Skip to main content

DeepSeek R1 🐋

Overview

This repository contains a powerful coding assistant application that integrates with the DeepSeek API to process user conversations and generate structured JSON responses. Through an intuitive command-line interface, it can read local file contents, create new files, and apply diff edits to existing files in real time.

Key Features

  1. DeepSeek Client Configuration

    • Automatically configures an API client to use the DeepSeek service with a valid DEEPSEEK_API_KEY
    • Connects to the DeepSeek endpoint specified in the environment variable to stream GPT-like completions
  2. Data Models

    • Leverages Pydantic for type-safe handling of file operations:
      • FileToCreate: Defines structure for new files to be created
      • FileToEdit: Specifies changes to be made to existing files
      • AssistantResponse: Structures chat responses and file operations
  3. System Prompt

    • Implements a comprehensive system prompt that guides conversation flow
    • Ensures all responses follow strict JSON formatting
    • Supports both file creation and editing operations
  4. File Operations

    • read_local_file(): Reads and returns file contents as string
    • create_file(): Creates or updates files with provided content
    • show_diff_table(): Displays proposed changes in a rich format
    • apply_diff_edit(): Implements precise file modifications
  5. File Integration Commands

    • "/add path/to/file": Reads and includes single file content
    • "/add path/to/folder": Adds all non-binary, non-hidden files from directory
    • Enables context-aware assistance based on your codebase
  6. Conversation Management

    • Maintains conversation history for context awareness
    • Streams responses via DeepSeek API in real-time
    • Parses responses as JSON for structured operations
  7. Interactive CLI

    • Simple command-line interface
    • Real-time file modification previews
    • Easy confirmation of suggested changes
    • Exit with "exit" or "quit" commands

Installation

  1. Configure Environment:

    # Create .env file with API key
    echo "DEEPSEEK_API_KEY=your_api_key_here" > .env
    
  2. Install & Run:

    Using pip:

    pip install -r requirements.txt
    python3 src/deepseek_r1/main.py
    

    Using uv (recommended for speed):

    uv venv
    uv run src/deepseek_r1/main.py
    

Advanced Features: Reasoning Model

The src/deepseek_r1/r1.py script provides enhanced capabilities using DeepSeek's Reasoning Model:

  • Chain of Thought (CoT) reasoning visualization
  • Transparent decision-making process
  • Full compatibility with base features
  • Dedicated reasoning display panel
  • Clean conversation history

Usage:

python3 src/deepseek_r1/r1.py

Release files for deepseek-r1 0.1.1

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

Source distribution (sdist)

Source distribution for deepseek-r1 0.1.1
File Size Uploaded
deepseek_r1-0.1.1.tar.gz 11.5 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for deepseek-r1 0.1.1
File Interpreter ABI Platform
deepseek_r1-0.1.1-py3-none-any.whl Python 3 none any Details

Total release size:22.8 kB

Release files / deepseek_r1-0.1.1.tar.gz

Download URL deepseek_r1-0.1.1.tar.gz
Size 11.5 kB
Tags Source
SHA-256 checksum
How to use checksums
e5cc93aceb8b11bf7e6032fce3afbb71decb5e8d39d5d44a309693099b195abc
BLAKE2b-256 checksum
How to use checksums
2af0eb9402d500c33f78db6a3893da6449ebfd0230206bb574aa459176965ccf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.12.7

Release files / deepseek_r1-0.1.1-py3-none-any.whl

Download URL deepseek_r1-0.1.1-py3-none-any.whl
Size 11.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
0dd7434f26ea9bf4fc9726a5d1b3ed3ad630d53c46d73e608ada4860225715a5
BLAKE2b-256 checksum
How to use checksums
1924c0986dc9a9baf20867250c6d7afba57adf217a5b2c66c83a0256aac11951
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.12.7

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files

0.1.0

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