732c66b0f3
The skills directory was getting disorganized — mlops alone had 40 skills in a flat list, and 12 categories were singletons with just one skill each. Code change: - prompt_builder.py: Support sub-categories in skill scanner. skills/mlops/training/axolotl/SKILL.md now shows as category 'mlops/training' instead of just 'mlops'. Backwards-compatible with existing flat structure. Split mlops (40 skills) into 7 sub-categories: - mlops/training (12): accelerate, axolotl, flash-attention, grpo-rl-training, peft, pytorch-fsdp, pytorch-lightning, simpo, slime, torchtitan, trl-fine-tuning, unsloth - mlops/inference (8): gguf, guidance, instructor, llama-cpp, obliteratus, outlines, tensorrt-llm, vllm - mlops/models (6): audiocraft, clip, llava, segment-anything, stable-diffusion, whisper - mlops/vector-databases (4): chroma, faiss, pinecone, qdrant - mlops/evaluation (5): huggingface-tokenizers, lm-evaluation-harness, nemo-curator, saelens, weights-and-biases - mlops/cloud (2): lambda-labs, modal - mlops/research (1): dspy Merged singleton categories: - gifs → media (gif-search joins youtube-content) - music-creation → media (heartmula, songsee) - diagramming → creative (excalidraw joins ascii-art) - ocr-and-documents → productivity - domain → research (domain-intel) - feeds → research (blogwatcher) - market-data → research (polymarket) Fixed misplaced skills: - mlops/code-review → software-development (not ML-specific) - mlops/ml-paper-writing → research (academic writing) Added DESCRIPTION.md files for all new/updated categories.
2.3 KiB
2.3 KiB
Real-World Examples
Practical examples of using Instructor for structured data extraction.
Data Extraction
class CompanyInfo(BaseModel):
name: str
founded: int
industry: str
employees: int
text = "Apple was founded in 1976 in the technology industry with 164,000 employees."
company = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{"role": "user", "content": f"Extract: {text}"}],
response_model=CompanyInfo
)
Classification
class Sentiment(str, Enum):
POSITIVE = "positive"
NEGATIVE = "negative"
NEUTRAL = "neutral"
class Review(BaseModel):
sentiment: Sentiment
confidence: float = Field(ge=0.0, le=1.0)
review = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{"role": "user", "content": "This product is amazing!"}],
response_model=Review
)
Multi-Entity Extraction
class Person(BaseModel):
name: str
role: str
class Entities(BaseModel):
people: list[Person]
organizations: list[str]
locations: list[str]
entities = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{"role": "user", "content": "Tim Cook, CEO of Apple, spoke in Cupertino..."}],
response_model=Entities
)
Structured Analysis
class Analysis(BaseModel):
summary: str
key_points: list[str]
sentiment: Sentiment
actionable_items: list[str]
analysis = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{"role": "user", "content": "Analyze: [long text]"}],
response_model=Analysis
)
Batch Processing
texts = ["text1", "text2", "text3"]
results = [
client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{"role": "user", "content": text}],
response_model=YourModel
)
for text in texts
]
Streaming
for partial in client.messages.create_partial(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{"role": "user", "content": "Generate report..."}],
response_model=Report
):
print(f"Progress: {partial.title}")
# Update UI in real-time