from haystack import Document
from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.document_stores.types import FilterPolicy


document_store = InMemoryDocumentStore(
    bm25_algorithm="BM25Plus",
    bm25_parameters={"k1": 1.2, "b": 0.75, "delta": 0.5},
)

documents = [
    Document(
        content="Restart the payment API after changing retry settings.",
        meta={"domain": "operations", "section": "api"},
    ),
    Document(
        content="BM25 retrievers match exact error codes and product names.",
        meta={"domain": "operations", "section": "search"},
    ),
    Document(
        content="Embedding retrievers find semantic matches with vector similarity.",
        meta={"domain": "ml", "section": "search"},
    ),
]

document_store.write_documents(documents)

retriever = InMemoryBM25Retriever(
    document_store=document_store,
    filters={"field": "meta.domain", "operator": "==", "value": "operations"},
    filter_policy=FilterPolicy.MERGE,
    top_k=2,
    scale_score=True,
)

result = retriever.run(
    query="exact error codes product names",
    filters={"field": "meta.section", "operator": "==", "value": "search"},
    top_k=1,
)

documents = result["documents"]

print(f"indexed_documents: {document_store.count_documents()}")
print(f"retrieved_documents: {len(documents)}")
for document in documents:
    print(f"content: {document.content}")
    print(f"section: {document.meta['section']}")
    print(f"score: {document.score:.4f}")