Skip to main content

A Python project for generating and using S3 presigned URLs with a chat interface.

Project description

AI Assistant

This project implements an AI assistant with various features and customizable settings.

Features

  1. Conversational AI: Interact with the AI assistant through a command-line interface.
  2. Customizable Settings: Change the assistant's name, model, and system message on the fly.
  3. Tool Integration: The assistant can use various tools to perform tasks.
  4. Conversation History: Maintains a history of the conversation, with a configurable limit.
  5. Dot Commands: Special commands to control the assistant's behavior and view settings.

Agent Settings

  • Agent Name: AI Assistant (customizable)
  • Default LLM Model: bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0 (customizable)
  • Default System Message: "You are a helpful assistant named MATH Assistant." (customizable)
  • Max Tokens: 1000
  • History Limit: 100 messages

Tool Settings

  • Enable Tools: Yes

Usage

Run the agent.py file to start the AI assistant. Interact with it using text input.

Dot Commands

  • .help: Show available commands
  • .clear: Clear the conversation history
  • .model <model_name>: Change the LLM model
  • .view: View current settings
  • .system <message>: Change the system message
  • .name <new_name>: Change the assistant's name

Implementation Details

  • The assistant uses the litellm library for LLM interactions.
  • Asynchronous programming is used for improved performance.
  • The assistant can make tool calls and process their results.
  • Environment variables are loaded from a .env file.

Customization

Most settings can be customized in the settings.py file or during runtime using dot commands.

For more information on how to use or customize the AI Assistant, please refer to the documentation or contact the project maintainers.

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

keystroke_agent-0.1.2.tar.gz (7.2 kB view details)

Uploaded Source

Built Distribution

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

keystroke_agent-0.1.2-py3-none-any.whl (8.8 kB view details)

Uploaded Python 3

File details

Details for the file keystroke_agent-0.1.2.tar.gz.

File metadata

  • Download URL: keystroke_agent-0.1.2.tar.gz
  • Upload date:
  • Size: 7.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for keystroke_agent-0.1.2.tar.gz
Algorithm Hash digest
SHA256 17f9a8d0b954dca26c83adf8535b7bb53ea905ff60c2bf809f2d16196bc93688
MD5 8c8f0d80495913fec80f09c2f0aa0738
BLAKE2b-256 d0a519de73b5921841204ee20ab02b83ff7fc417506a5e6ae82b294a0c3e3045

See more details on using hashes here.

File details

Details for the file keystroke_agent-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for keystroke_agent-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 7bbf51731c9843f1147dbde63717a1455d06438b3ee757000493033a499a55da
MD5 86b947de6a39b941af821420bdc07b95
BLAKE2b-256 10ce9d5e1d9ab341a39b72e2f76c4e4a53a842ed833425a9a1d8a1bc9d753baf

See more details on using hashes here.

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