Index of every page on this site: llms.txt
All skills
inference-sh avatar

/python-sdk

@c895a47
by inference.shinference-sh/skills819 stars
108
Run it yourself

Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python

Use this Skill: https://skilld.dev/gh/inference-sh/skills/python-sdk

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈136 tokens for metadata: the name and description. ≈2.7k when used: this file. ≈11k more on demand in 6 files.

Description uses 6.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈546 characters, or 6.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Install the belt CLI skill: npx skills add belt-sh/cli

Python SDK

Build AI applications with the inference.sh Python SDK.

Python SDK

Quick Start

pip install inferencesh
from inferencesh import inference

client = inference(api_key="inf_your_key")

# Run an AI app
result = client.run({
    "app": "infsh/flux-1-dev",
    "input": {"prompt": "A sunset over mountains"}
})
print(result["output"])

Installation

# Standard installation
pip install inferencesh

# With async support
pip install inferencesh[async]

Requirements: Python 3.8+

Authentication

import os
from inferencesh import inference

# Direct API key
client = inference(api_key="inf_your_key")

# From environment variable (recommended)
client = inference(api_key=os.environ["INFERENCE_API_KEY"])

Get your API key: Settings → API Keys → Create API Key

Running Apps

Basic Execution

result = client.run({
    "app": "infsh/flux-1-dev",
    "input": {"prompt": "A cat astronaut"}
})

print(result["status"])  # "completed"
print(result["output"])  # Output data

Fire and Forget

task = client.run({
    "app": "google/veo-3-1-fast",
    "input": {"prompt": "Drone flying over mountains"}
}, wait=False)

print(f"Task ID: {task['id']}")
# Check later with client.get_task(task['id'])

Streaming Progress

for update in client.run({
    "app": "google/veo-3-1-fast",
    "input": {"prompt": "Ocean waves at sunset"}
}, stream=True):
    print(f"Status: {update['status']}")
    if update.get("logs"):
        print(update["logs"][-1])

Run Parameters

Parameter Type Description
app string App ID (namespace/name@version)
input dict Input matching app schema
setup dict Hidden setup configuration
infra string 'cloud' or 'private'
session string Session ID for stateful execution
session_timeout int Idle timeout (1-3600 seconds)

File Handling

Automatic Upload

result = client.run({
    "app": "image-processor",
    "input": {
        "image": "/path/to/image.png"  # Auto-uploaded
    }
})

Manual Upload

from inferencesh import UploadFileOptions

# Basic upload
file = client.upload_file("/path/to/image.png")

# With options
file = client.upload_file(
    "/path/to/image.png",
    UploadFileOptions(
        filename="custom_name.png",
        content_type="image/png",
        public=True
    )
)

result = client.run({
    "app": "image-processor",
    "input": {"image": file["uri"]}
})

Sessions (Stateful Execution)

Keep workers warm across multiple calls:

# Start new session
result = client.run({
    "app": "my-app",
    "input": {"action": "init"},
    "session": "new",
    "session_timeout": 300  # 5 minutes
})
session_id = result["session_id"]

# Continue in same session
result = client.run({
    "app": "my-app",
    "input": {"action": "process"},
    "session": session_id
})

Agent SDK

Template Agents

Use pre-built agents from your workspace:

agent = client.agent("my-team/support-agent@latest")

# Send message
response = agent.send_message("Hello!")
print(response.text)

# Multi-turn conversation
response = agent.send_message("Tell me more")

# Reset conversation
agent.reset()

# Get chat history
chat = agent.get_chat()

Ad-hoc Agents

Create custom agents programmatically:

from inferencesh import tool, string, number, app_tool

# Define tools
calculator = (
    tool("calculate")
    .describe("Perform a calculation")
    .param("expression", string("Math expression"))
    .build()
)

image_gen = (
    app_tool("generate_image", "infsh/flux-1-dev@latest")
    .describe("Generate an image")
    .param("prompt", string("Image description"))
    .build()
)

# Create agent
agent = client.agent({
    "core_app": {"ref": "anthropic/claude-sonnet-5-5@latest"},
    "system_prompt": "You are a helpful assistant.",
    "tools": [calculator, image_gen],
    "temperature": 0.7,
    "max_tokens": 4096
})

response = agent.send_message("What is 25 * 4?")

Available Core Apps

Model App Reference
Claude Sonnet 5.5 anthropic/claude-sonnet-5-5@latest
Claude Haiku 5.5 anthropic/claude-haiku-5-5@latest
GPT-6.1 Sol openai/gpt-6-1-sol@latest
GPT-6 Luna openai/gpt-6-luna@latest

Tool Builder API

Parameter Types

from inferencesh import (
    string, number, integer, boolean,
    enum_of, array, obj, optional
)

name = string("User's name")
age = integer("Age in years")
score = number("Score 0-1")
active = boolean("Is active")
priority = enum_of(["low", "medium", "high"], "Priority")
tags = array(string("Tag"), "List of tags")
address = obj({
    "street": string("Street"),
    "city": string("City"),
    "zip": optional(string("ZIP"))
}, "Address")

Client Tools (Run in Your Code)

greet = (
    tool("greet")
    .display("Greet User")
    .describe("Greets a user by name")
    .param("name", string("Name to greet"))
    .require_approval()
    .build()
)

App Tools (Call AI Apps)

generate = (
    app_tool("generate_image", "infsh/flux-1-dev@latest")
    .describe("Generate an image from text")
    .param("prompt", string("Image description"))
    .input({"num_inference_steps": 20})
    .require_approval()
    .build()
)

Agent Tools (Delegate to Sub-agents)

from inferencesh import agent_tool

researcher = (
    agent_tool("research", "my-org/researcher@v1")
    .describe("Research a topic")
    .param("topic", string("Topic to research"))
    .build()
)

Webhook Tools (Call External APIs)

from inferencesh import webhook_tool

notify = (
    webhook_tool("slack", "https://hooks.slack.com/...")
    .describe("Send Slack notification")
    .secret("SLACK_SECRET")
    .param("channel", string("Channel"))
    .param("message", string("Message"))
    .build()
)

Internal Tools (Built-in Capabilities)

from inferencesh import internal_tools

config = (
    internal_tools()
    .plan()
    .memory()
    .web_search(True)
    .code_execution(True)
    .image_generation({
        "enabled": True,
        "app_ref": "pruna/flux-dev@latest"
    })
    .build()
)

agent = client.agent({
    "core_app": {"ref": "anthropic/claude-sonnet-5-5@latest"},
    "internal_tools": config
})

Streaming Agent Responses

def handle_message(msg):
    if msg.get("content"):
        print(msg["content"], end="", flush=True)

def handle_tool(call):
    print(f"\n[Tool: {call.name}]")
    result = execute_tool(call.name, call.args)
    agent.submit_tool_result(call.id, result)

response = agent.send_message(
    "Explain quantum computing",
    on_message=handle_message,
    on_tool_call=handle_tool
)

File Attachments

# From file path
with open("image.png", "rb") as f:
    response = agent.send_message(
        "What's in this image?",
        files=[f.read()]
    )

# From base64
response = agent.send_message(
    "Analyze this",
    files=["data:image/png;base64,iVBORw0KGgo..."]
)

Skills (Reusable Context)

agent = client.agent({
    "core_app": {"ref": "anthropic/claude-sonnet-5-5@latest"},
    "skills": [
        {
            "name": "code-review",
            "description": "Code review guidelines",
            "content": "# Code Review\n\n1. Check security\n2. Check performance..."
        },
        {
            "name": "api-docs",
            "description": "API documentation",
            "url": "https://example.com/skills/api-docs.md"
        }
    ]
})

Async Support

from inferencesh import async_inference
import asyncio

async def main():
    client = async_inference(api_key="inf_...")

    # Async app execution
    result = await client.run({
        "app": "infsh/flux-1-dev",
        "input": {"prompt": "A galaxy"}
    })

    # Async agent
    agent = client.agent("my-org/assistant@latest")
    response = await agent.send_message("Hello!")

    # Async streaming
    async for msg in agent.stream_messages():
        print(msg)

asyncio.run(main())

Error Handling

from inferencesh import RequirementsNotMetException

try:
    result = client.run({"app": "my-app", "input": {...}})
except RequirementsNotMetException as e:
    print(f"Missing requirements:")
    for err in e.errors:
        print(f"  - {err['type']}: {err['key']}")
except RuntimeError as e:
    print(f"Error: {e}")

Human Approval Workflows

def handle_tool(call):
    if call.requires_approval:
        # Show to user, get confirmation
        approved = prompt_user(f"Allow {call.name}?")
        if approved:
            result = execute_tool(call.name, call.args)
            agent.submit_tool_result(call.id, result)
        else:
            agent.submit_tool_result(call.id, {"error": "Denied by user"})

response = agent.send_message(
    "Delete all temp files",
    on_tool_call=handle_tool
)

Reference Files

Related Skills

# JavaScript SDK
npx skills add inference-sh/skills@javascript-sdk

# Full platform skill (all apps via CLI)
npx skills add inference-sh/skills@infsh-cli

# LLM models
npx skills add inference-sh/skills@llm-models

# Image generation
npx skills add inference-sh/skills@ai-image-generation

Documentation

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert3d5 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    This skill provides a Python SDK and documentation for the inference.sh platform. It includes examples for building AI agents and tools. Although designed for developers, it contains educational examples that use the risky 'eval()' function and creates a surface for indirect prompt injection when agents process external or untrusted data.

  • Socket3d

    1 alert: gptAnomaly

  • Snyk3d

    Risk: CRITICAL · 2 issues

  • Runlayer8mo

    1/7 files flagged

  • ZeroLeaks7mo

    3 findings · Score: 69/100

Signed by skilld at c895a47. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 days ago
What it can do
Runs commands
All 2 allowed tools
Bash(pip install inferencesh)Bash(python *)
  • Python
  • sdk
  • inference-sh
  • ai-agents
  • llm
  • async
  • streaming
  • tool-builder
  • rag
  • api-client

README badge

README badge for inference-sh/skills/python-sdk

Provides a Python SDK for inference.sh that runs AI apps, builds agents with tool builders and human approval workflows, and integrates 250+ models via a single API. Supports sync/async execution, streaming, file uploads, and stateful sessions—targets Python developers building AI applications and agent systems.

Generated from the current SKILL.md.

What Python versions does this SDK support?
Python 3.8 and later. Install with `pip install inferencesh` for sync support or `pip install inferencesh[async]` for async/await.
Does this support async/await?
Yes. Use `async_inference` instead of `inference` and await calls like `await client.run(...)` and `await agent.send_message(...)`.
Can I build agents with custom tools?
Yes. Use the tool builder API to define client tools, app tools (calls to inference.sh apps), agent tools (delegation to sub-agents), and webhook tools (external APIs). Tools can require human approval before execution.
What models are available as core apps for agents?
Claude Sonnet 4, Claude 3.5 Haiku, GPT-4o, and GPT-4o Mini. Access via app references like `infsh/claude-sonnet-4@latest`.
Does the SDK handle file uploads?
Yes. Files can be auto-uploaded by passing file paths directly in input, or manually uploaded via `client.upload_file()` with optional metadata like custom filename and content-type.

Generated from the current SKILL.md. These answers refresh after source changes.