RAG Pipeline

# RAG JSON — LangChain / LlamaIndex compatible
curl "https://api.flexorch.com/v1/datasets/{id}/export?format=rag&min_quality=B" \
  -H "X-API-KEY: dfx_your_key_here" \
  -o chunks.json

# HuggingFace Arrow — datasets.load_from_disk() compatible
curl "https://api.flexorch.com/v1/datasets/{id}/export?format=hf&min_quality=B" \
  -H "X-API-KEY: dfx_your_key_here" \
  -o dataset.zip

{
  "chunks": [
    {
      "chunk_id": "abc-001",
      "chunk_index": 0,
      "text": "Invoice FTR-2024-001 from [MASKED_NAME]...",
      "token_count": 84,
      "metadata": {
        "doc_type": "invoice",
        "quality_grade": "A",
        "quality_score": 0.91,
        "pii_masked": true,
        "language": "tr"
      }
    }
  ]
}

from flexorch_sdk import FlexOrch

client = FlexOrch()

# Export to disk
client.datasets.export(dataset_id=89, format="rag", path="chunks.json", min_quality="B")

# Or load in-memory via the chunks() method
chunks_page = client.datasets.get(89).chunks(
    quality_grade="A,B",
    pii_masked=True,
    page=1,
    page_size=100,
)

for chunk in chunks_page["data"]["chunks"]:
    print(chunk["text"][:80], chunk["metadata"]["quality_grade"])

from flexorch_sdk import FlexOrch, FlexOrchReader

client = FlexOrch()
reader = FlexOrchReader(client)

documents = reader.load_data(
    dataset_id=89,
    min_quality="B",
    pii_masked_only=True,
)

from llama_index.core import VectorStoreIndex
index = VectorStoreIndex.from_documents(documents)

curl -X POST "https://api.flexorch.com/v1/datasets/{id}/index" \
  -H "X-API-KEY: dfx_your_key_here"

curl -X POST "https://api.flexorch.com/v1/search" \
  -H "X-API-KEY: dfx_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "invoices over 10000 EUR from Germany",
    "top_k": 5,
    "mode": "hybrid"
  }'

curl "https://api.flexorch.com/v1/datasets/89/chunks?quality_grade=A,B&pii_masked=true&page=1&page_size=20" \
  -H "X-API-KEY: dfx_your_key_here"

from flexorch_sdk import FlexOrch, FlexOrchRetriever

client = FlexOrch()

retriever = FlexOrchRetriever(
    client,
    quality_threshold="B",   # include A and B grade chunks
    pii_masked=True,
    top_k=5,
    mode="hybrid",
)

docs = retriever.invoke("payment terms in German invoices")
for doc in docs:
    print(doc.page_content[:80])
    print(doc.metadata["quality_grade"])

from flexorch_audit import chunk_text, rag_metadata, audit

text = open("contract.txt").read()
result = audit(text)
meta = rag_metadata(result)

if meta["should_index"] and meta["pii_safe"]:
    chunks = chunk_text(
        text,
        strategy="paragraph",
        max_tokens=meta["recommended_chunk_size"],
    )

from flexorch_sdk import FlexOrch, FlexOrchRetriever
from langchain.chains import RetrievalQA
from langchain_openai import ChatOpenAI

client = FlexOrch()

# 1 — Upload and process document
job = client.upload("invoice_batch.pdf")
job.wait()

# 2 — Build dataset
dataset = client.datasets.build(name="invoice-rag", job_ids=[job.id])

# 3 — Index for semantic search (Pro+)
client.datasets.index(dataset.id)

# 4 — Wire into LangChain
retriever = FlexOrchRetriever(client, quality_threshold="B", mode="hybrid")

qa = RetrievalQA.from_chain_type(
    llm=ChatOpenAI(model="gpt-4o-mini"),
    retriever=retriever,
)

print(qa.invoke("What is the total amount on invoice FTR-2024-001?"))