use the [`CloudTraceLoggingSpanExporter`](https://github.com/GoogleCloudPlatform/agent-starter-pack/blob/3dfb0c444aa70a3b0c62313c4cba14f9bc9d1723/src/base_template/app/utils/tracing.py) 
+from the [Google Cloud `agent-starter-pack`](https://github.com/GoogleCloudPlatform/agent-starter-pack) as a drop-in replacement for the
+`CloudTraceSpanExporter`. That exporter writes large attributes to Google Cloud Storage and writes a reference URL to Cloud Observability.