# Text ChatGPT Connector
The Text ChatGPT Connector is a simple script for connecting text files and ChatGPT.
Forked from [scrapbox_chatgpt_connector](https://github.com/nishio/scrapbox_chatgpt_connector).
Ref: https://scrapbox.io/villagepump/Scrapbox_ChatGPT_Connector
## How to install
Install by pip:
```
$ pip install text_chatgpt_connector
```
Or you can use repository directly.
Install [Poetry](https://python-poetry.org/)
and run
```
$ poetry install
$ poetry run tcc ...
```
You can run \`tcc directly if you enter the poetry virtual environment:
```
$ poetry shell
```
## How to use
### Make index
To make index, run:
```
$ tcc index -i <input_dir>
```
`input_dir` is the directory which has text files (with suffix of `.txt`, `.md` or `.markdown` by default).
This will create pickle file named **index.pickle**.
If you want to change the name, set `-o <output_file>`.
If you run with different `input_dir` for the same `output_file`,
the index is appended to the previous one.
### Ask question
To ask a question, run:
```
$ tcc ask -q "もっとも大事な問いとは何だろう？"
```
If you want compare the answer without index, run with `-n` (`--no_index`) option:
```
$ tcc ask -n -q "もっとも大事な問いとは何だろう？"
```
### Usage
```
usage: tcc [-h] [-i INPUT_DIR] [-s INPUT_SUFFIX] [-o OUTPUT_FILE] [-k KEY] [-c CHARACTER_ENCODING] [--chat_model CHAT_MODEL]
[--encoding ENCODING] [--embedding EMBEDDING] [--remain_url] [--keep_spaces] [--block_size BLOCK_SIZE]
[--embed_max_size EMBED_MAX_SIZE] [--max_prompt_size MAX_PROMPT_SIZE] [--return_size RETURN_SIZE] [--prompt PROMPT]
[--bare_prompt BARE_PROMPT] [-q QUESTION] [-n] [-v]
[command]
positional arguments:
command Command (index or ask)
options:
-h, --help show this help message and exit
-i INPUT_DIR, --input_dir INPUT_DIR
Input directory
-s INPUT_SUFFIX, --input_suffix INPUT_SUFFIX
Comma separated suffixes of input files, "txt,md,markdown"
-o OUTPUT_FILE, --output_file OUTPUT_FILE
Output file (pickle), default: "index.pickle"
-k KEY, --key KEY OpenAI API key. If not given, try to get from environment variable: OPENAI_API_KEY.
-c CHARACTER_ENCODING, --character_encoding CHARACTER_ENCODING
Character encoding for input file, default: "utf-8"
--chat_model CHAT_MODEL
Chat model name, default: "gpt-3.5-turbo"
--encoding ENCODING Encoding name for tiktoken, default: "cl100k_base"
--embedding EMBEDDING
Embedding model name, default: "text-embedding-ada-002"
--remain_url Keep URL in the text
--keep_spaces Keep spaces in the text
--block_size BLOCK_SIZE
Block size for embedding, default: 500
--embed_max_size EMBED_MAX_SIZE
Max size for embedding, default: 8150
--max_prompt_size MAX_PROMPT_SIZE
Max size for prompt, default: 4096
--return_size RETURN_SIZE
Return size, default: 250
--prompt PROMPT Prompt template, default: "Read the following text and answer the question. Your reply should be shorter
than 250 characters. ## Text {text} ## Question {question}"
--bare_prompt BARE_PROMPT
Prompt template without index, default: "Read the following text and answer the question. Your reply
should be shorter than 250 characters. ## Text {text} ## Question {question}"
-q QUESTION, --question QUESTION
Question words for ask, default: "What is the most important question?"
-n, --no_index Ask the question directly
-v, --version Show version
```
Raw data
{
"_id": null,
"home_page": "https://github.com/rcmdnk/text_chatgpt_connector",
"name": "text-chatgpt-connector",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8.1,<3.12",
"maintainer_email": "",
"keywords": "API,ChatGPT,AI",
"author": "rcmdnk",
"author_email": "rcmdnk@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/21/2a/1e5fd4015459a51540f0fbce72b1227ebfd57752e303e0a7c2b43d1c5db1/text_chatgpt_connector-0.0.2.tar.gz",
"platform": null,
"description": "# Text ChatGPT Connector\n\nThe Text ChatGPT Connector is a simple script for connecting text files and ChatGPT.\n\nForked from [scrapbox_chatgpt_connector](https://github.com/nishio/scrapbox_chatgpt_connector).\n\nRef: https://scrapbox.io/villagepump/Scrapbox_ChatGPT_Connector\n\n## How to install\n\nInstall by pip:\n\n```\n$ pip install text_chatgpt_connector\n```\n\nOr you can use repository directly.\nInstall [Poetry](https://python-poetry.org/)\nand run\n\n```\n$ poetry install\n$ poetry run tcc ...\n```\n\nYou can run \\`tcc directly if you enter the poetry virtual environment:\n\n```\n$ poetry shell\n```\n\n## How to use\n\n### Make index\n\nTo make index, run:\n\n```\n$ tcc index -i <input_dir>\n```\n\n`input_dir` is the directory which has text files (with suffix of `.txt`, `.md` or `.markdown` by default).\n\nThis will create pickle file named **index.pickle**.\nIf you want to change the name, set `-o <output_file>`.\n\nIf you run with different `input_dir` for the same `output_file`,\nthe index is appended to the previous one.\n\n### Ask question\n\nTo ask a question, run:\n\n```\n$ tcc ask -q \"\u3082\u3063\u3068\u3082\u5927\u4e8b\u306a\u554f\u3044\u3068\u306f\u4f55\u3060\u308d\u3046\uff1f\"\n```\n\nIf you want compare the answer without index, run with `-n` (`--no_index`) option:\n\n```\n$ tcc ask -n -q \"\u3082\u3063\u3068\u3082\u5927\u4e8b\u306a\u554f\u3044\u3068\u306f\u4f55\u3060\u308d\u3046\uff1f\"\n```\n\n### Usage\n\n```\nusage: tcc [-h] [-i INPUT_DIR] [-s INPUT_SUFFIX] [-o OUTPUT_FILE] [-k KEY] [-c CHARACTER_ENCODING] [--chat_model CHAT_MODEL]\n [--encoding ENCODING] [--embedding EMBEDDING] [--remain_url] [--keep_spaces] [--block_size BLOCK_SIZE]\n [--embed_max_size EMBED_MAX_SIZE] [--max_prompt_size MAX_PROMPT_SIZE] [--return_size RETURN_SIZE] [--prompt PROMPT]\n [--bare_prompt BARE_PROMPT] [-q QUESTION] [-n] [-v]\n [command]\n\npositional arguments:\n command Command (index or ask)\n\noptions:\n -h, --help show this help message and exit\n -i INPUT_DIR, --input_dir INPUT_DIR\n Input directory\n -s INPUT_SUFFIX, --input_suffix INPUT_SUFFIX\n Comma separated suffixes of input files, \"txt,md,markdown\"\n -o OUTPUT_FILE, --output_file OUTPUT_FILE\n Output file (pickle), default: \"index.pickle\"\n -k KEY, --key KEY OpenAI API key. If not given, try to get from environment variable: OPENAI_API_KEY.\n -c CHARACTER_ENCODING, --character_encoding CHARACTER_ENCODING\n Character encoding for input file, default: \"utf-8\"\n --chat_model CHAT_MODEL\n Chat model name, default: \"gpt-3.5-turbo\"\n --encoding ENCODING Encoding name for tiktoken, default: \"cl100k_base\"\n --embedding EMBEDDING\n Embedding model name, default: \"text-embedding-ada-002\"\n --remain_url Keep URL in the text\n --keep_spaces Keep spaces in the text\n --block_size BLOCK_SIZE\n Block size for embedding, default: 500\n --embed_max_size EMBED_MAX_SIZE\n Max size for embedding, default: 8150\n --max_prompt_size MAX_PROMPT_SIZE\n Max size for prompt, default: 4096\n --return_size RETURN_SIZE\n Return size, default: 250\n --prompt PROMPT Prompt template, default: \"Read the following text and answer the question. Your reply should be shorter\n than 250 characters. ## Text {text} ## Question {question}\"\n --bare_prompt BARE_PROMPT\n Prompt template without index, default: \"Read the following text and answer the question. Your reply\n should be shorter than 250 characters. ## Text {text} ## Question {question}\"\n -q QUESTION, --question QUESTION\n Question words for ask, default: \"What is the most important question?\"\n -n, --no_index Ask the question directly\n -v, --version Show version\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "ChatGPT reads Text files",
"version": "0.0.2",
"split_keywords": [
"api",
"chatgpt",
"ai"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "c493b48386d1c5b2b63c16b042b0fdbae4eb1367f101c9ecc427731786a7307a",
"md5": "297ea36b5a1a9028a442af98cccc70b6",
"sha256": "f4728cbe9ed90f4fc32119639146d1ef664c1b36b7d6e00ec3c9629e8e883c46"
},
"downloads": -1,
"filename": "text_chatgpt_connector-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "297ea36b5a1a9028a442af98cccc70b6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8.1,<3.12",
"size": 8370,
"upload_time": "2023-03-21T18:43:53",
"upload_time_iso_8601": "2023-03-21T18:43:53.648765Z",
"url": "https://files.pythonhosted.org/packages/c4/93/b48386d1c5b2b63c16b042b0fdbae4eb1367f101c9ecc427731786a7307a/text_chatgpt_connector-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "212a1e5fd4015459a51540f0fbce72b1227ebfd57752e303e0a7c2b43d1c5db1",
"md5": "4f91e6f98210bfd0570adb58e1c738c4",
"sha256": "2cd2d3de3cb9310507ef82facb0e3e098c0abb76918a919faa8eedbf67aab757"
},
"downloads": -1,
"filename": "text_chatgpt_connector-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "4f91e6f98210bfd0570adb58e1c738c4",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8.1,<3.12",
"size": 7486,
"upload_time": "2023-03-21T18:43:55",
"upload_time_iso_8601": "2023-03-21T18:43:55.111598Z",
"url": "https://files.pythonhosted.org/packages/21/2a/1e5fd4015459a51540f0fbce72b1227ebfd57752e303e0a7c2b43d1c5db1/text_chatgpt_connector-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-03-21 18:43:55",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "rcmdnk",
"github_project": "text_chatgpt_connector",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "text-chatgpt-connector"
}
JSON
