菜单
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/majiayu000/claude-skill-registry --skill litellm命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据，按主题分组汇总"我都做了什么"，并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
| name | litellm |
| description | When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns. |
Unified Python interface for calling 100+ LLM APIs using consistent OpenAI format. Provides standardized exception handling, retry/fallback logic, and cost tracking across multiple providers.
Use this skill when:
LiteLLM supports 100+ providers through consistent OpenAI-style API:
completion() function for all providers# Using pip
pip install litellm
# Using uv
uv add litellm
All llamafile models MUST use the llamafile/ prefix for routing:
model = "llamafile/mistralai/mistral-7b-instruct-v0.2"
model = "llamafile/gemma-3-3b"
The api_base MUST point to llamafile's OpenAI-compatible endpoint:
api_base = "http://localhost:8080/v1"
Critical Requirements:
/v1 suffix/chat/completions (LiteLLM adds these automatically)import os
os.environ["LLAMAFILE_API_BASE"] = "http://localhost:8080/v1"
import litellm
response = litellm.completion(
model="llamafile/mistralai/mistral-7b-instruct-v0.2",
messages=[{"role": "user", "content": "Summarize this diff"}],
api_base="http://localhost:8080/v1",
temperature=0.2,
max_tokens=80,
)
print(response.choices[0].message.content)
from litellm import acompletion
import asyncio
async def generate_message():
response = await acompletion(
model="llamafile/gemma-3-3b",
messages=[{"role": "user", "content": "Write a commit message"}],
api_base="http://localhost:8080/v1",
temperature=0.3,
max_tokens=200,
)
return response.choices[0].message.content
result = asyncio.run(generate_message())
print(result)
from litellm import acompletion
import asyncio
async def stream_response():
response = await acompletion(
model="llamafile/gemma-3-3b",
messages=[{"role": "user", "content": "Hello, how are you?"}],
api_base="http://localhost:8080/v1",
stream=True,
)
async for chunk in response:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
print()
asyncio.run(stream_response())
from litellm import embedding
import os
os.environ["LLAMAFILE_API_BASE"] = "http://localhost:8080/v1"
response = embedding(
model="llamafile/sentence-transformers/all-MiniLM-L6-v2",
input=["Hello world"],
)
print(response)
All exceptions can be imported directly from litellm:
from litellm import (
BadRequestError, # 400 errors
AuthenticationError, # 401 errors
NotFoundError, # 404 errors
Timeout, # 408 errors (alias: openai.APITimeoutError)
RateLimitError, # 429 errors
APIConnectionError, # 500 errors / connection issues (default)
ServiceUnavailableError, # 503 errors
)
| Status Code | Exception Type | Inherits from | Description |
|---|---|---|---|
| 400 | BadRequestError | openai.BadRequestError | Invalid request |
| 400 | ContextWindowExceededError | litellm.BadRequestError | Token limit exceeded |
| 400 | ContentPolicyViolationError | litellm.BadRequestError | Content policy violation |
| 401 | AuthenticationError | openai.AuthenticationError | Auth failure |
| 403 | PermissionDeniedError | openai.PermissionDeniedError | Permission denied |
| 404 | NotFoundError | openai.NotFoundError | Invalid model/endpoint |
| 408 | Timeout | openai.APITimeoutError | Request timeout |
| 429 | RateLimitError | openai.RateLimitError | Rate limited |
| 500 | APIConnectionError | openai.APIConnectionError | Default for unmapped errors |
| 500 | APIError | openai.APIError | Generic 500 error |
| 503 | ServiceUnavailableError | openai.APIStatusError | Service unavailable |
| >=500 | InternalServerError | openai.InternalServerError | Unmapped 500+ errors |
All LiteLLM exceptions include:
status_code: HTTP status codemessage: Error messagellm_provider: Provider that raised the exceptionimport litellm
import openai
try:
response = litellm.completion(
model="llamafile/gemma-3-3b",
messages=[{"role": "user", "content": "Hello"}],
api_base="http://localhost:8080/v1",
timeout=30.0,
)
except openai.APITimeoutError as e:
# LiteLLM exceptions inherit from OpenAI types
print(f"Timeout: {e}")
except litellm.APIConnectionError as e:
print(f"Connection failed: {e.message}")
print(f"Provider: {e.llm_provider}")
from litellm.exceptions import BadRequestError, AuthenticationError, APIError
try:
response = litellm.completion(
model="llamafile/gemma-3-3b",
messages=[{"role": "user", "content": "Hello"}],
api_base="http://localhost:8080/v1",
)
except AuthenticationError as e:
print(f"Authentication failed: {e}")
except BadRequestError as e:
print(f"Bad request: {e}")
except APIError as e:
print(f"API error: {e}")
import litellm
try:
response = litellm.completion(
model="llamafile/gemma-3-3b",
messages=[{"role": "user", "content": "Hello"}],
api_base="http://localhost:8080/v1",
)
except Exception as e:
if hasattr(e, 'status_code'):
should_retry = litellm._should_retry(e.status_code)
print(f"Should retry: {should_retry}")
from litellm import completion
response = completion(
model="llamafile/gemma-3-3b",
messages=[{"role": "user", "content": "Hello"}],
api_base="http://localhost:8080/v1",
num_retries=3, # Retry 3 times on failure
timeout=30.0, # 30 second timeout
)
For proxy deployments, use config.yaml:
model_list:
- model_name: commit-polish-model
litellm_params:
model: llamafile/gemma-3-3b # add llamafile/ prefix
api_base: http://localhost:8080/v1 # add api base for OpenAI compatible provider
import litellm
from litellm import APIConnectionError
def verify_llamafile_connection(api_base: str = "http://localhost:8080/v1") -> bool:
"""Check if llamafile server is running."""
try:
litellm.completion(
model="llamafile/test",
messages=[{"role": "user", "content": "test"}],
api_base=api_base,
max_tokens=1,
)
return True
except APIConnectionError:
return False
import litellm
from litellm import acompletion, APIConnectionError
import asyncio
class AIService:
"""LiteLLM wrapper with llamafile routing."""
def __init__(self, model: str, api_base: str, temperature: float = 0.3, max_tokens: int = 200):
self.model = model
self.api_base = api_base
self.temperature = temperature
self.max_tokens = max_tokens
async def generate_commit_message(self, diff: str, system_prompt: str) -> str:
"""Generate a commit message using the LLM."""
try:
response = await acompletion(
model=self.model,
messages=[
{"role": "system", "content": system_prompt},
{"role": "user", "content": f"Generate a commit message for this diff:\n\n{diff}"},
],
api_base=self.api_base,
temperature=self.temperature,
max_tokens=self.max_tokens,
)
return response.choices[0].message.content.strip()
except APIConnectionError as e:
raise RuntimeError(f"Failed to connect to llamafile server at {self.api_base}: {e.message}")
llamafile/ prefix: Without prefix, LiteLLM won't route to OpenAI-compatible endpoint/v1 suffix: API base must end with /v1http://localhost:8080/v1/chat/completions - LiteLLM adds the endpoint path automatically# ~/.config/commit-polish/config.toml
[ai]
model = "llamafile/gemma-3-3b" # MUST have llamafile/ prefix
temperature = 0.3
max_tokens = 200
export LLAMAFILE_API_BASE="http://localhost:8080/v1"
export LITELLM_LOG="INFO" # Enable LiteLLM debug logging
For comprehensive documentation on related tools:
Skill(command: "llamafile") for llamafile server setup, model management, and local LLM deployment patternsSkill(command: "uv") for Python project management, dependency handling, and virtual environment workflows