Chat

from ragrails import RagRails

rag = RagRails(
    collection="support",
    vector_store={"provider": "qdrant", "url": "http://localhost:6333"},
    embedding={"provider": "voyage", "model": "voyage-3"},
    llm={"provider": "openai", "model": "gpt-4o-mini"},
)

history = []
result = rag.chat("How long do I have to request a refund?", history=history)

print(result.answer)
history = result.history

result.answer
result.sources
result.history
result.retrieval
result.llm
result.errors
result.retrieval_quality
result.answer_confidence
result.compacted
result.intent

for event in rag.chat_stream("How long do I have to request a refund?", history=[]):
    if event["type"] == "progress":
        print(event["stage"], event["message"])
    elif event["type"] == "token":
        print(event["data"]["text"], end="")
    elif event["type"] == "final":
        result = event["data"]

from ragrails import (
    ChatRetrievalQualityConfig,
    HistoryCompactionConfig,
    IntentRoutingConfig,
    QueryRewriteConfig,
)

result = rag.chat(
    "What about the second step?",
    history=history,
    persona="Answer as a concise support engineer.",
    query_rewrite=QueryRewriteConfig(enabled=True, session_context="Refund policy flow"),
    history_compaction=HistoryCompactionConfig(enabled=True, history_limit=15, keep_recent=5),
    intent_routing=IntentRoutingConfig(enabled=True),
    retrieval_quality=ChatRetrievalQualityConfig(
        min_retrieval_score=0.35,
        min_rerank_score=0.50,
        low_confidence_mode="answer_with_caution",
        max_context_chunks=5,
    ),
)

from ragrails.core.stg_05_retriever import RetrieverConfig

result = rag.chat(
    "How long do refunds take?",
    history=[],
    retrieval_config=RetrieverConfig(use_rerank=True, rerank_top_k=5),
)

llm = rag.llm(provider="openai", model="gpt-4o-mini", max_tokens=1024)
result = rag.chat("Summarize the refund policy", llm=llm, history=[])