Skip to main content

Rail Engine Retrieval SDK

Python SDK for retrieving and searching data from Railtown AI Rail Engine - handles embeddings, storage documents, and indexed content.

Overview

The rail-engine package provides a Pythonic interface for retrieving and searching data from Rail Engine. It supports async/await patterns, client-side filtering, automatic pagination, and Pydantic model deserialization.

Installation

uv pip install rail-engine

Quick Start

import asyncio
from railtown.engine import Railengine

async def main():
    # Initialize client (reads from ENGINE_PAT and ENGINE_ID env vars)
    async with Railengine() as client:
        # Search vector store
        results = client.search_vector_store(
            query="apple"
        )
        async for item in results:
            print(item)

asyncio.run(main())

Configuration

Environment Variables

  • ENGINE_PAT (required) - Personal Access Token
  • ENGINE_ID (required) - Engine ID (can also be passed to constructor)
  • RAILTOWN_API_URL (optional) - Base API URL (defaults to https://cndr.railtown.ai/api)

Constructor Parameters

  • pat (optional) - PAT token (if not provided, reads from ENGINE_PAT env)
  • engine_id (optional) - Engine ID (if not provided, reads from ENGINE_ID env, required if not in env)
  • api_url (optional) - Base API URL (if not provided, reads from RAILTOWN_API_URL env or defaults to production)
  • model (optional) - Pydantic model type for deserializing retrieved data

Features

  • Multiple retrieval methods:
    • search_vector_store() - Semantic search in vector stores
    • get_storage_document_by_event_id() - Get document by EventId
    • get_storage_document_by_customer_key() - Get documents by customer key
    • query_storage_by_jsonpath() - Query using JSONPath
    • list_storage_documents() - List all documents with pagination
    • search_index() - Full-text search using Azure Search
  • Client-side filtering - Filter results using filter_fn parameter
  • Automatic pagination - Handles pagination automatically
  • Model deserialization - Optional Pydantic model support with per-call override
  • Graceful error handling - Returns None or empty iterables on errors
  • Async/await support - Built for modern async Python applications

Error Handling

The SDK provides custom exception classes:

  • RailtownError - Base exception
  • RailtownBadRequestError - 400 Bad Request
  • RailtownUnauthorizedError - 401 Unauthorized
  • RailtownNotFoundError - 404 Not Found
  • RailtownConflictError - 409 Conflict
  • RailtownServerError - 5xx Server errors

Returns None or empty iterables on errors (graceful degradation).

Requirements

  • uv
  • Python 3.10+
  • httpx >= 0.24.0
  • pydantic >= 1.10.0

Related Package

For ingesting data into Rail Engine, see rail-engine.

License

MIT

Metadata

Release files for rail-engine 0.1.6

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

Source distribution (sdist)

Source distribution for rail-engine 0.1.6
File Size Uploaded Provenance Actions
rail_engine-0.1.6.tar.gz 24.6 kB Without provenance Details for rail_engine-0.1.6.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for rail-engine 0.1.6
File Interpreter ABI Platform Actions
rail_engine-0.1.6-py3-none-any.whl Python 3 none any Details for rail_engine-0.1.6-py3-none-any.whl

Total release size: 42.2 kB

Release files / rail_engine-0.1.6.tar.gz

Download URL rail_engine-0.1.6.tar.gz
Size 24.6 kB
Tags Source
SHA-256 checksum
How to use checksums
40a102d9222b651efaa0d9ac41e9f6bdba6aa47352b121a7c272821488edadf6
BLAKE2b-256 checksum
How to use checksums
2f3d82baa9f29fd9f9a7fe466910927d746c8e3fd59db21c287fb9a7bbc1ce12
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.8.22

Release files / rail_engine-0.1.6-py3-none-any.whl

Download URL rail_engine-0.1.6-py3-none-any.whl
Size 17.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
729c5cde413241af71c32d89f6ed21bc2d89b7b6ba29f7a429448c703221c7b7
BLAKE2b-256 checksum
How to use checksums
835d60681aebcf41861b7e8632a28953f3116bd4d368d60ff5662431dbc59305
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.8.22

Security for rail-engine 0.1.6

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