Expand description
Prost-generated typed model, compiled from proto/llmleaf/v1/llmleaf.proto by
build.rs. This is the “real codegen” proof: the proto genuinely compiles into the
crate and the generated messages are available here as a typed mirror.
These types are NOT what the SDK serialises onto the wire — prost emits
protobuf-binary-shaped types (oneofs, i32 enums, no OpenAI JSON casing). The wire
uses the hand-written serde structs in [crate::types]. Use this module when you
want the canonical proto representation (e.g. to interop with a protobuf toolchain).
Modules§
- chat_
message - Nested message and enum types in
ChatMessage. - content_
part - Nested message and enum types in
ContentPart. - tool_
choice - Nested message and enum types in
ToolChoice.
Structs§
- Architecture
- Batch
Counts - Batch
Create Request - Batch
Error - Batch
Handle - Batch
Request Item - Batch
Response - Batch
Result Line - One line of the JSONL results stream (GET /v1/batches/{id}/results).
- Chat
Completion Chunk - Chat
Message - Chat
Request - Chat
Response - Choice
- Chunk
Choice - Content
Part - A single content part for multimodal messages: {“type”:“text”,“text”:“…”} {“type”:“image_url”,“image_url”:{“url”:“…”,“detail”:“auto”}}
- Content
Parts - Delta
- Streaming SSE frame:
data: <ChatCompletionChunk JSON>\n\n, terminated by the sentinel linedata: \[DONE\]. - Embedding
- Embedding
Request - Embedding
Response - Error
Body - Error
Response - The canonical error envelope returned by every endpoint: {“error”:{“message”:…}}.
- Function
Call - A function the model called.
argumentsis a JSON-encoded string (OpenAI shape). - Function
Call Delta - Incremental tool-call fragment on a streaming delta; fields arrive piecemeal.
- Function
Def - A function the model MAY call.
parametersis a raw JSON Schema string. - Function
Name - Image
UrlPart - List
Models Response - Model
Endpoint - Admin-only fallback-chain entry (present only with a valid x-admin-token).
- Model
Entry - Named
Tool Choice - Pricing
- Response
Format - response_format: {“type”:“text”|“json_object”|“json_schema”, “json_schema”: {…}}
- Speech
Request - Text
Part - Tool
Call - Tool
Call Delta - Tool
Choice - tool_choice is either a mode string (“auto”|“none”|“required”) or an object pinning a specific function: {“type”:“function”,“function”:{“name”:“…”}}.
- ToolDef
- TopProvider
- Transcription
Request - The audio file itself is sent as the multipart
filepart, NOT in this message; these are the accompanying form fields. - Transcription
Response - For response_format json/verbose_json. text/srt/vtt return a plain-text body.
- Usage
- Token accounting echoed on every response.
cost_usdis an llmleaf addition (real-time price from the bundled pricing dataset); it is null/absent when the model has no known price. - Voice
- Voices
Response