Skip to main content

CLI to use DuckDuckGo AI Chat service from terminal

Project description

duckduckgo-ai-chat

PyPI Changelog Tests License

CLI to use DuckDuckGo AI Chat service from terminal

Based on the ideas of duckduckGO-chat-cli

Usage

Duckduck-aichat

For help, run:

duckchat --help

You can also use:

python -m duckchat --help

This produces.

usage: duckchat [-h] [-m {1,2,3,4,5}] [-y] [-q QUERY]

CLI to use DuckDuckGo AI Chat service from terminal

optional arguments:
  -h, --help            show this help message and exit
  -m {1,2,3,4,5}, --model {1,2,3,4,5}
                        Select a model by key:
                         1: gpt-4o-mini
                         2: claude-3-haiku-20240307
                         3: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
                         4: mistralai/Mistral-Small-24B-Instruct-2501
                         5: o3-mini
  -y, --yes             If provided, means user accept terms of service.
  -q QUERY, --query QUERY
                        First query to submit to the model

Using duckchat with initial Query

Now we can pass initial context when invoking a model with duckchat

cat app.py | duckchat --yes --model 4 --query "Explain this code" 

or launch a model with an initial query

duckchat -y -m 4 -q "How to use pytest-vcr?" 

query demo

Using Duckchat with uv

Use duckchat without installing with uv

uv run --with duckduckgo-ai-chat duckchat

Saving conversations in duckchat

Now user can save their conversaions using the /save command within the duckchat interface.

Save demo

And the saved file looks like this

Saved example

Available Models

Model Name Actual Model Performance Recommended Usage Characteristics
GPT-4o mini gpt-4o-mini Fast Quick, simple tasks Default model, Versatile
Claude 3 Haiku claude-3-haiku-20240307 Balanced Technical discussions Good context handling, Structured responses
Llama 3.3 70B meta-llama/Llama-3.3-70B-Instruct-Turbo Code optimized Programming tasks Documentation analysis, Code generation
Mistral Small 3 mistralai/Mistral-Small-24B-Instruct-2501 Knowledge focused Complex topics Detailed explanations, In-depth analysis
o3-mini o3-mini Very fast Simple queries Lightweight, Quick responses

Installation

Install this tool using pip:

pip install duckduckgo-ai-chat

Development

To contribute to this tool, first checkout the code. Then create a new virtual environment:

cd duckduckgo-ai-chat
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

pip install -e '.[test]'

To run the tests:

python -m pytest

Disclaimer

By using this client you accept DuckDuckGo AI Chat ToS

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

duckduckgo_ai_chat-0.0.8.tar.gz (11.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

duckduckgo_ai_chat-0.0.8-py3-none-any.whl (11.4 kB view details)

Uploaded Python 3

File details

Details for the file duckduckgo_ai_chat-0.0.8.tar.gz.

File metadata

  • Download URL: duckduckgo_ai_chat-0.0.8.tar.gz
  • Upload date:
  • Size: 11.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for duckduckgo_ai_chat-0.0.8.tar.gz
Algorithm Hash digest
SHA256 cbb799bf1a565b7e8c850aed8edade7936ed62e38a4a0051a4ffed72ca03c937
MD5 4d04a99497935397e7eba60ee7920045
BLAKE2b-256 a3b928c9574487b774a7c7b45b74bea037fe9fedcf08e3ecee4888b87909bdf6

See more details on using hashes here.

Provenance

The following attestation bundles were made for duckduckgo_ai_chat-0.0.8.tar.gz:

Publisher: publish.yml on sukhbinder/duckduckgo-ai-chat

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file duckduckgo_ai_chat-0.0.8-py3-none-any.whl.

File metadata

File hashes

Hashes for duckduckgo_ai_chat-0.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 6104fba5932d964c1208ef8d5084bba4d7d732a3b98c0afd090f9e14a7678ba4
MD5 186b974191568597c7e2c8b273dd9e21
BLAKE2b-256 2df83cb847c6f8777881e694942246c23bcd920d60afe2543107d6ce5d13b49f

See more details on using hashes here.

Provenance

The following attestation bundles were made for duckduckgo_ai_chat-0.0.8-py3-none-any.whl:

Publisher: publish.yml on sukhbinder/duckduckgo-ai-chat

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page