Skip to main content

LLM Conveyors Python SDK

Official Python SDK for the LLM Conveyors AI Agent Platform API.

Installation

pip install llmconveyors

Quick Start

from llmconveyors import LLMConveyors

# Uses LLMCONVEYORS_API_KEY env var, or pass api_key= directly
client = LLMConveyors(api_key="llmc_...")

# Generate with streaming
result = client.agents.run(
    "job-hunter",
    {
        "companyName": "Acme Corp",
        "jobTitle": "Senior Engineer",
        "companyWebsite": "https://acme.com",
        "contactEmail": "hiring@acme.com",
        "genericEmail": "info@acme.com",
        "jobSourceUrl": "https://acme.com/careers",
    },
    on_progress=lambda e: print(f"[{e.step}] {e.percent}%"),
)

print(f"Success: {result.success}, Artifacts: {len(result.artifacts)}")

Async Usage

import asyncio
from llmconveyors import AsyncLLMConveyors

async def main():
    async with AsyncLLMConveyors() as client:
        result = await client.agents.run(
            "b2b-sales",
            {
                "companyName": "Target Corp",
                "companyWebsite": "https://target.com",
                "skipResearchCache": False,
            },
        )
        print(result.artifacts)

asyncio.run(main())

Features

  • Sync + Async clients with identical APIs
  • 15 resource namespaces: agents, stream, sessions, upload, resume, ats, settings, privacy, auth, documents, logging, health, content, shares, referral
  • SSE streaming via generators (sync) and async generators
  • High-level run() method — generate + stream + interact in one call
  • poll() method for non-streaming environments
  • Typed exceptions for all 17 API error codes
  • Automatic retry with exponential backoff and jitter
  • Webhook verification with HMAC-SHA256 and constant-time comparison
  • Pydantic v2 models for all request/response types

Webhook Verification

from llmconveyors import construct_event

event = construct_event(
    payload=request.body,  # raw bytes
    sig_header=request.headers["X-Webhook-Signature"],
    secret="your_webhook_secret",
)

Documentation

License

MIT

Metadata

Release files for llmconveyors 0.1.0

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

Source distribution (sdist)

Source distribution for llmconveyors 0.1.0
File Size Uploaded
llmconveyors-0.1.0.tar.gz 65.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for llmconveyors 0.1.0
File Interpreter ABI Platform
llmconveyors-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 105.5 kB

Release files / llmconveyors-0.1.0.tar.gz

Download URL llmconveyors-0.1.0.tar.gz
Size 65.2 kB
Tags Source
SHA-256 checksum
How to use checksums
e87cc4a09ce6554bf1e533d533c0c9762ad3fd8b2cb26b4d4f46d8b90605111f
BLAKE2b-256 checksum
How to use checksums
e23047274eabd1575b682b3e7dbacf5a828db6dd99e17d102f659a9e89fb23a0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.0

Release files / llmconveyors-0.1.0-py3-none-any.whl

Download URL llmconveyors-0.1.0-py3-none-any.whl
Size 40.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6a7c2f402af233e4d53be04ac7d932ca7c4cd652a94c386897f9d2a23b2be8c3
BLAKE2b-256 checksum
How to use checksums
a832a20249a287f7a950033827a57c83767d977309e82cf3433a4f676d4635a3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.0

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

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