deploy oai sdk integration

Author: james-pplx

perplexity-openai-agents-sdk/README.md

@@ -0,0 +1,65 @@
+# Integrating Perplexity’s Sonar API with the OpenAI SDK
+
+This guide demonstrates how to integrate Perplexity’s Sonar API into the OpenAI SDK using a custom asynchronous client. The example shows how to create an agent that leverages the custom LLM provider, set up function tools, and run a sample query. This is ideal if you want to extend or customize your integration of the Sonar API for various applications.
+
+## Table of Contents
+	•	Overview
+	•	Prerequisites
+	•	Environment Setup
+	•	Usage
+	•	Code Walkthrough
+	•	Running the Example
+	•	References
+
+## Overview
+
+This example involves:
+	•	Creating an asynchronous OpenAI client configured with Perplexity’s Sonar API.
+	•	Creating a custom model that uses this client.
+	•	Configuring an agent with custom instructions and a function tool to fetch weather.
+	•	Running a sample query to demonstrate integration.
+
+## Prerequisites
+	•	Python 3.7 or later.
+	•	Required Python packages:
+	•	openai
+	•	nest_asyncio
+	•	The custom agents package (ensure this is installed or available in your environment).
+
+Install dependencies via pip if needed:
+
+```bash
+pip install openai nest_asyncio
+```
+
+## Environment Setup
+
+Set the following environment variables or update the code with the appropriate values:
+	•	`EXAMPLE_BASE_URL`: The base URL of the Perplexity API (default: https://api.perplexity.ai).
+	•	`EXAMPLE_API_KEY`: Your API key for accessing the Sonar API.
+	•	`EXAMPLE_MODEL_NAME`: The model name, defaulting to `sonar-pro`.
+
+## Usage
+
+Simply run the script to create the agent and test a sample query asking for the weather in Tokyo. The agent will execute the query using the custom Sonar API-powered model and a tool to fetch weather data.
+
+
+## Running the Example
+	1.	Set up Environment Variables:
+Ensure `EXAMPLE_BASE_URL`, `EXAMPLE_API_KEY`, and `EXAMPLE_MODEL_NAME` are set, either in your shell or within the code.
+	2.	Install Dependencies:
+Make sure you have installed the required packages (`openai`, `nest_asyncio`, and `agents`).
+	3.	Execute the Script:
+Run the script using Python:
+
+```bash
+python your_script_name.py
+```
+
+## Conclusion
+
+This example provides a hands-on guide for integrating Perplexity’s Sonar API with the OpenAI SDK. The approach involves creating a custom asynchronous client, setting up a model with our API, and using an agent to process queries with additional function tools. Customize this code as needed to fit your application’s requirements.
+
+References
+	•	[Perplexity Sonar API Documentation](https://docs.perplexity.ai/home)
+	•	[OpenAI Agents SDK Documentation](https://github.com/openai/openai-agents-python/blob/main/examples/model_providers/custom_example_agent.py)

perplexity-openai-agents-sdk/pplx_openai.py

@@ -0,0 +1,92 @@
+# Import necessary standard libraries
+import asyncio  # For running asynchronous code
+import os       # To access environment variables
+
+# Import AsyncOpenAI for creating an async client
+from openai import AsyncOpenAI
+
+# Import custom classes and functions from the agents package.
+# These handle agent creation, model interfacing, running agents, and more.
+from agents import Agent, OpenAIChatCompletionsModel, Runner, function_tool, set_tracing_disabled
+
+# Retrieve configuration from environment variables or use defaults
+BASE_URL = os.getenv("EXAMPLE_BASE_URL") or "https://api.perplexity.ai"
+API_KEY = os.getenv("EXAMPLE_API_KEY") 
+MODEL_NAME = os.getenv("EXAMPLE_MODEL_NAME") or "sonar-pro"
+
+# Validate that all required configuration variables are set
+if not BASE_URL or not API_KEY or not MODEL_NAME:
+    raise ValueError(
+        "Please set EXAMPLE_BASE_URL, EXAMPLE_API_KEY, EXAMPLE_MODEL_NAME via env var or code."
+    )
+
+"""
+This example illustrates how to use a custom provider with a specific agent:
+1. We create an asynchronous OpenAI client configured to interact with the Perplexity Sonar API.
+2. We define a custom model using this client.
+3. We set up an Agent with our custom model and attach function tools.
+Note: Tracing is disabled in this example. If you have an OpenAI platform API key,
+you can enable tracing by setting the environment variable OPENAI_API_KEY or using set_tracing_export_api_key().
+"""
+
+# Initialize the custom OpenAI async client with the specified BASE_URL and API_KEY.
+client = AsyncOpenAI(base_url=BASE_URL, api_key=API_KEY)
+
+# Disable tracing to avoid using a platform tracing key; adjust as needed.
+set_tracing_disabled(disabled=True)
+
+# (Alternate approach example, commented out)
+# PROVIDER = OpenAIProvider(openai_client=client)
+# agent = Agent(..., model="some-custom-model")
+# Runner.run(agent, ..., run_config=RunConfig(model_provider=PROVIDER))
+
+# Define a function tool that the agent can call.
+# The decorator registers this function as a tool in the agents framework.
+@function_tool
+def get_weather(city: str):
+    """
+    Simulate fetching weather data for a given city.
+    
+    Args:
+        city (str): The name of the city to retrieve weather for.
+        
+    Returns:
+        str: A message with weather information.
+    """
+    print(f"[debug] getting weather for {city}")
+    return f"The weather in {city} is sunny."
+
+# Import nest_asyncio to support nested event loops (helpful in interactive environments like Jupyter)
+import nest_asyncio
+
+# Apply the nest_asyncio patch to enable running asyncio.run() even if an event loop is already running.
+nest_asyncio.apply()
+
+async def main():
+    """
+    Main asynchronous function to set up and run the agent.
+    
+    This function creates an Agent with a custom model and function tools,
+    then runs a query to get the weather in Tokyo.
+    """
+    # Create an Agent instance with:
+    # - A name ("Assistant")
+    # - Custom instructions ("Be precise and concise.")
+    # - A model built from OpenAIChatCompletionsModel using our client and model name.
+    # - A list of tools; here, only get_weather is provided.
+    agent = Agent(
+        name="Assistant",
+        instructions="Be precise and concise.",
+        model=OpenAIChatCompletionsModel(model=MODEL_NAME, openai_client=client),
+        tools=[get_weather],
+    )
+
+    # Execute the agent with the sample query.
+    result = await Runner.run(agent, "What's the weather in Tokyo?")
+    
+    # Print the final output from the agent.
+    print(result.final_output)
+
+# Standard boilerplate to run the async main() function.
+if __name__ == "__main__":
+    asyncio.run(main())