mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
08a4c72692
* run azure testing on ci/cd * update docs on azure batches endpoints * add input azure.jsonl * refactor - use separate file for batches endpoints * fixes for passing custom llm provider to /batch endpoints * pass custom llm provider to files endpoints * update azure batches doc * add info for azure batches api * update batches endpoints * use simple helper for raising proxy exception * update config.yml * fix imports * add type hints to get_litellm_params * update get_litellm_params * update get_litellm_params * update get slp * QOL - stop double logging a create batch operations on custom loggers * re use slp from og event * _create_standard_logging_object_for_completed_batch * fix linting errors * reduce num changes in PR * update BATCH_STATUS_POLL_MAX_ATTEMPTS
97 lines
2.3 KiB
Python
97 lines
2.3 KiB
Python
ROUTER_MAX_FALLBACKS = 5
|
|
DEFAULT_BATCH_SIZE = 512
|
|
DEFAULT_FLUSH_INTERVAL_SECONDS = 5
|
|
DEFAULT_MAX_RETRIES = 2
|
|
DEFAULT_REPLICATE_POLLING_RETRIES = 5
|
|
DEFAULT_REPLICATE_POLLING_DELAY_SECONDS = 1
|
|
DEFAULT_IMAGE_TOKEN_COUNT = 250
|
|
DEFAULT_IMAGE_WIDTH = 300
|
|
DEFAULT_IMAGE_HEIGHT = 300
|
|
LITELLM_CHAT_PROVIDERS = [
|
|
"openai",
|
|
"openai_like",
|
|
"xai",
|
|
"custom_openai",
|
|
"text-completion-openai",
|
|
"cohere",
|
|
"cohere_chat",
|
|
"clarifai",
|
|
"anthropic",
|
|
"anthropic_text",
|
|
"replicate",
|
|
"huggingface",
|
|
"together_ai",
|
|
"openrouter",
|
|
"vertex_ai",
|
|
"vertex_ai_beta",
|
|
"gemini",
|
|
"ai21",
|
|
"baseten",
|
|
"azure",
|
|
"azure_text",
|
|
"azure_ai",
|
|
"sagemaker",
|
|
"sagemaker_chat",
|
|
"bedrock",
|
|
"vllm",
|
|
"nlp_cloud",
|
|
"petals",
|
|
"oobabooga",
|
|
"ollama",
|
|
"ollama_chat",
|
|
"deepinfra",
|
|
"perplexity",
|
|
"mistral",
|
|
"groq",
|
|
"nvidia_nim",
|
|
"cerebras",
|
|
"ai21_chat",
|
|
"volcengine",
|
|
"codestral",
|
|
"text-completion-codestral",
|
|
"deepseek",
|
|
"sambanova",
|
|
"maritalk",
|
|
"cloudflare",
|
|
"fireworks_ai",
|
|
"friendliai",
|
|
"watsonx",
|
|
"watsonx_text",
|
|
"triton",
|
|
"predibase",
|
|
"databricks",
|
|
"empower",
|
|
"github",
|
|
"custom",
|
|
"litellm_proxy",
|
|
"hosted_vllm",
|
|
"lm_studio",
|
|
"galadriel",
|
|
]
|
|
|
|
RESPONSE_FORMAT_TOOL_NAME = "json_tool_call" # default tool name used when converting response format to tool call
|
|
|
|
########################### Logging Callback Constants ###########################
|
|
AZURE_STORAGE_MSFT_VERSION = "2019-07-07"
|
|
|
|
########################### LiteLLM Proxy Specific Constants ###########################
|
|
########################################################################################
|
|
MAX_SPENDLOG_ROWS_TO_QUERY = (
|
|
1_000_000 # if spendLogs has more than 1M rows, do not query the DB
|
|
)
|
|
# makes it clear this is a rate limit error for a litellm virtual key
|
|
RATE_LIMIT_ERROR_MESSAGE_FOR_VIRTUAL_KEY = "LiteLLM Virtual Key user_api_key_hash"
|
|
|
|
# pass through route constansts
|
|
BEDROCK_AGENT_RUNTIME_PASS_THROUGH_ROUTES = [
|
|
"agents/",
|
|
"knowledgebases/",
|
|
"flows/",
|
|
"retrieveAndGenerate/",
|
|
"rerank/",
|
|
"generateQuery/",
|
|
"optimize-prompt/",
|
|
]
|
|
|
|
BATCH_STATUS_POLL_INTERVAL_SECONDS = 3600 # 1 hour
|
|
BATCH_STATUS_POLL_MAX_ATTEMPTS = 24 # for 24 hours
|