feat: add README and release please for anthropic instrumentor (#925)

Arize-ai · Aug 20, 2024 · e8b8973 · e8b8973
1 parent bb742d6
commit e8b8973
Show file tree

Hide file tree

Showing 3 changed files with 32 additions and 22 deletions.
diff --git a/README.md b/README.md
@@ -40,20 +40,23 @@ OpenInference provides a set of instrumentations for popular machine learning SD
 | [`openinference-instrumentation-litellm`](./python/instrumentation/openinference-instrumentation-litellm)         | OpenInference Instrumentation for liteLLM.     | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-litellm.svg)](https://pypi.python.org/pypi/openinference-instrumentation-litellm)         |
 | [`openinference-instrumentation-groq`](./python/instrumentation/openinference-instrumentation-groq)               | OpenInference Instrumentation for Groq.        | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-groq.svg)](https://pypi.python.org/pypi/openinference-instrumentation-groq)               |
 | [`openinference-instrumentation-instructor`](./python/instrumentation/openinference-instrumentation-instructor)   | OpenInference Instrumentation for Instructor.  | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-instructor.svg)](https://pypi.python.org/pypi/openinference-instrumentation-instructor)   |
+| [`openinference-instrumentation-anthropic`](./python/instrumentation/openinference-instrumentation-instructor)    | OpenInference Instrumentation for Anthropic.   | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-anthropic.svg)](https://pypi.python.org/pypi/openinference-instrumentation-anthropic)     |
+
 
 ### Examples
 
 | Name                                                                                           | Description                                                                                  | Complexity Level |
 |------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------|------------------|
 | [OpenAI SDK](python/instrumentation/openinference-instrumentation-openai/examples/)            | OpenAI Python SDK, including chat completions and embeddings                                 | Beginner         |
-| [MistralAI SDK](python/instrumentation/openinference-instrumentation-mistralai/examples/)      | MistraAI Python SDK                                                                          | Beginner         |
+| [MistralAI SDK](python/instrumentation/openinference-instrumentation-mistralai/examples/)      | MistralAI Python SDK                                                                         | Beginner         |
 | [VertexAI SDK](python/instrumentation/openinference-instrumentation-vertexai/examples/)        | VertexAI Python SDK                                                                          | Beginner         |
 | [LlamaIndex](python/instrumentation/openinference-instrumentation-llama-index/examples/)       | LlamaIndex query engines                                                                     | Beginner         |
 | [DSPy](python/instrumentation/openinference-instrumentation-dspy/examples/)                    | DSPy primitives and custom RAG modules                                                       | Beginner         |
 | [Boto3 Bedrock Client](python/instrumentation/openinference-instrumentation-bedrock/examples/) | Boto3 Bedrock client                                                                         | Beginner         |
 | [LangChain](python/instrumentation/openinference-instrumentation-langchain/examples/)          | LangChain primitives and simple chains                                                       | Beginner         |
 | [LiteLLM](python/instrumentation/openinference-instrumentation-litellm/)                       | A lightweight LiteLLM framework                                                              | Beginner         |
 | [Groq](python/instrumentation/openinference-instrumentation-groq/examples/)                    | Groq and AsyncGroq chat completions                                                          | Beginner         |
+| [Anthropic](python/instrumentation/openinference-instrumentation-anthropic/examples/)          | Anthropic Messages client                                                                    | Beginner         |
 | [LlamaIndex + Next.js Chatbot](python/examples/llama-index/)                                   | A fully functional chatbot using Next.js and a LlamaIndex FastAPI backend                    | Intermediate     |
 | [LangServe](python/examples/langserve/)                                                        | A LangChain application deployed with LangServe using custom metadata on a per-request basis | Intermediate     |
 | [DSPy](python/examples/dspy-rag-fastapi/)                                                      | A DSPy RAG application using FastAPI, Weaviate, and Cohere                                   | Intermediate     |

diff --git a/python/instrumentation/openinference-instrumentation-anthropic/README.md b/python/instrumentation/openinference-instrumentation-anthropic/README.md
@@ -1,24 +1,28 @@
-# OpenInference Groq Instrumentation
+# OpenInference Anthropic Instrumentation
 
-Python autoinstrumentation library for the [Groq](https://wow.groq.com/why-groq/) package
+Python autoinstrumentation library for the [Anthropic](https://www.anthropic.com/api) package
 
-This package implements OpenInference tracing for both the Groq and AsyncGroq clients.
+This package implements the following Anthropic clients:
+- `Messages`
+- `Completions`
+- `AsyncMessages`
+- `AsyncCompletions`
 
 These traces are fully OpenTelemetry compatible and can be sent to an OpenTelemetry collector for viewing, such as [Arize `phoenix`](https://github.com/Arize-ai/phoenix).
 
 
 ## Installation
 
 ```shell
-pip install openinference-instrumentation-groq
+pip install openinference-instrumentation-anthropic
 ```
 
 ## Quickstart
 
 Through your *terminal*, install required packages.
 
 ```shell
-pip install openinference-instrumentation-groq groq arize-phoenix opentelemetry-sdk opentelemetry-exporter-otlp
+pip install openinference-instrumentation-anthropic anthropic arize-phoenix opentelemetry-sdk opentelemetry-exporter-otlp
 ```
 
 You can start Phoenix with the following terminal command:
@@ -30,41 +34,40 @@ By default, Phoenix listens on `http://localhost:6006`. You can visit the app vi
 
 Try the following code in a *Python file*.
 
-1. Set up `GroqInstrumentor` to trace your application and sends the traces to Phoenix. 
-2. Then, set your Groq API key as an environment variable. 
-3. Lastly, create a Groq client, make a request, then go see your results in Phoenix at `http://localhost:6006`!
+1. Set up `AnthropicInstrumentor` to trace your application and sends the traces to Phoenix. 
+2. Then, set your Anthropic API key as an environment variable. 
+3. Lastly, create a Anthropic client, make a request, then go see your results in Phoenix at `http://localhost:6006`!
 
 ```python
 import os
-from groq import Groq
-from openinference.instrumentation.groq import GroqInstrumentor
+from anthropic import Anthropic
+from openinference.instrumentation.anthropic import AnthropicInstrumentor
 from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
 from opentelemetry.sdk import trace as trace_sdk
 from opentelemetry.sdk.trace.export import SimpleSpanProcessor
 
-# Configure GroqInstrumentor with Phoenix endpoint
+# Configure AnthropicInstrumentor with Phoenix endpoint
 endpoint = "http://127.0.0.1:6006/v1/traces"
 tracer_provider = trace_sdk.TracerProvider()
 tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
 
-GroqInstrumentor().instrument(tracer_provider=tracer_provider)
+AnthropicInstrumentor().instrument(tracer_provider=tracer_provider)
 
-os.environ["GROQ_API_KEY"] = "YOUR_KEY_HERE"
+os.environ["ANTHROPIC_API_KEY"] = "YOUR_KEY_HERE"
 
-client = Groq()
+client = Anthropic()
 
-chat_completion = client.chat.completions.create(
+response = client.messages.create(
+    max_tokens=1024,
     messages=[
         {
             "role": "user",
-            "content": "Explain the importance of low latency LLMs",
+            "content": "Tell me about the history of Iceland!",
         }
     ],
-    model="llama3-8b-8192",
+    model="claude-3-opus-20240229",
 )
-
-if __name__ == "__main__":
-    print(chat_completion.choices[0].message.content)
+print(response)
 ```
 
-Now, on the Phoenix UI on your browser, you should see the traces from your Groq application. Click on a trace, then the "Attributes" tab will provide you with in-depth information regarding execution!
+Now, on the Phoenix UI on your browser, you should see the traces from your Anthropic application. Click on a trace, then the "Attributes" tab will provide you with in-depth information regarding execution!
diff --git a/release-please-config.json b/release-please-config.json
@@ -62,6 +62,10 @@
         "python/instrumentation/openinference-instrumentation-instructor": {
             "package-name": "python-openinference-instrumentation-instructor",
             "release-type": "python"
+        },
+        "python/instrumentation/openinference-instrumentation-anthropic": {
+            "package-name": "python-openinference-instrumentation-anthropic",
+            "release-type": "python"
         }
     }
 }