Skip to main content

​
OpenAI Integration

This example demonstrates how to integrate Corvic AI with an OpenAI agent framework to analyze structured data from a parquet file containing video game sales information.

​
Use Case

In this tutorial, you’ll upload a parquet file containing data about video game sales and ask Corvic to provide a report.

​
Prerequisites

  1. Download the CSV Dataset: Obtain the video game sales data from Kaggle.
  2. Convert CSV to Parquet: Use Python to convert the CSV file to Parquet format:
import pandas as pd

df = pd.read_csv("vgsales.csv")
df.to_parquet("vgsales.parquet", index=False)
  1. Upload to Corvic: Follow the documentation here to create an agent using this parquet file.
  2. Deploy the Agent: Deploy the agent and obtain the MCP endpoint and access token.

​
Question Asked

Group all the data by name and find the top titles by global sales. Output the name and the total global sales in a tabular format.

​
Code Example

import mcp
from openai import OpenAI

# Configuration
MCP_ENDPOINT = "<<MCP_ENDPOINT>>"
CORVIC_API_TOKEN = "<<YOUR_CORVIC_API_TOKEN>>"
OPENAI_API_KEY = "<<YOUR_OPENAI_API_KEY>>"

headers = {
    "Authorization": f"Bearer {CORVIC_API_TOKEN}",
    "Content-Type": "application/json"
}

# Initialize OpenAI client
openai_client = OpenAI(api_key=OPENAI_API_KEY)

async def query_corvic_agent(question: str):
    """Query Corvic agent using MCP."""
    async with mcp.ClientSession(
        transport=mcp.SSEClientTransport(MCP_ENDPOINT, headers=headers)
    ) as session:
        await session.initialize()
        
        query_result = await session.call_tool(
            "query",
            arguments={"query_content": question}
        )
        
        return query_result.content[0].text if query_result.content else ""

# Query Corvic agent
question = "Group all the data by name and find the top titles by global sales. Output the name and the total global sales in a tabular format."
corvic_response = await query_corvic_agent(question)

# Use OpenAI to format the response
openai_response = openai_client.chat.completions.create(
    model="gpt-4",
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant. Format the data analysis results clearly."
        },
        {
            "role": "user",
            "content": f"Here is the analysis from Corvic:\n\n{corvic_response}\n\nPlease format this as a clear report."
        }
    ],
    tools=[{
        "type": "function",
        "function": {
            "name": "query_corvic",
            "description": "Query Corvic agent for data analysis",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string"}
                }
            }
        }
    }]
)

print(openai_response.choices[0].message.content)

​
Response

The Corvic agent will process the parquet data and return a report including the top-performing video game titles.
Top Performing Titles Screenshot

​
Notes

  • Ensure that the vgsales.parquet file is correctly formatted and uploaded to the Corvic platform.
  • Replace <<MCP_ENDPOINT>> and <<YOUR_CORVIC_API_TOKEN>> with your actual endpoint and token.
  • The agent is instructed to use tools exclusively for answering queries.

​
Resources