| Name | llm-term JSON |
| Version |
0.13.0
JSON |
| download |
| home_page | None |
| Summary | A simple CLI to chat with OpenAI GPT Models |
| upload_time | 2024-03-28 13:41:12 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | <4,>=3.8 |
| license | None |
| keywords |
chatgpt
cli
openai
python
rich
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# llm-term
Chat with LLM models directly from the command line.
<p align="center">
<img width="600" alt="image" src="https://i.imgur.com/1BUegLB.png">
</p>
[](https://github.com/juftin/llm-term)
[](https://pypi.python.org/pypi/llm-term/)
[](https://github.com/juftin/llm-term/blob/main/LICENSE)
[](https://github.com/astral-sh/ruff)
[](https://github.com/pre-commit/pre-commit)
[](https://github.com/semantic-release/semantic-release)
[](https://gitmoji.dev)
<details>
<summary>Screen Recording</summary>
https://user-images.githubusercontent.com/49741340/270871763-d872650e-bceb-4da3-8bc6-3e079d55e5a3.mov
</details>
<h2><a href="https://juftin.com/llm-term">Check Out the Docs</a></h2>
## Installation
```bash
pipx install llm-term
```
## Usage
Then, you can chat with the model directly from the command line:
```shell
llm-term
```
`llm-term` works with multiple LLM providers, but by default it uses OpenAI.
Most providers require extra packages to be installed, so make sure you
read the [Providers](#providers) section below. To use a different provider, you
can set the `--provider` / `-p` flag:
```shell
llm-term --provider anthropic
```
If needed, make sure you have your LLM's API key set as an environment variable
(this can also set via the `--api-key` / `-k` flag in the CLI). If your LLM uses
a particular environment variable for its API key, such as `OPENAI_API_KEY`,
that will be detected automatically.
```shell
export LLM_API_KEY="xxxxxxxxxxxxxx"
```
Optionally, you can set a custom model. llm-term defaults
to `gpt-3.5-turbo` (this can also set via the `--model` / `-m` flag in the CLI):
```shell
export LLM_MODEL="gpt-4"
```
Want to start the conversion directly from the command line? No problem,
just pass your prompt to `llm-term`:
```shell
llm-term show me python code to detect a palindrome
```
You can also set a custom system prompt. llm-term defaults to a reasonable
prompt for chatting with the model, but you can set your own prompt (this
can also set via the `--system` / `-s` flag in the CLI):
```shell
export LLM_SYSTEM_MESSAGE="You are a helpful assistant who talks like a pirate."
```
## Providers
### OpenAI
By default, llm-term uses OpenAI as your LLM provider. The default model is
`gpt-3.5-turbo` and you can also use the `OPENAI_API_KEY` environment variable
to set your API key.
### Anthropic
You can request access to Anthropic [here](https://www.anthropic.com/). The
default model is `claude-2.1`, and you can use the `ANTHROPIC_API_KEY` environment
variable. To use `anthropic` as your provider you must install the `anthropic`
extra.
```shell
pipx install "llm-term[anthropic]"
```
```shell
llm-term --provider anthropic
```
### MistralAI
You can request access to the [MistralAI](https://mistral.ai/)
[here](https://console.mistral.ai/). The default model is
`mistral-small`, and you can use the `MISTRAL_API_KEY` environment variable.
```shell
pipx install "llm-term[mistralai]"
```
```shell
llm-term --provider mistralai
```
### GPT4All
GPT4All is a an open source LLM provider. These models run locally on your
machine, so you don't need to worry about API keys or rate limits. The default
model is `mistral-7b-openorca.Q4_0.gguf`, and you can see what models are available on the [GPT4All
Website](https://gpt4all.io/index.html). Models are downloaded automatically when you first use them.
To use GPT4All as your provider you must install the `gpt4all` extra.
```bash
pipx install "llm-term[gpt4all]"
```
```shell
llm-term --provider gpt4all --model mistral-7b-openorca.Q4_0.gguf
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llm-term",
"maintainer": null,
"docs_url": null,
"requires_python": "<4,>=3.8",
"maintainer_email": null,
"keywords": "chatgpt, cli, openai, python, rich",
"author": null,
"author_email": "Justin Flannery <juftin@juftin.com>",
"download_url": "https://files.pythonhosted.org/packages/4f/f7/0a50e842bb72394799b31e8636446993f36057ad29da486cc201d1b66c39/llm_term-0.13.0.tar.gz",
"platform": null,
"description": "# llm-term\n\nChat with LLM models directly from the command line.\n\n<p align=\"center\">\n<img width=\"600\" alt=\"image\" src=\"https://i.imgur.com/1BUegLB.png\">\n</p>\n\n[](https://github.com/juftin/llm-term)\n[](https://pypi.python.org/pypi/llm-term/)\n[](https://github.com/juftin/llm-term/blob/main/LICENSE)\n[](https://github.com/astral-sh/ruff)\n[](https://github.com/pre-commit/pre-commit)\n[](https://github.com/semantic-release/semantic-release)\n[](https://gitmoji.dev)\n\n<details>\n<summary>Screen Recording</summary>\n\nhttps://user-images.githubusercontent.com/49741340/270871763-d872650e-bceb-4da3-8bc6-3e079d55e5a3.mov\n\n</details>\n\n<h2><a href=\"https://juftin.com/llm-term\">Check Out the Docs</a></h2>\n\n## Installation\n\n```bash\npipx install llm-term\n```\n\n## Usage\n\nThen, you can chat with the model directly from the command line:\n\n```shell\nllm-term\n```\n\n`llm-term` works with multiple LLM providers, but by default it uses OpenAI.\nMost providers require extra packages to be installed, so make sure you\nread the [Providers](#providers) section below. To use a different provider, you\ncan set the `--provider` / `-p` flag:\n\n```shell\nllm-term --provider anthropic\n```\n\nIf needed, make sure you have your LLM's API key set as an environment variable\n(this can also set via the `--api-key` / `-k` flag in the CLI). If your LLM uses\na particular environment variable for its API key, such as `OPENAI_API_KEY`,\nthat will be detected automatically.\n\n```shell\nexport LLM_API_KEY=\"xxxxxxxxxxxxxx\"\n```\n\nOptionally, you can set a custom model. llm-term defaults\nto `gpt-3.5-turbo` (this can also set via the `--model` / `-m` flag in the CLI):\n\n```shell\nexport LLM_MODEL=\"gpt-4\"\n```\n\nWant to start the conversion directly from the command line? No problem,\njust pass your prompt to `llm-term`:\n\n```shell\nllm-term show me python code to detect a palindrome\n```\n\nYou can also set a custom system prompt. llm-term defaults to a reasonable\nprompt for chatting with the model, but you can set your own prompt (this\ncan also set via the `--system` / `-s` flag in the CLI):\n\n```shell\nexport LLM_SYSTEM_MESSAGE=\"You are a helpful assistant who talks like a pirate.\"\n```\n\n## Providers\n\n### OpenAI\n\nBy default, llm-term uses OpenAI as your LLM provider. The default model is\n`gpt-3.5-turbo` and you can also use the `OPENAI_API_KEY` environment variable\nto set your API key.\n\n### Anthropic\n\nYou can request access to Anthropic [here](https://www.anthropic.com/). The\ndefault model is `claude-2.1`, and you can use the `ANTHROPIC_API_KEY` environment\nvariable. To use `anthropic` as your provider you must install the `anthropic`\nextra.\n\n```shell\npipx install \"llm-term[anthropic]\"\n```\n\n```shell\nllm-term --provider anthropic\n```\n\n### MistralAI\n\nYou can request access to the [MistralAI](https://mistral.ai/)\n[here](https://console.mistral.ai/). The default model is\n`mistral-small`, and you can use the `MISTRAL_API_KEY` environment variable.\n\n```shell\npipx install \"llm-term[mistralai]\"\n```\n\n```shell\nllm-term --provider mistralai\n```\n\n### GPT4All\n\nGPT4All is a an open source LLM provider. These models run locally on your\nmachine, so you don't need to worry about API keys or rate limits. The default\nmodel is `mistral-7b-openorca.Q4_0.gguf`, and you can see what models are available on the [GPT4All\nWebsite](https://gpt4all.io/index.html). Models are downloaded automatically when you first use them.\nTo use GPT4All as your provider you must install the `gpt4all` extra.\n\n```bash\npipx install \"llm-term[gpt4all]\"\n```\n\n```shell\nllm-term --provider gpt4all --model mistral-7b-openorca.Q4_0.gguf\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "A simple CLI to chat with OpenAI GPT Models",
"version": "0.13.0",
"project_urls": {
"Changelog": "https://github.com/juftin/llm-term/releases",
"Documentation": "https://juftin.github.io/llm-term",
"Issues": "https://juftin.github.io/llm-term/issues",
"Source": "https://github.com/juftin/llm-term"
},
"split_keywords": [
"chatgpt",
" cli",
" openai",
" python",
" rich"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ed6a988269ec865932d67dc19ca5a14f342f2ca45e3d277eb4b0806d94f6fc81",
"md5": "347de88825a4651faa4ae720bbbd4009",
"sha256": "545e8e32e31ec04f7e647b7a3c81e1422960c7773170e799d7d6f952e012f7f4"
},
"downloads": -1,
"filename": "llm_term-0.13.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "347de88825a4651faa4ae720bbbd4009",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4,>=3.8",
"size": 8860,
"upload_time": "2024-03-28T13:41:09",
"upload_time_iso_8601": "2024-03-28T13:41:09.463378Z",
"url": "https://files.pythonhosted.org/packages/ed/6a/988269ec865932d67dc19ca5a14f342f2ca45e3d277eb4b0806d94f6fc81/llm_term-0.13.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "4ff70a50e842bb72394799b31e8636446993f36057ad29da486cc201d1b66c39",
"md5": "ae52e070867ef0b5a2a00d82a67e467e",
"sha256": "37712746079f6756eaeb0b8a1a4178fc2f1bcf92cbfea47b526682798f947bda"
},
"downloads": -1,
"filename": "llm_term-0.13.0.tar.gz",
"has_sig": false,
"md5_digest": "ae52e070867ef0b5a2a00d82a67e467e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4,>=3.8",
"size": 151131,
"upload_time": "2024-03-28T13:41:12",
"upload_time_iso_8601": "2024-03-28T13:41:12.859814Z",
"url": "https://files.pythonhosted.org/packages/4f/f7/0a50e842bb72394799b31e8636446993f36057ad29da486cc201d1b66c39/llm_term-0.13.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-28 13:41:12",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "juftin",
"github_project": "llm-term",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "llm-term"
}
