Skip to main content

​
extras

Rust AI Agent SDK Extra parity types and functions This module implements additional Python SDK features for full parity:
  • Deep Research types (DeepResearchResponse, ReasoningStep, etc.)
  • RAG types (RAGCitation, RetrievalPolicy, etc.)
  • Guardrail types (LLMGuardrail)
  • Handoff errors
  • App protocols
  • Embedding functions
  • Module re-exports

​
Import

use praisonai::parity::extras::*;

​
Classes

Citation

Represents a citation in the research report

ReasoningStep

Represents a reasoning step in the research process

WebSearchCall

Represents a web search call made during research

CodeExecutionStep

Represents a code execution step during research

FileSearchCall

Represents a file search call (Gemini-specific)

DeepResearchResponse

Complete response from a Deep Research query

LLMGuardrail

LLM-based guardrail for content validation

AgentAppConfig

Agent application configuration

SecurityPolicy

Security policy for sandbox execution

ReflectionOutput

Output from a reflection step

EmbeddingResult

Embedding result

EmbeddingUsage

Embedding usage statistics

TraceContextData

Trace context for tracking operations

AgentAppProtocol

Agent application protocol

AgentOSProtocol

Agent OS protocol (alias)

DbAdapter

Database adapter trait

ObsCollector

Observability collector trait

Provider

Supported Deep Research providers

RetrievalPolicy

Retrieval policy for RAG

HandoffError

Base error type for handoff operations

​
Functions

embed()

Synchronous embedding function

embedding()

Synchronous embedding function (alias)

embeddings()

Synchronous embeddings function (batch)

aembed()

Async embedding function

aembedding()

Async embedding function (alias)

aembeddings()

Async embeddings function (batch)

sync_display_callbacks()

Get sync display callbacks

async_display_callbacks()

Get async display callbacks

error_logs()

Get error logs

resolve_guardrail_policies()

Resolve guardrail policies

trace_context()

Get or create trace context

track_workflow()

Track workflow execution

load_plugin()

Load a plugin from a path