Skip to content

Orchestra-Research/AI-Research-SKILLs / 16-prompt-engineering/instructor

instructor

Verified

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

FileKindSize
SKILL.mdskill md16.4 KB
references/examples.mdmarkdown2.3 KB
references/providers.mdmarkdown1.3 KB
references/validation.mdmarkdown14.9 KB

references/providers.md

View on GitHub
# Provider Configuration

Guide to using Instructor with different LLM providers.

## Anthropic Claude

```python
import instructor
from anthropic import Anthropic

# Basic setup
client = instructor.from_anthropic(Anthropic())

# With API key
client = instructor.from_anthropic(
    Anthropic(api_key="your-api-key")
)

# Recommended mode
client = instructor.from_anthropic(
    Anthropic(),
    mode=instructor.Mode.ANTHROPIC_TOOLS
)

# Usage
result = client.messages.create(
    model="claude-sonnet-4-5-20250929",
    max_tokens=1024,
    messages=[{"role": "user", "content": "..."}],
    response_model=YourModel
)
```

## OpenAI

```python
from openai import OpenAI

client = instructor.from_openai(OpenAI())

result = client.chat.completions.create(
    model="gpt-4o-mini",
    response_model=YourModel,
    messages=[{"role": "user", "content": "..."}]
)
```

## Local Models (Ollama)

```python
client = instructor.from_openai(
    OpenAI(
        base_url="http://localhost:11434/v1",
        api_key="ollama"
    ),
    mode=instructor.Mode.JSON
)

result = client.chat.completions.create(
    model="llama3.1",
    response_model=YourModel,
    messages=[...]
)
```

## Modes

- `Mode.ANTHROPIC_TOOLS`: Recommended for Claude
- `Mode.TOOLS`: OpenAI function calling
- `Mode.JSON`: Fallback for unsupported providers
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall