LlamaIndex Integration

pip install flexorch-sdk llama-index-core

from flexorch_sdk import FlexOrch, FlexOrchReader

client = FlexOrch()  # reads FLEXORCH_API_KEY from env

reader = FlexOrchReader(client)

documents = reader.load_data(
    dataset_id=89,
    min_quality="B",           # exclude C and D grade chunks
    pii_masked_only=True,      # only load PII-safe chunks
    page_size=100,             # chunks fetched per request
)

for doc in documents:
    print(doc.text[:100])
    print(doc.metadata["quality_grade"])

from flexorch_sdk import FlexOrch, FlexOrchReader
from llama_index.core import VectorStoreIndex

client = FlexOrch()
reader = FlexOrchReader(client)

documents = reader.load_data(dataset_id=89, min_quality="B")
index = VectorStoreIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What are the payment terms in the contracts?")
print(response)

from llama_index.core import StorageContext, load_index_from_storage

# Persist
index.storage_context.persist("./storage")

# Reload (no re-fetch needed)
storage_context = StorageContext.from_defaults(persist_dir="./storage")
index = load_index_from_storage(storage_context)

query_engine = index.as_query_engine(streaming=True)
response = query_engine.query("Summarise the Q1 invoices.")

for token in response.response_gen:
    print(token, end="", flush=True)

from llama_index.core.vector_stores import MetadataFilter, MetadataFilters

filters = MetadataFilters(filters=[
    MetadataFilter(key="quality_grade", value="A"),
])

query_engine = index.as_query_engine(filters=filters)
response = query_engine.query("High-quality contract clauses only")

all_documents = []
for dataset_id in [89, 90, 91]:
    docs = reader.load_data(dataset_id=dataset_id, min_quality="B")
    all_documents.extend(docs)

index = VectorStoreIndex.from_documents(all_documents)