本地LLM提示工程2026：思维链与少样本

# Prompt with CoT
prompt = """
You will answer a question by thinking step-by-step.
Let me think about this:

Question: Why do local LLMs require more explicit prompting than cloud APIs?

Thinking:
1. First, consider the differences in model size...
2. Then, think about training data and fine-tuning...
3. Finally, consider the architecture and inference optimization...

Answer:
"""

# This guides the model to reason through the problem

# Bad: ambiguous output
prompt = "Summarize this text"

# Good: explicit format
prompt = """
Summarize the text in EXACTLY 3 bullet points.
Format as a JSON list:
{
  "summary": [
    "- Point 1",
    "- Point 2",
    "- Point 3"
  ]
}
"""

# Ollama (Modelfile)
FROM llama3.1:8b
SYSTEM """You are a Python expert with 10 years experience. Answer only Python questions. Provide code examples. Use type hints."""
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER repeat_penalty 1.1

# Ollama (API / OpenAI SDK)
response = client.chat.completions.create(
  model="llama3.1:8b",
  messages=[
    {"role": "system", "content": "You are a Python expert..."},
    {"role": "user", "content": "Write a FastAPI endpoint"}
  ],
  temperature=0.7
)

# LM Studio (GUI)
# Settings → System Prompt field (paste your prompt)
# Or via API at localhost:1234 — identical format to Ollama

# llama.cpp (CLI)
./main -m llama-3.1-8b.gguf \
  --system-prompt "You are a Python expert..." \
  --temp 0.7 --top-p 0.9 --repeat-penalty 1.1 \
  -p "Write a FastAPI endpoint"

# Few-shot prompt
prompt = """
Classify sentiment. Examples:

"I love this product!" → positive
"Worst experience ever" → negative
"It's okay, nothing special" → neutral

Now classify: "This is amazing!"
Answer: """

# Model learns format and style from examples