A prompt
is a column.

from ondine import PipelineBuilder
from pydantic import BaseModel

class ReviewAnalysis(BaseModel):
    sentiment: str
    score: int
    topic: str

# Full pipeline. Composable stages, total control.
pipeline = (
    PipelineBuilder.create()
    .from_csv("reviews.csv",
              input_columns=["review"],
              output_columns=["sentiment", "score", "topic"])
    .with_prompt("Analyze the review: {review}")
    .with_llm(provider="openai", model="gpt-5.4-mini")
    .with_structured_output(ReviewAnalysis)
    .with_batch_size(50)              # 200 calls, not 10,000
    .with_max_budget(25.00)            # hard halt at $25
    .with_checkpoint_interval(100)    # checkpoint every 100 rows
    .with_disk_cache(".cache")          # identical prompts = $0 second call
    .with_router(strategy="latency")   # fastest provider wins
    .build()
)

result = pipeline.execute()

from ondine import PipelineBuilder
from ondine.knowledge import KnowledgeStore

# Index your docs once. Hybrid BM25 + dense search, optional reranker.
kb = KnowledgeStore("knowledge.db")
kb.ingest("docs/")   # PDFs, Markdown, HTML, text — OCR included

# Retrieval stage runs before the LLM, injects {_kb_context}.
pipeline = (
    PipelineBuilder.create()
    .from_csv("questions.csv",
              input_columns=["question"],
              output_columns=["answer"])
    .with_knowledge_base(kb,
                         top_k=5,
                         rerank=True,              # cross-encoder reranker
                         query_transform="hyde")   # or "multi-query", "step-back"
    .with_prompt("Context:\n{_kb_context}\n\nQ: {question}\nA:")
    .with_llm(model="gpt-5.4-mini")
    .build()
)

result = pipeline.execute()

from ondine import PipelineBuilder
from ondine.context import RustContextStore

# Optional trust layer: LLM answers verified against your evidence graph.
pipeline = (
    PipelineBuilder.create()
    .from_csv("records.csv",
              input_columns=["record"],
              output_columns=["extracted"])
    .with_prompt("Extract: {record}")
    .with_llm(model="gpt-5.4-mini")
    .with_context_store(RustContextStore("evidence.db"))
    .with_grounding(threshold=0.3)         # contradictions flagged, not written
    .with_evidence_priming(top_k=3)          # cross-run consistency
    .build()
)

result = pipeline.execute()
# Rows that failed grounding are marked in result.dataframe.