@qvac/sdk
API reference — v0.8.0
Overview
@qvac/sdk npm package exposes a function-centric, typed JS API.
Functions
| Function | Summary |
|---|---|
cancel() | Cancels an ongoing operation. |
close() | Closes the SDK client connection and releases all associated resources. |
completion() | Generates completion from a language model based on conversation history. |
defineHandler() | Helper function to define a handler with full type inference. |
definePlugin() | Helper function to define a plugin with full type inference. |
deleteCache() | Deletes KV cache files. |
downloadAsset() | Downloads an asset (model file) without loading it into memory. |
embed() | Generates embeddings for a single text using a specified model. |
getLogger() | Creates or retrieves a namespaced logger instance. |
getModelByName() | Looks up a model in the built-in catalog by its constant name. |
getModelByPath() | Looks up a model in the built-in catalog by its registry path. |
getModelBySrc() | Looks up a model in the built-in catalog by model file ID and blob core key. |
getModelInfo() | Returns status information for a catalog model, including cache state and loaded instances. |
invokePlugin() | Invoke a non-streaming plugin handler. |
invokePluginStream() | Invoke a streaming plugin handler. |
loadModel() | Loads a machine learning model from a local path, remote URL, or Hyperdrive key. |
loggingStream() | Opens a logging stream to receive real-time logs. |
modelRegistryGetModel() | Fetches a single model entry from the registry by its path and source. |
modelRegistryList() | Returns all available models from the QVAC distributed model registry. |
modelRegistrySearch() | Searches the model registry with optional filters for model type, engine, and quantization. |
ocr() | Performs Optical Character Recognition (OCR) on an image to extract text. |
ping() | Sends a ping request to the server and returns the pong response. |
ragChunk() | Chunks documents into smaller pieces for embedding. |
ragCloseWorkspace() | Closes a RAG workspace, releasing in-memory resources (Corestore, HyperDB adapter, RAG instance). |
ragDeleteEmbeddings() | Deletes document embeddings from the RAG vector database. |
ragDeleteWorkspace() | Deletes a RAG workspace and all its data. |
ragIngest() | Ingests documents into the RAG vector database. |
ragListWorkspaces() | Lists all RAG workspaces with their open status. |
ragReindex() | Reindexes the RAG database to optimize search performance. |
ragSaveEmbeddings() | Saves pre-embedded documents to the RAG vector database. |
ragSearch() | Searches for similar documents in the RAG vector database. |
startQVACProvider() | Starts a provider service that offers QVAC capabilities to remote peers. |
stopQVACProvider() | Stops a running provider service and leaves the specified topic. |
textToSpeech() | Converts text to speech audio using a loaded TTS model. |
transcribe() | Collects all streaming results into a single string response. |
transcribeStream() | Streams audio transcription results in real-time, yielding text chunks as they become available. |
translate() | Translates text from one language to another using a specified translation model. |
unloadModel() | Unloads a previously loaded model from the server. |
Object
| Object | Summary |
|---|---|
profiler | Singleton object that collects and exports profiling data for SDK operations. |
Shared types
Shared types
Common type definitions used across SDK functions.
Errors
Error codes
All errors thrown by the SDK and how to handle them via SDK_CLIENT_ERROR_CODES and SDK_SERVER_ERROR_CODES.