from __future__ import annotations

from typing import Any

def _normalize_rag_queries(params: dict[str, Any]) -> list[str]:
    raw_queries = params.get("queries")
    queries: list[str] = []
    if isinstance(raw_queries, (list, tuple)):
        for item in raw_queries:
            text = str(item or "").strip()
            if text:
                queries.append(text)
    elif isinstance(raw_queries, str) and raw_queries.strip():
        queries.append(raw_queries.strip())

    if not queries:
        query = str(params.get("query", "")).strip()
        if query:
            queries.append(query)
    return queries


def _extract_rag_documents(payload: Any) -> list[dict[str, Any]]:
    documents: list[dict[str, Any]] = []
    if not isinstance(payload, dict):
        return documents
    raw_documents = payload.get("documents")
    if isinstance(raw_documents, (list, tuple)):
        for item in raw_documents:
            if isinstance(item, dict):
                documents.append(dict(item))
    return documents


def _rag_document_title(doc: dict[str, Any]) -> str:
    return str(
        doc.get("title_proc")
        or doc.get("title")
        or doc.get("chunk_texto")
        or ""
    ).strip()


def _rag_document_text(doc: dict[str, Any]) -> str:
    return str(
        doc.get("chunk_texto")
        or doc.get("text")
        or doc.get("title_proc")
        or doc.get("title")
        or ""
    ).strip()


def _is_selected_rag_document(doc: dict[str, Any]) -> bool:
    try:
        return float(doc.get("distance", 1.0)) <= 0.6
    except (TypeError, ValueError):
        return False


def _build_rag_answer_item(query: str, documents: list[dict[str, Any]]) -> str:
    if not documents:
        return f"{query}: Nao encontrei trechos relevantes para essa busca."
    snippets = []
    for doc in documents:
        text = _rag_document_text(doc)
        if text:
            snippets.append(text)
    if not snippets:
        return f"{query}: Encontrei trecho(s), mas sem texto disponivel."
    return f"{query}: {' '.join(snippets)}"


__all__ = [
    '_normalize_rag_queries',
    '_extract_rag_documents',
    '_rag_document_title',
    '_rag_document_text',
    '_is_selected_rag_document',
    '_build_rag_answer_item',
]