README.md

@@ -1,49 +1,3 @@
 # LLM Chat
 
-This project is currently a CLI interface for OpenAI's [GPT model API](https://platform.openai.com/docs/guides/gpt). The long term goal is to be much more general and interface with any LLM, whether that be a cloud service or a model running locally.
+A general CLI interface for large language models.
-
-## Usage
-
-### Installation
-
-The package is not currently published so you will need to build it yourself. To do so you will need [Poetry](https://python-poetry.org/) v1.5 or later. Once you have that installed, run the following commands:
-
-```bash
-git clone https://code.harrison.sh/paul/llm-chat.git
-cd llm-chat
-poetry build
-```
-
-This will create a wheel file in the `dist` directory. You can then install it with `pip`:
-
-```bash
-pip install dist/llm_chat-0.6.1-py3-none-any.whl
-```
-
-Note, a much better way to install this package system wide is to use [pipx](https://pypa.github.io/pipx/). This will install the package in an isolated environment and make the `llm` command available on your path.
-
-### Configuration
-
-Your OpenAI API key must be set in the `OPENAI_API_KEY` environment variable. The following additional environment variables are supported:
-
-| Variable             | Description                                                        |
-| -------------------- | ------------------------------------------------------------------ |
-| `OPENAI_MODEL`       | The model to use. Defaults to `gpt-3.5-turbo`.                     |
-| `OPENAI_TEMPERATURE` | The temperature to use when generating text. Defaults to `0.7`.    |
-| `OPENAI_HISTORY_DIR` | The directory to store chat history in. Defaults to `~/.llm_chat`. |
-
-The settings can also be configured via command line arguments. Run `llm chat --help` for more information.
-
-### Usage
-
-To start a chat session, run the following command:
-
-```bash
-llm chat 
-```
-
-This will start a chat session with the default settings looking something like the image below:
-
-![Chat session](./llm-chat.png)
-
-The CLI accepts multi-line input, so to send the input to the model press `Esc + Enter`. After each message a running total cost will be displayed. To exit the chat session, send the message `/q`.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "llm-chat"
-version = "0.6.1"
+version = "0.6.0"
 description = "A general CLI interface for large language models."
 authors = ["Paul Harrison <paul@harrison.sh>"]
 readme = "README.md"

src/llm_chat/settings.py

@@ -1,7 +1,6 @@
 from enum import StrEnum
 from pathlib import Path
 
-from pydantic import field_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
@@ -14,7 +13,7 @@ class Model(StrEnum):
 
 DEFAULT_MODEL = Model.GPT3
 DEFAULT_TEMPERATURE = 0.7
-DEFAULT_HISTORY_DIR = Path.home() / ".llm_chat"
+DEFAULT_HISTORY_DIR = Path().absolute() / ".history"
 
 
 class OpenAISettings(BaseSettings):
@@ -32,10 +31,3 @@ class OpenAISettings(BaseSettings):
         frozen=True,
         use_enum_values=True,
     )
-
-    @field_validator("history_dir")
-    def history_dir_must_exist(cls, history_dir: Path) -> Path:
-        """Ensure that the history directory exists."""
-        if not history_dir.exists():
-            history_dir.mkdir(parents=True)
-        return history_dir

tests/conftest.py

@@ -1,5 +1,4 @@
 import os
-from pathlib import Path
 
 import pytest
 
@@ -8,9 +7,3 @@ import pytest
 def mock_openai_api_key() -> None:
     """Set a fake OpenAI API key."""
     os.environ["OPENAI_API_KEY"] = "dummy_key"
-
-
-@pytest.fixture(autouse=True)
-def mock_history_dir(tmp_path: Path) -> None:
-    """Set a fake history directory."""
-    os.environ["OPENAI_HISTORY_DIR"] = str(tmp_path / ".llm_chat")