Skip to main content

RAGfly Python SDK

Official Python client for RAGfly. It speaks the English REST /v1 contract.

Using TypeScript/JavaScript? See the TypeScript SDK (npm install @ragfly/sdk) — same surface.

Install

pip install ragfly

Quick start

from ragfly import RAGfly

client = RAGfly(api_key="rf_...")

# RAG end to end
print(client.ask("What are the Q1 sales figures?").answer)

# Retrieval only
results = client.search("maintenance contracts", limit=5)
for doc in results.documents:
    print(doc.name, doc.max_similarity)

Operations

Everything the RAGfly application lets your user do is available as an operation, with the same permissions and audit as the web app.

ops = client.list_operations()["operations"]              # what this key can run
schema = client.get_operation("document_types.update")    # input_schema / output_schema

client.run_operation("document_types.update", {"code": "TDOC_...", "name": "Invoices"})

# write_confirm operations (deletes, reverts, resets) need confirm=True
preview = client.run_operation("document_types.delete", {"code": "TDOC_..."})
assert preview["executed"] is False
client.run_operation("document_types.delete", {"code": "TDOC_..."}, confirm=True)

Errors raise RAGflyError with status_code, the public code (NOT_FOUND, VALIDATION_ERROR, …) and details.

API keys

Create an API key from app.ragfly.ai → API Keys. A key only works on /v1; creating or revoking keys needs a signed-in person.

Methods

Area Methods
Session and documents session, set_active_workspace, set_active_area, list_areas, list_locations, list_documents, get_document, document_edges, search, search_filtered
Collections list_collections, get_collection, refresh_collection, save_collection, compose_collections, read_collection
Queue, catalog, skills queue, list_runs, catalog, list_document_types, list_characteristics, get_function, list_skills, get_skill, run_skill
Answers and agents ask, agent_context, run_agent_tool
Organization get_organization, update_organization, draft_organization
Usage, conversations, processes get_usage, list_conversations, delete_conversation, list_processes, get_process, update_process
Operations list_operations, get_operation, run_operation

Metadata

Release files for ragfly 0.6.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ragfly 0.6.0
File Size Uploaded Provenance
ragfly-0.6.0.tar.gz 11.8 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for ragfly 0.6.0
File Interpreter ABI Platform
ragfly-0.6.0-py3-none-any.whl Python 3 none any Details

Total release size: 19.8 kB

Release files / ragfly-0.6.0.tar.gz

Download URL ragfly-0.6.0.tar.gz
Size 11.8 kB
Tags Source
SHA-256 checksum
How to use checksums
8397c652452c220ca4a16a842b5b5f1c214437a9db2ba5a3ee43cdb5d70ace95
BLAKE2b-256 checksum
How to use checksums
454c02ec0b5da53a38e3dd37b10104e09d32b0af35f1613177ff6b0456735644
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Release files / ragfly-0.6.0-py3-none-any.whl

Download URL ragfly-0.6.0-py3-none-any.whl
Size 8.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
fcc0d44630b124f1ebf4f06f22130886632c6fd5a0b172ceb5b9ad3a9c8afc00
BLAKE2b-256 checksum
How to use checksums
6db354becae6769a3d4fb387710f9e1dcbd105e0c377e585497cf049b22dd3fe
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Security for ragfly 0.6.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page