Instructor

Instructor is a lightweight library that makes it easy to get structured data like JSON from LLMs.

In order to use OpenAI with Instructor, you need to set the OPENAI_API_KEY environment variable. You can get your API key from platform.openai.com/api-keys.

Tracing

It’s important to store traces of language model applications in a central location, both during development and in production. These traces can be useful for debugging, and as a dataset that will help you improve your application.

Weave will automatically capture traces for Instructor and OpenaAI. To start tracking, calling weave.init() and use the library as normal.

Track your own ops

Wrapping a function with @weave.op starts capturing inputs, outputs and app logic so you can debug how data flows through your app. You can deeply nest ops and build a tree of functions that you want to track. This also starts automatically versioning code as you experiment to capture ad-hoc details that haven't been committed to git.

Simply create a function decorated with @weave.op.

In the example below, we have the function extract_person which is the metric function wrapped with @weave.op. This helps us see how intermediate steps, such as OpenAI chat completion call.

Create a Model for easier experimentation

Organizing experimentation is difficult when there are many moving pieces. By using the Model class, you can capture and organize the experimental details of your app like your system prompt or the model you're using. This helps organize and compare different iterations of your app.

In addition to versioning code and capturing inputs/outputs, a Model captures structured parameters that control your application’s behavior, making it easy to find what parameters worked best. You can also use Weave a Model with serve, and Evaluations.

In the example below, you can experiment with PersonExtractor. Every time you change one of these, you'll get a new version of PersonExtractor.