Add embeddings example

Author: drewby

instrumentation-genai/opentelemetry-instrumentation-openai-v2/examples/embeddings/.env

@@ -0,0 +1,22 @@
+# Update this with your real OpenAI API key
+OPENAI_API_KEY=sk-YOUR_API_KEY
+
+# Uncomment to use Ollama instead of OpenAI
+# OPENAI_BASE_URL=http://localhost:11434/v1
+# OPENAI_API_KEY=unused
+# CHAT_MODEL=qwen2.5:0.5b
+
+# Uncomment and change to your OTLP endpoint
+# OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
+# OTEL_EXPORTER_OTLP_PROTOCOL=grpc
+
+OTEL_SERVICE_NAME=opentelemetry-python-openai
+
+# Change to 'false' to disable collection of python logging logs
+OTEL_PYTHON_LOGGING_AUTO_INSTRUMENTATION_ENABLED=true
+
+# Uncomment if your OTLP endpoint doesn't support logs
+# OTEL_LOGS_EXPORTER=console
+
+# Change to 'false' to hide prompt and completion content
+OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true

instrumentation-genai/opentelemetry-instrumentation-openai-v2/examples/embeddings/README.rst

@@ -0,0 +1,44 @@
+OpenTelemetry OpenAI Embeddings API Instrumentation Example
+========================================================
+
+This is an example of how to instrument OpenAI Embeddings API calls with zero code changes,
+using ``opentelemetry-instrument``.
+
+When ``main.py`` is run, it exports traces and metrics to an OTLP
+compatible endpoint. Traces include details such as the model used,
+dimensions of embeddings, and the duration of the embedding request.
+Metrics capture token usage and performance data.
+
+Note: ``.env`` file configures additional environment variables:
+
+- ``OTEL_PYTHON_LOGGING_AUTO_INSTRUMENTATION_ENABLED=true`` configures OpenTelemetry SDK to export logs and events.
+- ``OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true`` configures OpenAI instrumentation to capture content on events.
+- ``OTEL_LOGS_EXPORTER=otlp`` to specify exporter type.
+
+Setup
+-----
+
+Minimally, update the ``.env`` file with your ``OPENAI_API_KEY``. An
+OTLP compatible endpoint should be listening for traces and logs on
+http://localhost:4317. If not, update ``OTEL_EXPORTER_OTLP_ENDPOINT`` as well.
+
+Next, set up a virtual environment like this:
+
+::
+
+    python3 -m venv .venv
+    source .venv/bin/activate
+    pip install "python-dotenv[cli]"
+    pip install -r requirements.txt
+
+Run
+---
+
+Run the example like this:
+
+::
+
+    dotenv run -- opentelemetry-instrument python main.py
+
+You should see embedding information printed while traces and metrics export to your
+configured observability tool.

instrumentation-genai/opentelemetry-instrumentation-openai-v2/examples/embeddings/main.py

@@ -0,0 +1,29 @@
+import os
+
+from openai import OpenAI
+
+
+def main():
+    client = OpenAI()
+
+    # Create embeddings with OpenAI API
+    embedding_response = client.embeddings.create(
+        model=os.getenv("EMBEDDING_MODEL", "text-embedding-3-small"),
+        input="OpenTelemetry provides observability for your applications.",
+    )
+
+    # Print embedding information
+    print(f"Model: {embedding_response.model}")
+    print(f"Dimensions: {len(embedding_response.data[0].embedding)}")
+    print(
+        f"Token usage - Prompt: {embedding_response.usage.prompt_tokens}, Total: {embedding_response.usage.total_tokens}"
+    )
+
+    # Print a sample of the embedding vector (first 5 dimensions)
+    print(
+        f"Embedding sample (first 5 dimensions): {embedding_response.data[0].embedding[:5]}"
+    )
+
+
+if __name__ == "__main__":
+    main()

instrumentation-genai/opentelemetry-instrumentation-openai-v2/examples/embeddings/requirements.txt

@@ -0,0 +1,6 @@
+openai~=1.57.3
+
+opentelemetry-sdk~=1.30.0
+opentelemetry-exporter-otlp-proto-grpc~=1.30.0
+opentelemetry-distro~=0.51b0
+opentelemetry-instrumentation-openai-v2~=2.1b0