Add OpenAI example (#3006)

.pylintrc

@@ -7,7 +7,7 @@ extension-pkg-whitelist=cassandra
 
 # Add list of files or directories to be excluded. They should be base names, not
 # paths.
-ignore=CVS,gen,Dockerfile,docker-compose.yml,README.md,requirements.txt,docs
+ignore=CVS,gen,Dockerfile,docker-compose.yml,README.md,requirements.txt,docs,.venv
 
 # Add files or directories matching the regex patterns to be excluded. The
 # regex matches against base names, not paths.

CHANGELOG.md

@@ -15,7 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - `opentelemetry-instrumentation-sqlalchemy` Update unit tests to run with SQLALchemy 2
   ([#2976](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/2976))
-  - Add `opentelemetry-instrumentation-openai-v2` to `opentelemetry-bootstrap`
+- Add `opentelemetry-instrumentation-openai-v2` to `opentelemetry-bootstrap`
   ([#2996](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/2996))
   - `opentelemetry-instrumentation-sqlalchemy` Add sqlcomment to `db.statement` attribute
   ([#2937](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/2937))

instrumentation-genai/opentelemetry-instrumentation-openai-v2/CHANGELOG.md

@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Unreleased
 
+- Add example to `opentelemetry-instrumentation-openai-v2`
+  ([#3006](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3006))
 - Support for `AsyncOpenAI/AsyncCompletions` ([#2984](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/2984))
 
 ## Version 2.0b0 (2024-11-08)

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

@@ -6,17 +6,21 @@ OpenTelemetry OpenAI Instrumentation
 .. |pypi| image:: https://badge.fury.io/py/opentelemetry-instrumentation-openai-v2.svg
    :target: https://pypi.org/project/opentelemetry-instrumentation-openai-v2/
 
-Instrumentation with OpenAI that supports the OpenAI library and is
+This library allows tracing LLM requests and logging of messages made by the
-specified to trace_integration using 'OpenAI'.
+`OpenAI Python API library <https://pypi.org/project/openai/>`_.
 
 
 Installation
 ------------
 
+If your application is already instrumented with OpenTelemetry, add this
+package to your requirements.
 ::
 
     pip install opentelemetry-instrumentation-openai-v2
 
+If you don't have an OpenAI application, yet, try our `example <example>`_
+which only needs a valid OpenAI API key.
 
 References
 ----------

instrumentation-genai/opentelemetry-instrumentation-openai-v2/example/.env

@@ -0,0 +1,18 @@
+# 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
+
+OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318
+OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf
+OTEL_SERVICE_NAME=opentelemetry-python-openai
+
+# Change to 'false' to disable logging
+OTEL_PYTHON_LOGGING_AUTO_INSTRUMENTATION_ENABLED=true
+# Change to 'console' if your OTLP endpoint doesn't support logs
+OTEL_LOGS_EXPORTER=otlp_proto_http
+# Change to 'false' to hide prompt and completion content
+OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true

instrumentation-genai/opentelemetry-instrumentation-openai-v2/example/README.rst

@@ -0,0 +1,39 @@
+OpenTelemetry OpenAI Instrumentation Example
+============================================
+
+This is an example of how to instrument OpenAI calls with zero code changes,
+using `opentelemetry-instrument`.
+
+When `main.py <main.py>`_ is run, it exports traces and logs to an OTLP
+compatible endpoint. Traces include details such as the model used and the
+duration of the chat request. Logs capture the chat request and the generated
+response, providing a comprehensive view of the performance and behavior of
+your OpenAI requests.
+
+Setup
+-----
+
+Minimally, update the `.env <.env>`_ file with your "OPENAI_API_KEY". An
+OTLP compatible endpoint should be listening for traces and logs on
+http://localhost:4318. 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 a poem generated by OpenAI while traces and logs export to your
+configured observability tool.

instrumentation-genai/opentelemetry-instrumentation-openai-v2/example/main.py

@@ -0,0 +1,21 @@
+import os
+
+from openai import OpenAI
+
+
+def main():
+    client = OpenAI()
+    chat_completion = client.chat.completions.create(
+        model=os.getenv("CHAT_MODEL", "gpt-4o-mini"),
+        messages=[
+            {
+                "role": "user",
+                "content": "Write a short poem on OpenTelemetry.",
+            },
+        ],
+    )
+    print(chat_completion.choices[0].message.content)
+
+
+if __name__ == "__main__":
+    main()

instrumentation-genai/opentelemetry-instrumentation-openai-v2/example/requirements.txt

@@ -0,0 +1,6 @@
+openai~=1.54.4
+
+opentelemetry-sdk~=1.28.2
+opentelemetry-exporter-otlp-proto-http~=1.28.2
+opentelemetry-distro~=0.49b2
+opentelemetry-instrumentation-openai-v2~=2.0b0