Module azure_chatbot

Structs§

AiSearchOutput
ArrayItem
ArrayProperty
ChatResponse
ChatbotUserContext: Context about the user and course for a chatbot interaction. Passed to tool implementations so they can access user-specific data.
ContentFilter
ContentFilterResult
ContentFilterResults
GuardedStream 🔒: Custom stream that encapsulates both the response stream and the cancellation guard. Makes sure that the guard is always dropped when the stream is dropped.
IncompleteReason: Response received from LLM API
IncompleteResponse: Incomplete response received from LLM API
LLMRequest
LLMRequestResponseFormatParam
MistralParams
NonThinkingParams
Reasoning
ReasoningOutput
RequestCancelledGuard 🔒
RequestTextOptions
Response: Response received from LLM API
ResponseOutput: Streamed token of the response text
Schema: Defines LLM structured output shape and types
ThinkingParams

make_request_and_stream: Creates a stream with the LLMRequest and processes received OutputItems until receiving a response text or tool call. Returns: response id created by Azure (String), ResponseStreamType (type: response text or tool call) containing the created stream
parse_and_stream_to_user: Streams and parses a LLM response from Azure that contains a text response.
parse_tool: Streams and parses a LLM response from Azure that contains function calls. Calls the functions and returns a Vec of function results to be sent to Azure.
process_output_item: For saving output items that are not text messages or function calls, i.e. that don’t need further processing and are not streamed to the user. Saves reasoning and Azure AI items.
send_chat_request_and_parse_stream

PeekableLinesStream 🔒: A LinesStream that is peekable. Needed to determine which type of LLM response is being received.