> ## Documentation Index
> Fetch the complete documentation index at: https://portkey-docs-add-third-party-integration-issues-fixes.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Instructor

> With Portkey, you can confidently take your Instructor pipelines to production and get complete observability over all of your calls + make them reliable - all with a 2 LOC change!

**Instructor** is a framework for extracting structured outputs from LLMs, available in [Python](https://python.useinstructor.com/) & [JS](https://js.useinstructor.com/).

## Integrating Portkey with Instructor

<Tabs>
  <Tab title="Instructor Python - OpenAI">
    ```python theme={null}
    import instructor
    from pydantic import BaseModel
    from openai import OpenAI
    from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

    portkey = OpenAI(
        base_url=PORTKEY_GATEWAY_URL,
        default_headers=createHeaders(
            virtual_key="OPENAI_VIRTUAL_KEY",
            api_key="PORTKEY_API_KEY"
        )
    )

    class User(BaseModel):
        name: str
        age: int

    client = instructor.from_openai(portkey)

    user_info = client.chat.completions.create(
        model="gpt-4-turbo",
        max_tokens=1024,
        response_model=User,
        messages=[{"role": "user", "content": "John Doe is 30 years old."}],
    )

    print(user_info.name)
    print(user_info.age)
    ```
  </Tab>

  <Tab title="Instructor JS - OpenAI">
    ```python theme={null}
    import Instructor from "@instructor-ai/instructor";
    import OpenAI from "openai";
    import { z } from "zod";
    import { PORTKEY_GATEWAY_URL, createHeaders } from "portkey-ai";

    const portkey = new OpenAI({
      baseURL: PORTKEY_GATEWAY_URL,
      defaultHeaders: createHeaders({
        apiKey: "PORTKEY_API_KEY",
        virtualKey: "OPENAI_API_KEY",
      }),
    });

    const client = Instructor({
      client: portkey,
      mode: "TOOLS",
    });

    const UserSchema = z.object({
      age: z.number().describe("The age of the user"),
      name: z.string(),
    });

    const user = await client.chat.completions.create({
      messages: [{ role: "user", content: "Jason Liu is 30 years old" }],
      model: "claude-3-sonnet-20240229",
      //  model: "gpt-4",
      max_tokens: 512,
      response_model: {
        schema: UserSchema,
        name: "User",
      },
    });

    console.log(user);
    ```
  </Tab>
</Tabs>

## Caching Your Requests

Let's now bring down the cost of running your Instructor pipeline with Portkey caching. You can just create a Config object where you define your cache setting:

```py theme={null}
{
  "cache": {
    "mode": "simple"
  }
}
```

You can write it raw, or use Portkey's Config builder and get a corresponding `config id`. Then, just pass it while instantiating your OpenAI client:

<Tabs>
  <Tab title="Instructor Python - OpenAI">
    ```python theme={null}
    import instructor
    from pydantic import BaseModel
    from openai import OpenAI
    from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

    cache_config = {
      "cache": {
        "mode": "simple"
      }
    }

    portkey = OpenAI(
        base_url=PORTKEY_GATEWAY_URL,
        default_headers=createHeaders(
            virtual_key="OPENAI_VIRTUAL_KEY",
            api_key="PORTKEY_API_KEY",
            config=cache_config # Or pass your Config ID saved from Portkey app
        )
    )

    class User(BaseModel):
        name: str
        age: int

    client = instructor.from_openai(portkey)

    user_info = client.chat.completions.create(
        model="gpt-4-turbo",
        max_tokens=1024,
        response_model=User,
        messages=[{"role": "user", "content": "John Doe is 30 years old."}],
    )

    print(user_info.name)
    print(user_info.age)
    ```
  </Tab>

  <Tab title="Instructor JS - OpenAI">
    ```python theme={null}
    import Instructor from "@instructor-ai/instructor";
    import OpenAI from "openai";
    import { z } from "zod";
    import { PORTKEY_GATEWAY_URL, createHeaders } from "portkey-ai";

    const cache_config = {
      "cache": {
        "mode": "simple"
      }
    }

    const portkey = new OpenAI({
      baseURL: PORTKEY_GATEWAY_URL,
      defaultHeaders: createHeaders({
        apiKey: "PORTKEY_API_KEY",
        virtualKey: "OPENAI_API_KEY",
        config: cache_config // Or pass your Config ID saved from Portkey app
      }),
    });

    const client = Instructor({
      client: portkey,
      mode: "TOOLS",
    });

    const UserSchema = z.object({
      age: z.number().describe("The age of the user"),
      name: z.string(),
    });

    const user = await client.chat.completions.create({
      messages: [{ role: "user", content: "Jason Liu is 30 years old" }],
      model: "claude-3-sonnet-20240229",
      //  model: "gpt-4",
      max_tokens: 512,
      response_model: {
        schema: UserSchema,
        name: "User",
      },
    });

    console.log(user);
    ```
  </Tab>
</Tabs>

Similarly, you can add [Fallback](/product/ai-gateway/fallbacks), [Loadbalancing](/product/ai-gateway/load-balancing), [Timeout](/product/ai-gateway/request-timeouts), or [Retry](/product/ai-gateway/automatic-retries) settings to your Configs and make your Instructor requests robust & reliable.