v0.0.101

New Features

• Enhanced CLI functionality to interact with vector databases for more dynamic responses.
• Introduced a WebScraper class for managing web scraping operations, including fetching and parsing HTML content.
• Added methods for processing text documents, generating unique identifiers for chunks, and integrating with a Chroma vector store.
• Implemented functionality to load documents from specified directories and update the Chroma database with new chunks.
• Added a similarity search feature to retrieve relevant results based on queries.
• Updated configuration options to support new features and improve user interaction.

Chores

• Updated .gitignore to exclude /docs and /vector directories from version control.
• Incremented package version and updated dependency requirements in setup.py.

What's Changed

• Create rag.py by @shouryashashank in #3
• bug fixes by @shouryashashank in #4

Full Changelog: v0.0.100...v0.0.101

v0.0.100

Predacons CLI

Welcome to the Predacons CLI! This command-line interface (CLI) allows you to interact with the Predacons library, providing a seamless way to load models, generate responses, and manage configurations directly from your terminal.

Features

• Model Management: Load and manage different types of models including local, Hugging Face safetensor, PyTorch, and GGUF models.
• Interactive Chat: Engage in interactive chat sessions with the loaded model.
• Configuration Management: Easily create, update, and clear configuration files.
• Rich Output: Utilize rich text formatting for better readability and user experience.
• Logging: Optionally enable logging for debugging and tracking purposes.

Installation

To install the Predacons CLI, you need to have Python installed on your system. You can install the required dependencies using pip:

pip install -r requirements.txt

Usage

Launching the CLI

To start the Predacons CLI, simply run:

python cli.py

Commands

Once the CLI is launched, you can use the following commands:

• clear: Clear the chat history.
• exit: Quit the CLI.
• clear-config: Clear the current configuration file.
• settings: Show and update settings.
• version: Display the current version of the Predacons CLI.
• help: Show help information.

Example Session

$ python cli.py
Welcome to the Predacons CLI!
No config file found. Creating one now...
Creating a new configuration file...
Please enter the following details to create a new configuration file
...
Welcome to the Predacons CLI! Model: Precacons/Pico-Lamma-3.2-1B-Reasoning-Instruct loaded successfully!
You can start chatting with Predacons now. Type 'clear' to clear history, Type 'exit' to quit, Type 'help' for more options,
User: Hello!
Predacons: Hi there! How can I assist you today?

Configuration

The configuration file is stored at ~/.predacons_cli/predacon_cli_config.json. You can update the configuration settings by using the settings command within the CLI.

Configuration Options

• model_path: Path to the model or Hugging Face model name.
• trust_remote_code: Boolean to trust remote code.
• use_fast_generation: Boolean to enable fast generation.
• draft_model_name: Optional draft model name.
• gguf_file: Path to the GGUF file.
• auto_quantize: Boolean to enable auto quantization.
• temperature: Temperature setting for response generation.
• max_length: Maximum length for each response.
• top_k: Top K value for response generation.
• top_p: Top P value for response generation.
• [repetition_penalty](command:_github.copilot.openSymbolFromReferences?%5B%22%22%2C%5B%7B...