prebuilt.perplexity.base.engines

Engine configurations for the Perplexity multi-agent system.

This module defines all the engine configurations used by different agents, including LLM configurations, tool configurations, and retrieval engines.

Attributes

TOOL_REGISTRY

Classes

DocumentScoringOutput	Output model for document relevance scoring.
GeneratedResponse	Output model for response generation.
QualityCheckOutput	Output model for quality assurance.
QueryAnalysisOutput	Output model for query analysis.
SearchQueryOutput	Output model for search query generation.

Functions

create_calculator_tool(...)	Create a calculator tool for mathematical operations.
create_code_interpreter_tool(...)	Create a Python code interpreter tool.
create_document_scoring_engine(...)	Create engine for document relevance scoring.
create_engine_set_for_mode(→ Dict[str, ...)	Create the appropriate set of engines for a search mode.
create_planning_engine(...)	Create engine for multi-step planning.
create_project_analysis_engine(...)	Create engine for project analysis.
create_quality_assurance_engine(...)	Create engine for quality assurance.
create_query_analysis_engine(...)	Create engine for query analysis.
create_rag_generation_engine(...)	Create engine for RAG-based response generation.
create_reasoning_engine(...)	Create engine for chain-of-thought reasoning.
create_research_planning_engine(...)	Create engine for research planning.
create_retriever_config(...)	Create a retriever configuration.
create_search_generation_engine(...)	Create engine for search query generation.
create_source_analysis_engine(...)	Create engine for source analysis.
create_synthesis_engine(...)	Create engine for research synthesis.
create_tavily_search_tool(...)	Create a Tavily search tool configuration.
create_tool_orchestration_engine(...)	Create engine for tool orchestration.
create_vector_store_config(...)	Create a vector store configuration.
create_web_loader_tool(...)	Create a web page loader tool.
get_tools_for_mode(...)	Get the appropriate tools for a search mode.

Module Contents

class prebuilt.perplexity.base.engines.DocumentScoringOutput(/, **data: Any)

Bases: pydantic.BaseModel

Output model for document relevance scoring.

scored_results: List[Dict[str, Any]]

summary: str

class prebuilt.perplexity.base.engines.GeneratedResponse(/, **data: Any)

Bases: pydantic.BaseModel

Output model for response generation.

confidence: float = None

conflicting_sources: List[Dict[str, Any]] = None

key_citations: List[Dict[str, Any]] = None

missing_information: List[str] = None

response: str

class prebuilt.perplexity.base.engines.QualityCheckOutput(/, **data: Any)

Bases: pydantic.BaseModel

Output model for quality assurance.

citations_verified: bool

enhanced_response: str

issues_found: List[Dict[str, str]] = None

quality_score: float = None

ready_for_delivery: bool

class prebuilt.perplexity.base.engines.QueryAnalysisOutput(/, **data: Any)

Bases: pydantic.BaseModel

Output model for query analysis.

analysis_rationale: str

clarifying_questions: List[str] = None

complexity_score: float = None

decomposed_steps: List[str] = None

original_query: str

query_type: haive.agents.perplexity.base.state.QueryType

requires_real_time: bool

requires_reasoning: bool

requires_tools: bool

suggested_mode: haive.agents.perplexity.base.state.SearchMode

class prebuilt.perplexity.base.engines.SearchQueryOutput(/, **data: Any)

Bases: pydantic.BaseModel

Output model for search query generation.

search_queries: List[Dict[str, str]]

search_strategy: str

prebuilt.perplexity.base.engines.create_calculator_tool() → langchain_core.tools.StructuredTool

Create a calculator tool for mathematical operations.

prebuilt.perplexity.base.engines.create_code_interpreter_tool() → langchain_core.tools.StructuredTool

Create a Python code interpreter tool.

prebuilt.perplexity.base.engines.create_document_scoring_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for document relevance scoring.

prebuilt.perplexity.base.engines.create_engine_set_for_mode(mode: haive.agents.perplexity.base.state.SearchMode) → Dict[str, haive.core.engine.aug_llm.AugLLMConfig]

Create the appropriate set of engines for a search mode.

prebuilt.perplexity.base.engines.create_planning_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for multi-step planning.

prebuilt.perplexity.base.engines.create_project_analysis_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for project analysis.

prebuilt.perplexity.base.engines.create_quality_assurance_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for quality assurance.

prebuilt.perplexity.base.engines.create_query_analysis_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for query analysis.

prebuilt.perplexity.base.engines.create_rag_generation_engine(model: haive.agents.perplexity.base.state.ModelChoice = ModelChoice.GPT_4O) → haive.core.engine.aug_llm.AugLLMConfig

Create engine for RAG-based response generation.

prebuilt.perplexity.base.engines.create_reasoning_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for chain-of-thought reasoning.

prebuilt.perplexity.base.engines.create_research_planning_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for research planning.

prebuilt.perplexity.base.engines.create_retriever_config(vector_store_config: haive.core.engine.vectorstore.VectorStoreConfig, search_type: str = 'similarity', k: int = 5) → haive.core.engine.retriever.VectorStoreRetrieverConfig

Create a retriever configuration.

prebuilt.perplexity.base.engines.create_search_generation_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for search query generation.

prebuilt.perplexity.base.engines.create_source_analysis_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for source analysis.

prebuilt.perplexity.base.engines.create_synthesis_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for research synthesis.

prebuilt.perplexity.base.engines.create_tavily_search_tool() → langchain_core.tools.StructuredTool

Create a Tavily search tool configuration.

prebuilt.perplexity.base.engines.create_tool_orchestration_engine() → haive.core.engine.aug_llm.AugLLMConfig

Create engine for tool orchestration.

prebuilt.perplexity.base.engines.create_vector_store_config(name: str = 'perplexity_knowledge_base', provider: haive.core.engine.vectorstore.VectorStoreProvider = VectorStoreProvider.FAISS) → haive.core.engine.vectorstore.VectorStoreConfig

Create a vector store configuration.

prebuilt.perplexity.base.engines.create_web_loader_tool() → langchain_core.tools.StructuredTool

Create a web page loader tool.

prebuilt.perplexity.base.engines.get_tools_for_mode(mode: haive.agents.perplexity.base.state.SearchMode) → List[langchain_core.tools.StructuredTool]

Get the appropriate tools for a search mode.

prebuilt.perplexity.base.engines.TOOL_REGISTRY