Skip to main content

OpenSeek is an open-source Python library that provides free access to DeepSeek models. Designed for developers and researchers, it offers a simple and unified interface to interact with various DeepSeek LLM models without requiring API keys, subscriptions, or paid plans.

Installation

pip install openseek

Quick Start

Asynchronous Usage

import asyncio
from openseek import DeepSeek


async def main():
    async with DeepSeek(
            email="your_email@example.com",
            password="your_password",
            headless=True
    ) as api:
        response = await api.send_message("Расскажи мне о квантовой физике")
        print(response.text)


asyncio.run(main())

Synchronous Usage

from openseek import DeepSeek


def main():
    api = DeepSeek(
        email="your_email@example.com",
        password="your_password",
        headless=True
    )

    try:
        api.initialize_sync()
        response = api.send_message_sync("Расскажи мне о квантовой физике")
        print(response.text)
    finally:
        api.close_sync()


main()

Features

  • Free Access: Use DeepSeek models without API keys or paid subscriptions
  • Asynchronous and Synchronous API: Flexibility for different usage scenarios
  • DeepThink Mode: Activate advanced thinking features for more complex queries
  • Search Support: Enable web search to get up-to-date information
  • Session Management: Resume existing chats using a session ID

Parameters

When initializing DeepSeek, the following parameters are available:

Parameter Type Default Description
email str - Email for logging into DeepSeek
password str - Password for logging into DeepSeek
chat_id Optional[str] None ID of a specific chat session
headless bool True Launch browser in headless mode
verbose bool False Enable detailed logging
chrome_args Optional[List] None Additional arguments for Chrome
attempt_cf_bypass bool True Attempt to bypass Cloudflare protection

Sending Messages

The send_message method accepts:

Parameter Type Default Description
message str - Message text to send
slow_mode bool False Send the message slowly, character by character
deepthink bool False Activate DeepThink feature
search bool False Activate search feature
timeout int 60 Maximum response waiting time
slow_mode_delay float 0.25 Delay between characters in slow_mode

Error Handling

The library can raise the following exceptions:

  • MissingCredentials: Missing credentials (email or password)
  • InvalidCredentials: Invalid credentials
  • ServerDown: DeepSeek server is unavailable
  • MissingInitialization: Required dependencies are missing or initialization not done

Requirements

  • Python 3.10 or higher
  • Dependencies: beautifulsoup4, zendriver, inscriptis, pyvirtualdisplay (for Linux)

License

MIT - see LICENSE for details.

Author

Daniel Cuzneţov danielcuznetov04@gmail.com

Metadata

Release files for openseek 0.1.4

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

Source distribution (sdist)

Source distribution for openseek 0.1.4
File Size Uploaded Provenance Actions
openseek-0.1.4.tar.gz 7.0 kB Without provenance Details for openseek-0.1.4.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for openseek 0.1.4
File Interpreter ABI Platform Actions
openseek-0.1.4-py3-none-any.whl Python 3 none any Details for openseek-0.1.4-py3-none-any.whl

Total release size: 14.9 kB

Release files / openseek-0.1.4.tar.gz

Download URL openseek-0.1.4.tar.gz
Size 7.0 kB
Tags Source
SHA-256 checksum
How to use checksums
ac14be4df6225e9479012597077d0eaf79d94617ca055cc3797778dd6b90785e
BLAKE2b-256 checksum
How to use checksums
0c0f1a0e14692f7338403956dc55acfaf51c45d71a118d0947c2a96c5dff4c46
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.1.1 CPython/3.10.11 Windows/10

Release files / openseek-0.1.4-py3-none-any.whl

Download URL openseek-0.1.4-py3-none-any.whl
Size 7.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7fe9f9037fb000603b497a03804f9565b38a88f1e6d318b6928400aaef9e5116
BLAKE2b-256 checksum
How to use checksums
b7b16d0b14b9077edf937c0f688391b9d1665a6b2cc87563e75640d9f0d51ca7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.1.1 CPython/3.10.11 Windows/10

Security for openseek 0.1.4

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