ai

# AI/ML Engineering

Build production AI systems with modern patterns and tools.

## Quick Reference

### The 2026 AI Stack

| Layer               | Tool              | Purpose                          |
| ------------------- | ----------------- | -------------------------------- |
| Prompting           | DSPy              | Programmatic prompt optimization |
| Orchestration       | LangGraph         | Stateful multi-agent workflows   |
| RAG                 | LlamaIndex        | Document ingestion and retrieval |
| Vectors             | Qdrant / Pinecone | Embedding storage and search     |
| Evaluation          | RAGAS             | RAG quality metrics              |
| Experiment Tracking | MLflow / W&B      | Logging, versioning, comparison  |
| Serving             | BentoML / vLLM    | Model deployment                 |
| Protocol            | MCP               | Tool and context integration     |

### DSPy: Programmatic Prompting

**Manual prompts are dead.** DSPy treats prompts as optimizable code:

```python
import dspy

class QA(dspy.Signature):
    """Answer questions with short factoid answers."""
    question = dspy.InputField()
    answer = dspy.OutputField(desc="1-5 words")

# Create module
qa = dspy.Predict(QA)

# Use it
result = qa(question="What is the capital of France?")
print(result.answer)  # "Paris"
```

**Optimize with real data:**

```python
from dspy.teleprompt import BootstrapFewShot

optimizer = BootstrapFewShot(metric=exact_match)
optimized_qa = optimizer.compile(qa, trainset=train_data)
```

### RAG Architecture (Production)

```
Query → Rewrite → Hybrid Retrieval → Rerank → Generate → Cite
         │              │                │
         v              v                v
    Query expansion  Dense + BM25   Cross-encoder
```

**LlamaIndex + LangGraph Pattern:**

```python
from llama_index.core import VectorStoreIndex
from langgraph.graph import StateGraph

# Data layer (LlamaIndex)
index = VectorStoreIndex.from_documents(docs)
query_en