talk-codebase/README.md

# talk-codebase is a powerful tool for chatting with your codebase

<p align="center">
  <img src="https://github.com/rsaryev/talk-codebase/assets/70219513/87a031ec-51e2-4123-abe6-91bb4d248b4d" width="800" alt="chat">
</p>

## Description

In the chat, you can ask questions about the codebase. AI will answer your questions, and if necessary, it will offer code improvements. This is very convenient when you want to quickly find something in the codebase, but don't want to waste time searching. It is also convenient when you want to improve a specific function, you can ask "How can I improve the function {function name}?" and AI will suggest improvements. Codebase is analyzed using openai.

## Installation

```bash
pip install talk-codebase
```

## Usage

talk-codebase works only with files of popular programming languages and additionally with .txt files. All other files will be ignored.
```bash
# Start chatting with your codebase
talk-codebase chat <directory>

# Configure
talk-codebase configure

# Help
talk-codebase --help
```
Add CLI for chatting with OpenAI model - Add CLI functionality for chatting with OpenAI model - Implement function to allow users to input OpenAI API key and model name - Implement function to allow users to chat with OpenAI model using retrieved documents - Add module to handle sending questions to OpenAI model - Add module to load and split text documents, create retriever, and define StreamStdOut callback class 2023-05-26 01:15:30 +00:00			`# talk-codebase is a powerful tool for chatting with your codebase`

			`<p align="center">`
refactor: update function names and remove unused imports - Refactor cli.py and llm.py to use new function names for create_vector_store and send_question respectively - Remove unused imports in utils.py 2023-05-26 11:59:40 +00:00			`<img src="https://github.com/rsaryev/talk-codebase/assets/70219513/87a031ec-51e2-4123-abe6-91bb4d248b4d" width="800" alt="chat">`
Add CLI for chatting with OpenAI model - Add CLI functionality for chatting with OpenAI model - Implement function to allow users to input OpenAI API key and model name - Implement function to allow users to chat with OpenAI model using retrieved documents - Add module to handle sending questions to OpenAI model - Add module to load and split text documents, create retriever, and define StreamStdOut callback class 2023-05-26 01:15:30 +00:00			`</p>`

			`## Description`

			`In the chat, you can ask questions about the codebase. AI will answer your questions, and if necessary, it will offer code improvements. This is very convenient when you want to quickly find something in the codebase, but don't want to waste time searching. It is also convenient when you want to improve a specific function, you can ask "How can I improve the function {function name}?" and AI will suggest improvements. Codebase is analyzed using openai.`

			`## Installation`

			```bash
			`pip install talk-codebase`
			```

			`## Usage`

			`talk-codebase works only with files of popular programming languages and additionally with .txt files. All other files will be ignored.`
			```bash
			`# Start chatting with your codebase`
			`talk-codebase chat <directory>`

			`# Configure`
			`talk-codebase configure`

			`# Help`
			`talk-codebase --help`
			```