Skip to main content

metorial-deepseek

DeepSeek provider integration for Metorial.

Installation

pip install metorial openai

Quick Start

import asyncio
from metorial import Metorial, MetorialDeepSeek
from openai import AsyncOpenAI

metorial = Metorial(api_key="your-metorial-api-key")
deepseek = AsyncOpenAI(
    api_key="your-deepseek-api-key",
    base_url="https://api.deepseek.com"
)

async def main():
    async def session_handler(session):
        messages = [{"role": "user", "content": "What's the latest news?"}]

        for _ in range(10):
            response = await deepseek.chat.completions.create(
                model="deepseek-chat",
                messages=messages,
                tools=session["tools"]
            )

            choice = response.choices[0]
            tool_calls = choice.message.tool_calls

            if not tool_calls:
                print(choice.message.content)
                break

            tool_responses = await session["callTools"](tool_calls)
            messages.append({"role": "assistant", "tool_calls": tool_calls})
            messages.extend(tool_responses)

        await session["closeSession"]()

    await metorial.with_provider_session(
        MetorialDeepSeek.chat_completions,
        {"serverDeployments": [{"serverDeploymentId": "your-server-deployment-id"}]},
        session_handler
    )

asyncio.run(main())

Streaming

import asyncio
from metorial import Metorial, MetorialDeepSeek
from openai import AsyncOpenAI

metorial = Metorial(api_key="your-metorial-api-key")
deepseek = AsyncOpenAI(
    api_key="your-deepseek-api-key",
    base_url="https://api.deepseek.com"
)

async def main():
    async def session_handler(session):
        messages = [{"role": "user", "content": "What's the latest news?"}]

        stream = await deepseek.chat.completions.create(
            model="deepseek-chat",
            messages=messages,
            tools=session["tools"],
            stream=True
        )

        async for chunk in stream:
            if chunk.choices[0].delta.content:
                print(chunk.choices[0].delta.content, end="", flush=True)

        await session["closeSession"]()

    await metorial.with_provider_session(
        MetorialDeepSeek.chat_completions,
        {
            "serverDeployments": [{"serverDeploymentId": "your-server-deployment-id"}],
            "streaming": True,  # Required for streaming with tool calls
        },
        session_handler
    )

asyncio.run(main())

Supported Models

  • deepseek-chat: DeepSeek Chat
  • deepseek-reasoner: DeepSeek Reasoner

Session Object

async def session_handler(session):
    tools = session["tools"]           # Tool definitions in OpenAI-compatible format
    call_tools = session["callTools"]  # Execute tools and get responses
    close_session = session["closeSession"]  # Close the session when done

Error Handling

from metorial import MetorialAPIError

try:
    await metorial.with_provider_session(...)
except MetorialAPIError as e:
    print(f"API Error: {e.message} (Status: {e.status})")
except Exception as e:
    print(f"Unexpected error: {e}")

License

MIT License - see LICENSE file for details.

Metadata

Release files for metorial-deepseek 1.0.5

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

Source distribution (sdist)

Source distribution for metorial-deepseek 1.0.5
File Size Uploaded
metorial_deepseek-1.0.5.tar.gz 5.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for metorial-deepseek 1.0.5
File Interpreter ABI Platform
metorial_deepseek-1.0.5-py3-none-any.whl Python 3 none any Details

Total release size: 9.2 kB

Release files / metorial_deepseek-1.0.5.tar.gz

Download URL metorial_deepseek-1.0.5.tar.gz
Size 5.1 kB
Tags Source
SHA-256 checksum
How to use checksums
051583a495b481f3d10f78374b7c99f52a06703181b2fd75516efa330891fd92
BLAKE2b-256 checksum
How to use checksums
613e1aae6b81cf7405dfab64801f299765b1bb02653529a6a5c3c5df3528eb01
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Dec 23, 2025.

Transparency log

Release files / metorial_deepseek-1.0.5-py3-none-any.whl

Download URL metorial_deepseek-1.0.5-py3-none-any.whl
Size 4.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
20220c2e18a36e3f271f29c6d6984abc43782d9714991b562ea9ecd30046d44e
BLAKE2b-256 checksum
How to use checksums
f0be1c1f3d915ffe34ce345a939520ddf33ed942260dd6230136df09be289437
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Dec 23, 2025.

Transparency log
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