Expand description
AI Provider abstraction layer
Unified interface for multiple AI providers (OpenAI, Anthropic, Google, StepFun, etc.)
Modules§
- anthropic
- Anthropic provider implementation using the Messages API
- bedrock
- Amazon Bedrock provider implementation using the Converse API
- copilot
- GitHub Copilot provider implementation using raw HTTP.
- gemini_
web - Gemini Web provider drives the Gemini chat UI’s undocumented BardChatUi endpoint using browser cookies stored in HashiCorp Vault.
- Google Gemini provider implementation
- metrics
- Provider metrics wrapper
- models
- Model catalog from CodeTether API
- moonshot
- Moonshot AI provider implementation (direct API)
- openai
- OpenAI provider implementation
- openai_
codex - OpenAI Codex provider using ChatGPT Plus/Pro subscription via OAuth
- openrouter
- OpenRouter provider implementation using raw HTTP
- stepfun
- StepFun provider implementation (direct API, not via OpenRouter)
- vertex_
anthropic - Vertex AI Anthropic provider implementation
- vertex_
glm - Vertex AI GLM provider implementation (MaaS endpoint)
- zai
- Z.AI provider implementation (direct API)
Structs§
- Completion
Request - Request to generate a completion
- Completion
Response - Response from a completion request
- Message
- A message in a conversation
- Model
Info - Information about a model
- Provider
Registry - Registry of available providers
- Tool
Definition - Tool definition for the model
- Usage
- Token usage information
Enums§
- Content
Part - Finish
Reason - Role
- Stream
Chunk - A streaming chunk from the model
Traits§
- Provider
- Provider trait that all AI providers must implement
Functions§
- parse_
model_ string - Parse a model string in the format “provider/model”