Copy as Markdown[Open in ChatGPT](https://chatgpt.com/?q=Read%20https%3A%2F%2Fcoralogix.com%2Fdocs%2Fintegrations%2Fai-observability%2Fgemini.md%20and%20help%20me%20with%20my%20question%20about%20this%20Coralogix%20documentation%20page.)[Open in Claude](https://claude.ai/new?q=Read%20https%3A%2F%2Fcoralogix.com%2Fdocs%2Fintegrations%2Fai-observability%2Fgemini.md%20and%20help%20me%20with%20my%20question%20about%20this%20Coralogix%20documentation%20page.) # Gemini Coralogix's AI Observability integrations provide deep visibility into applications that rely on Google Gemini models. With a dedicated integration for the Google Generative AI SDK, Coralogix delivers consolidated insight into synchronous, streaming, and async calls, enabling teams to monitor performance, cost, and reliability across every Gemini workload. ## Overview[​](#overview "Direct link to Overview") This library offers customized [OpenTelemetry instrumentation](https://github.com/open-telemetry/opentelemetry-python-contrib/) for [Google Gemini](https://ai.google.dev/), optimized to support large language model (LLM) application development with streamlined integration, detailed production tracing, and effective debugging capabilities. ## Supported operations[​](#supported-operations "Direct link to Supported operations") * **Text generation**: `client.models.generate_content()` and `generate_content_stream()` (sync and async). * **Embeddings**: `client.models.embed_content()` (sync and async). ## Requirements[​](#requirements "Direct link to Requirements") * Python 3.10–3.13. * Coralogix [API keys](https://coralogix.com/docs/docs/user-guides/account-management/api-keys/api-keys/.md). ## Installation[​](#installation "Direct link to Installation") Run the following command. ``` pip install "llm-tracekit-gemini" ``` ## Authentication[​](#authentication "Direct link to Authentication") Authentication data is passed during OTel Span Exporter definition: 1. Choose the ingress.:443 endpoint that corresponds to your Coralogix [domain](https://coralogix.com/docs/docs/user-guides/account-management/account-settings/coralogix-domain/.md) using the domain selector at the top of the page. 2. Use your [customized API key](https://coralogix.com/docs/docs/user-guides/account-management/api-keys/api-keys/.md) in the authorization request header. 3. Provide the [application and subsystem names](https://coralogix.com/docs/docs/user-guides/account-management/account-settings/application-and-subsystem-names/.md). ``` from llm_tracekit.gemini import setup_export_to_coralogix setup_export_to_coralogix( coralogix_token=, coralogix_endpoint="ingress.eu2.coralogix.com:443", service_name="ai-service", application_name="ai-application", subsystem_name="ai-subsystem", capture_content=True, ) ``` Note All of the authentication parameters can also be provided through environment variables (`CX_TOKEN`, `CX_ENDPOINT`, etc.). ## Usage[​](#usage "Direct link to Usage") This section describes how to set up instrumentation for Google Gemini. ### Set up tracing[​](#set-up-tracing "Direct link to Set up tracing") **Automatic** Use the `setup_export_to_coralogix` function to set up tracing and export traces to Coralogix. See the code snippet in the [Authentication](#authentication) section. **Manual** Alternatively, you can set up tracing manually. ``` from opentelemetry import trace from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter from opentelemetry.sdk.resources import SERVICE_NAME, Resource from opentelemetry.sdk.trace import TracerProvider from opentelemetry.sdk.trace.export import SimpleSpanProcessor tracer_provider = TracerProvider( resource=Resource.create({SERVICE_NAME: "ai-service"}), ) exporter = OTLPSpanExporter() span_processor = SimpleSpanProcessor(exporter) tracer_provider.add_span_processor(span_processor) trace.set_tracer_provider(tracer_provider) ``` ### Instrument[​](#instrument "Direct link to Instrument") To instrument all clients, call the `instrument` method. ``` from llm_tracekit.gemini import GeminiInstrumentor GeminiInstrumentor().instrument() ``` ### Uninstrument[​](#uninstrument "Direct link to Uninstrument") To uninstrument clients, call the `uninstrument` method. ``` GeminiInstrumentor().uninstrument() ``` ### Full example: text generation[​](#full-example-text-generation "Direct link to Full example: text generation") ``` from google import genai from llm_tracekit.gemini import GeminiInstrumentor, setup_export_to_coralogix # Optional: Configure sending spans to Coralogix # Reads Coralogix connection details from the following environment variables: # - CX_TOKEN # - CX_ENDPOINT setup_export_to_coralogix( service_name="ai-service", application_name="ai-application", subsystem_name="ai-subsystem", capture_content=True, ) # Activate instrumentation GeminiInstrumentor().instrument() # Gemini usage example client = genai.Client() response = client.models.generate_content( model="gemini-2.0-flash", contents=[{"role": "user", "parts": [{"text": "Write a short poem on open telemetry."}]}], ) ``` ### Full example: embeddings[​](#full-example-embeddings "Direct link to Full example: embeddings") ``` from google import genai from google.genai import types from llm_tracekit.gemini import GeminiInstrumentor, setup_export_to_coralogix setup_export_to_coralogix( service_name="ai-service", application_name="ai-application", subsystem_name="ai-subsystem", capture_content=True, ) GeminiInstrumentor().instrument() client = genai.Client() # Single content embedding response = client.models.embed_content( model="gemini-embedding-001", contents="What is machine learning?", ) print(f"Embedding dimensions: {len(response.embeddings[0].values)}") # Batch embedding response = client.models.embed_content( model="gemini-embedding-001", contents=["First text", "Second text", "Third text"], ) print(f"Number of embeddings: {len(response.embeddings)}") # With dimensionality reduction response = client.models.embed_content( model="gemini-embedding-001", contents="What is quantum computing?", config=types.EmbedContentConfig(output_dimensionality=256), ) print(f"Reduced dimensions: {len(response.embeddings[0].values)}") ``` ### Enable message content capture[​](#enable-message-content-capture "Direct link to Enable message content capture") By default, message content — prompt contents, completions, function arguments, and return values — is not captured. To capture message content as span attributes: * Pass `capture_content=True` when calling `setup_export_to_coralogix`. * Set the environment variable `OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT` to `true`. Most Coralogix AI evaluations require message contents to function properly, so enabling message capture is strongly recommended. ## Semantic conventions[​](#semantic-conventions "Direct link to Semantic conventions") ### Text generation attributes[​](#text-generation-attributes "Direct link to Text generation attributes") | Attribute | Type | Description | Example | | ------------------------------------------------------------------------------------ | ------ | ----------------------------------------------------------------------------------------- | --------------------------------------------------------------------------- | | `gen_ai.prompt..role` | string | Role of message author for user message `` | `system`, `user`, `assistant`, `tool` | | `gen_ai.prompt..content` | string | Contents of user message `` | `What's the weather in Paris?` | | `gen_ai.prompt..tool_calls..id` | string | ID of tool call in user message `` | `call_O8NOz8VlxosSASEsOY7LDUcP` | | `gen_ai.prompt..tool_calls..type` | string | Type of tool call in user message `` | `function` | | `gen_ai.prompt..tool_calls..function.name` | string | The name of the function used in tool call within user message `` | `get_current_weather` | | `gen_ai.prompt..tool_calls..function.arguments` | string | Arguments passed to the function used in tool call within user message `` | `{"location": "Seattle, WA"}` | | `gen_ai.prompt..tool_call_id` | string | Tool call ID in user message `` | `call_mszuSIzqtI65i1wAUOE8w5H4` | | `gen_ai.completion..role` | string | Role of message author for choice `` in model response | `assistant` | | `gen_ai.completion..finish_reason` | string | Finish reason for choice `` in model response | `stop`, `tool_calls`, `error` | | `gen_ai.completion..content` | string | Contents of choice `` in model response | `The weather in Paris is rainy and overcast, with temperatures around 57°F` | | `gen_ai.completion..tool_calls..id` | string | ID of tool call in choice `` | `call_O8NOz8VlxosSASEsOY7LDUcP` | | `gen_ai.completion..tool_calls..type` | string | Type of tool call in choice `` | `function` | | `gen_ai.completion..tool_calls..function.name` | string | The name of the function used in tool call within choice `` | `get_current_weather` | | `gen_ai.completion..tool_calls..function.arguments` | string | Arguments passed to the function used in tool call within choice `` | `{"location": "Seattle, WA"}` | | `gen_ai.request.tools..type` | string | Type of tool definition advertised to the model | `function` | | `gen_ai.request.tools..function.name` | string | Name of the tool/function exposed to the model | `get_current_weather` | | `gen_ai.request.tools..function.description` | string | Description of the tool/function | `Get the current weather in a given location` | | `gen_ai.request.tools..function.parameters` | string | JSON schema describing the tool/function parameters passed with the request | `{"type": "object", "properties": {"city": {"type": "string"}}}` | ### Embeddings attributes[​](#embeddings-attributes "Direct link to Embeddings attributes") | Attribute | Type | Description | Example | | ----------------------------------- | ----- | ------------------------------------------------------------- | ----------------- | | `gen_ai.embeddings.dimension.count` | int | Requested output dimensionality | `256` | | `gen_ai.embeddings..vector` | array | The embedding vector values (when content capture is enabled) | `[0.1, 0.2, ...]` | ## Next steps[​](#next-steps "Direct link to Next steps") Once your integration is set up, explore the [AI Center Overview](https://coralogix.com/docs/docs/user-guides/ai/monitor/.md) to monitor performance, costs, quality issues, and security across all your AI applications — and to set up [Guardrails](https://coralogix.com/docs/docs/user-guides/ai/guardrails/.md) for real-time policy enforcement.