Liking cljdoc? Tell your friends :D
litellm.config
Configuration registry for provider/model switching
Configuration registry for provider/model switching
litellm.core
Core API for LiteLLM - Direct provider calls with model names as-is
Core API for LiteLLM - Direct provider calls with model names as-is
- anthropic-completion
- calculate-cost
- chat
- completion
- estimate-request-tokens
- estimate-tokens
- extract-content
- extract-message
- extract-usage
- gemini-completion
- list-providers
- mistral-completion
- ollama-completion
- openai-completion
- openrouter-completion
- provider-available?
- provider-info
- supports-function-calling?
- supports-streaming?
- validate-request
- with-error-handling
litellm.errors
Comprehensive error handling for LiteLLM-clj
This namespace provides:
- Namespaced error types for clear categorization
- Rich error data structures with context
- Error predicates for pattern matching
- Retry and recoverability analysis
Comprehensive error handling for LiteLLM-clj This namespace provides: - Namespaced error types for clear categorization - Rich error data structures with context - Error predicates for pattern matching - Retry and recoverability analysis
- all-error-types
- authentication-error
- authentication-error?
- authorization-error
- chunk->exception
- client-error?
- client-errors
- connection-error
- content-filter
- error-chunk?
- error-details
- error-summary
- error-type?
- get-error-category
- http-status->error
- internal-error
- invalid-config
- invalid-request
- invalid-response
- litellm-error?
- model-not-found
- model-not-found-error?
- provider-error
- provider-error?
- provider-errors
- provider-not-found
- quota-exceeded
- rate-limit
- rate-limit-error?
- recoverable?
- resource-exhausted
- response-error?
- response-errors
- retry-delay
- server-error
- should-retry?
- streaming-error
- streaming-error-chunk
- streaming-error?
- system-error?
- system-errors
- timeout-error
- timeout-error?
- unsupported-feature
- wrap-http-errors
litellm.providers.anthropic
Anthropic provider implementation for LiteLLM
Anthropic provider implementation for LiteLLM
- default-cost-map
- default-model-mapping
- extract-model-name
- get-cost-per-token-impl
- get-rate-limits-impl
- handle-error-response
- health-check-impl
- list-models
- make-request-impl
- make-streaming-request-impl
- supports-function-calling-impl
- supports-streaming-impl
- test-anthropic-connection
- transform-choice
- transform-message
- transform-messages
- transform-request-impl
- transform-response-impl
- transform-streaming-chunk-impl
- transform-tool-calls
- transform-tool-choice
- transform-tools
- transform-usage
- validate-api-key
litellm.providers.core
Core provider protocol and utilities for LiteLLM
Core provider protocol and utilities for LiteLLM
- authentication-error
- calculate-cost
- compare-providers
- create-standard-choice
- create-standard-message
- create-standard-response
- create-standard-usage
- default-provider-config
- estimate-request-tokens
- estimate-tokens
- extract-model-name
- extract-provider-name
- find-providers-for-model
- get-cost-per-token
- get-rate-limits
- health-check
- list-available-providers
- log-provider-status
- make-request
- make-streaming-request
- merge-provider-config
- model-not-found-error
- parse-model-string
- provider-available?
- provider-error
- provider-status
- provider-supports-model?
- quota-exceeded-error
- rate-limit-error
- supports-function-calling?
- supports-streaming?
- test-provider
- transform-messages-from-openai
- transform-messages-to-openai
- transform-request
- transform-response
- transform-streaming-chunk
- transform-tools-to-openai
- validate-provider-config
- validate-request
litellm.providers.gemini
Google Gemini provider implementation for LiteLLM
Google Gemini provider implementation for LiteLLM
- default-cost-map
- default-model-mapping
- extract-system-instruction
- get-cost-per-token-impl
- get-rate-limits-impl
- handle-error-response
- health-check-impl
- list-models
- make-request-impl
- make-streaming-request-impl
- supports-function-calling-impl
- supports-streaming-impl
- test-gemini-connection
- transform-candidate
- transform-generation-config
- transform-messages
- transform-request-impl
- transform-response
- transform-response-impl
- transform-role
- transform-streaming-chunk
- transform-streaming-chunk-impl
- transform-tool-calls
- transform-tool-choice
- transform-tools
- transform-usage
- validate-api-key
litellm.providers.mistral
Mistral AI provider implementation for LiteLLM
Mistral AI provider implementation for LiteLLM
- add-reasoning-system-prompt
- create-embedding-request
- default-cost-map
- get-cost-per-token-impl
- get-rate-limits-impl
- handle-error-response
- handle-streaming-response
- health-check-impl
- list-models
- magistral-models
- make-embedding-request
- make-request-impl
- parse-sse-line
- supports-function-calling-impl
- supports-reasoning?
- supports-streaming-impl
- test-mistral-connection
- transform-choice
- transform-message
- transform-messages
- transform-request-impl
- transform-response-impl
- transform-streaming-chunk
- transform-tool-calls
- transform-tool-choice
- transform-tools
- transform-usage
- validate-api-key
litellm.providers.ollama
Ollama provider implementation for LiteLLM
Ollama provider implementation for LiteLLM
- default-cost-map
- extract-model-name
- get-cost-per-token-impl
- get-rate-limits-impl
- handle-error-response
- handle-streaming-response
- health-check-impl
- list-models
- make-request-impl
- parse-streaming-chunk
- supports-function-calling-impl
- supports-streaming-impl
- test-ollama-connection
- transform-chat-response
- transform-generate-response
- transform-messages-for-chat
- transform-messages-for-generate
- transform-request-impl
- transform-response-impl
litellm.providers.openai
OpenAI provider implementation for LiteLLM
OpenAI provider implementation for LiteLLM
- default-cost-map
- default-model-mapping
- get-cost-per-token-impl
- get-rate-limits-impl
- handle-error-response
- health-check-impl
- list-models
- make-request-impl
- make-streaming-request-impl
- supports-function-calling-impl
- supports-streaming-impl
- test-openai-connection
- transform-choice
- transform-function-call
- transform-function-call-response
- transform-functions
- transform-message
- transform-messages
- transform-request-impl
- transform-response-impl
- transform-streaming-chunk-impl
- transform-tool-calls
- transform-tool-choice
- transform-tools
- transform-usage
- validate-api-key
litellm.providers.openrouter
OpenRouter provider implementation for LiteLLM
OpenRouter provider implementation for LiteLLM
- default-cost-map
- get-cost-per-token-impl
- get-rate-limits-impl
- handle-error-response
- health-check-impl
- list-models
- make-request-impl
- make-streaming-request-impl
- parse-sse-line
- supports-function-calling-impl
- supports-streaming-impl
- test-openrouter-connection
- transform-choice
- transform-message
- transform-messages
- transform-request-impl
- transform-response-impl
- transform-streaming-chunk
- transform-streaming-chunk-impl
- transform-tool-calls
- transform-tool-choice
- transform-tools
- transform-usage
- validate-api-key
litellm.router
Router-based configuration API for LiteLLM
Router-based configuration API for LiteLLM
- calculate-cost
- chat
- clear-router!
- completion
- create-router
- estimate-request-tokens
- estimate-tokens
- extract-content
- extract-message
- extract-usage
- get-config
- list-configs
- list-providers
- provider-available?
- provider-info
- quick-setup!
- register!
- setup-anthropic!
- setup-gemini!
- setup-mistral!
- setup-ollama!
- setup-openai!
- setup-openrouter!
- supports-function-calling?
- supports-streaming?
- unregister!
- validate-request
litellm.schemas
Malli schemas for LiteLLM library
Malli schemas for LiteLLM library
- ApiBase
- ApiKey
- BackoffMs
- CacheConfig
- CacheType
- Choice
- Choices
- CompletionRequest
- CompletionResponse
- CompletionTokens
- Created
- explain-config
- explain-request
- explain-response
- FallbackModel
- Fallbacks
- FinishReason
- FrequencyPenalty
- Function
- FunctionDescription
- FunctionName
- FunctionParameters
- Id
- Index
- json-transformer
- MaxBackoffMs
- MaxRetries
- MaxSize
- MaxTokens
- Message
- Messages
- Model
- ModelResponse
- object
- PoolSize
- PresencePenalty
- PromptTokens
- Provider
- ProviderConfig
- QueueSize
- RateLimit
- RetryAttempts
- RetryConfig
- Role
- RouterConfig
- RoutingStrategy
- Stop
- Stream
- string-transformer
- SystemConfig
- Temperature
- ThreadPoolConfig
- Timeout
- Tool
- ToolChoice
- Tools
- ToolType
- TopP
- TotalTokens
- transform-config
- transform-request
- transform-response
- TtlSeconds
- Usage
- valid-config?
- valid-request?
- valid-response?
- validate-config!
- validate-request!
- validate-response!
litellm.specs
Data specifications for LiteLLM library
Data specifications for LiteLLM library
litellm.streaming
Core streaming utilities for LiteLLM
Core streaming utilities for LiteLLM
litellm.wrappers
Utility wrappers for provider calls with fallback, retry, timeout, and cost-tracking
Utility wrappers for provider calls with fallback, retry, timeout, and cost-tracking
cljdoc builds & hosts documentation for Clojure/Script libraries
Keyboard shortcuts
× close| Ctrl+k | Jump to recent docs |
| ← | Move to previous article |
| → | Move to next article |
| Ctrl+/ | Jump to the search field |