ontocast.agent

Agent module for OntoCast.

This module provides a collection of agents that handle various aspects of ontology processing, including document conversion, text chunking, fact aggregation, and ontology management. Each agent is designed to perform a specific task in the ontology processing pipeline.

render_facts_fresh(state, tools) async

Render fresh facts from the current chunk into Turtle format.

Parameters:

Name	Type	Description	Default
state	UnitFactsState	The current unit facts state containing the chunk to render.	required
tools	AtomicToolBox	The toolbox instance providing utility functions.	required

Returns:

Name	Type	Description
UnitFactsState	UnitFactsState	Updated state with rendered facts.

Source code in ontocast/agent/render_facts.py

async def render_facts_fresh(
    state: UnitFactsState, tools: AtomicToolBox
) -> UnitFactsState:
    """Render fresh facts from the current chunk into Turtle format.

    Args:
        state: The current unit facts state containing the chunk to render.
        tools: The toolbox instance providing utility functions.

    Returns:
        UnitFactsState: Updated state with rendered facts.
    """
    logger.info("Rendering fresh facts")
    llm_tool = await tools.get_llm_tool(state.budget_tracker)
    parser = PydanticOutputParser(pydantic_object=FactsRenderReport)

    known_prefixes = _extract_known_prefixes(state)

    prompt_data = _prepare_prompt_data(state)
    prompt_data_fresh = {
        "preamble": preamble,
        "improvement_instruction": "",
        "output_instruction": output_instruction_empty,
    }
    prompt_data.update(prompt_data_fresh)

    prompt = _create_prompt_template()

    try:
        # Set known prefixes in context before parsing
        RDFGraph.set_known_prefixes(known_prefixes if known_prefixes else None)

        render_report: FactsRenderReport = await call_llm_with_retry(
            llm_tool=llm_tool,
            prompt=prompt,
            parser=parser,
            prompt_kwargs={
                "format_instructions": parser.get_format_instructions(),
                **prompt_data,
            },
        )
        state.set_external_evidence_request(
            WorkflowNode.TEXT_TO_FACTS, render_report.external_evidence_request
        )
        facts_report = render_report.facts_report
        facts_report.semantic_graph.sanitize_prefixes_namespaces()
        state.content_unit.graph = facts_report.semantic_graph

        # Track triples in budget tracker (fresh facts)
        num_triples = len(facts_report.semantic_graph)
        logger.info(f"Fresh facts generated with {num_triples} triple(s).")
        state.budget_tracker.add_facts_update(num_operations=1, num_triples=num_triples)

        state.clear_failure()
        state.set_node_status(WorkflowNode.TEXT_TO_FACTS, Status.SUCCESS)
        return state

    except Exception as e:
        return _handle_rendering_error(state, e, FailureStage.GENERATE_TTL_FOR_FACTS)
    finally:
        # Clear the context after parsing
        RDFGraph.set_known_prefixes(None)

render_ontology_fresh(state, tools) async

Render ontology triples into a human-readable format.

This function takes the triples from the current ontology and renders them into a more accessible format, making the ontological knowledge easier to understand.

Parameters:

Name	Type	Description	Default
state	UnitOntologyState	The current agent state containing the ontology to render.	required
tools	AtomicToolBox	The toolbox instance providing utility functions.	required

Returns:

Name	Type	Description
AgentState	UnitOntologyState	Updated state with rendered triples.

Source code in ontocast/agent/render_ontology.py

async def render_ontology_fresh(
    state: UnitOntologyState, tools: AtomicToolBox
) -> UnitOntologyState:
    """Render ontology triples into a human-readable format.

    This function takes the triples from the current ontology and renders them
    into a more accessible format, making the ontological knowledge easier to
    understand.

    Args:
        state: The current agent state containing the ontology to render.
        tools: The toolbox instance providing utility functions.

    Returns:
        AgentState: Updated state with rendered triples.
    """

    parser = PydanticOutputParser(pydantic_object=OntologyRenderReport)
    logger.info("Rendering fresh ontology")
    intro_instruction = intro_instruction_fresh.format(
        current_domain=state.current_domain
    )
    output_instruction = output_instruction_ttl
    ontology_ttl = ""
    improvement_instruction_str = ""
    general_ontology_instruction_str = general_ontology_instruction.format(
        prefix_instruction=prefix_instruction_fresh
    )

    text_chapter = text_template.format(text=state.content_unit.text)

    external_evidence = state.external_evidence_text
    if external_evidence:
        state.mark_external_evidence_used(WorkflowNode.TEXT_TO_ONTOLOGY)

    prompt = PromptTemplate(
        template=template_prompt,
        input_variables=[
            "preamble",
            "intro_instruction",
            "ontology_instruction",
            "output_instruction",
            "user_instruction",
            "improvement_instruction",
            "ontology_ttl",
            "text",
            "external_evidence",
            "format_instructions",
        ],
    )

    try:
        llm_tool = await tools.get_llm_tool(state.budget_tracker)
        render_report: OntologyRenderReport = await call_llm_with_retry(
            llm_tool=llm_tool,
            prompt=prompt,
            parser=parser,
            prompt_kwargs={
                "preamble": system_preamble,
                "intro_instruction": intro_instruction,
                "ontology_instruction": general_ontology_instruction_str,
                "output_instruction": output_instruction,
                "ontology_ttl": ontology_ttl,
                "user_instruction": state.ontology_user_instruction,
                "improvement_instruction": improvement_instruction_str,
                "text": text_chapter,
                "external_evidence": external_evidence,
                "format_instructions": parser.get_format_instructions(),
            },
        )
        state.set_external_evidence_request(
            WorkflowNode.TEXT_TO_ONTOLOGY, render_report.external_evidence_request
        )
        state.current_ontology = render_report.ontology
        state.current_ontology.graph.sanitize_prefixes_namespaces()

        num_triples = len(state.current_ontology.graph)
        logger.info(f"New ontology created with {num_triples} triple(s).")

        # Track triples in budget tracker (fresh ontology)
        state.budget_tracker.add_ontology_update(
            num_operations=1, num_triples=num_triples
        )

        state.clear_failure()
        state.set_node_status(WorkflowNode.TEXT_TO_ONTOLOGY, Status.SUCCESS)
        return state

    except Exception as e:
        logger.error(f"Failed to generate triples: {str(e)}")
        state.set_node_status(WorkflowNode.TEXT_TO_ONTOLOGY, Status.FAILED)
        state.set_failure(FailureStage.GENERATE_TTL_FOR_ONTOLOGY, str(e))
        return state