efc84fbb97
Implement yao doc process list/inspect/validate and yao doc runtime list/inspect/validate commands. Validate uses engine addressing logic (process.Of) and checks dynamic-ID group registries (model, store, fs, task, schedule) to verify resources actually exist. - cmd/doc/: CLI command tree with process and runtime subcommands - cmd/root.go: wire docCmd into rootCmd - 27 process doc.yml + doc.go pairs across yao packages - cmd/doc/doc_test.go: integration tests Made-with: Cursor
97 lines
2.8 KiB
YAML
97 lines
2.8 KiB
YAML
group: openai
|
|
type: process
|
|
entries:
|
|
- name: tiktoken
|
|
desc: Count the number of tokens for a given model and input text
|
|
args:
|
|
- name: model
|
|
type: string
|
|
required: true
|
|
desc: Model name for tokenization (e.g. "gpt-3.5-turbo", "gpt-4")
|
|
- name: input
|
|
type: string
|
|
required: true
|
|
desc: Input text to tokenize
|
|
return:
|
|
type: number
|
|
desc: Number of tokens in the input text
|
|
|
|
- name: embeddings
|
|
desc: Create embedding vectors representing the input text
|
|
args:
|
|
- name: model
|
|
type: string
|
|
required: true
|
|
desc: AI connector name (e.g. "openai")
|
|
- name: input
|
|
type: any
|
|
required: true
|
|
desc: Input text or array of texts to embed
|
|
- name: user
|
|
type: string
|
|
required: false
|
|
desc: Unique identifier for the end-user
|
|
return:
|
|
type: object
|
|
desc: Embedding response with vector data
|
|
|
|
- name: chat.completions
|
|
desc: Create a chat completion response for the given messages
|
|
args:
|
|
- name: model
|
|
type: string
|
|
required: true
|
|
desc: AI connector name (e.g. "openai")
|
|
- name: messages
|
|
type: array
|
|
required: true
|
|
desc: "Array of message objects with role and content fields"
|
|
- name: options
|
|
type: object
|
|
required: false
|
|
desc: "Additional options: temperature, max_tokens, etc."
|
|
- name: callback
|
|
type: function
|
|
required: false
|
|
desc: Callback function for streaming responses; receives each chunk and returns an int status
|
|
return:
|
|
type: object
|
|
desc: Chat completion response object
|
|
|
|
- name: audio.transcriptions
|
|
desc: Transcribe audio from base64-encoded data into text
|
|
args:
|
|
- name: model
|
|
type: string
|
|
required: true
|
|
desc: AI connector name (e.g. "openai.whisper-1")
|
|
- name: dataBase64
|
|
type: string
|
|
required: true
|
|
desc: Base64-encoded audio data
|
|
- name: options
|
|
type: object
|
|
required: false
|
|
desc: "Additional options: language, model override, etc."
|
|
return:
|
|
type: object
|
|
desc: "Transcription result (e.g. {\"text\": \"...\"})"
|
|
|
|
- name: audio.transcriptionsfile
|
|
desc: Transcribe audio from a file path using streaming upload (no base64 overhead)
|
|
args:
|
|
- name: connector
|
|
type: string
|
|
required: true
|
|
desc: AI connector name (e.g. "openai.whisper-1")
|
|
- name: filePath
|
|
type: string
|
|
required: true
|
|
desc: Absolute OS file path to the audio file
|
|
- name: options
|
|
type: object
|
|
required: false
|
|
desc: "Additional options: language, model override, etc."
|
|
return:
|
|
type: object
|
|
desc: "Transcription result (e.g. {\"text\": \"...\"})"
|