| Name | multiai JSON |
| Version |
0.8
JSON |
| download |
| home_page | None |
| Summary | A Python library for text-based AI interactions |
| upload_time | 2024-08-18 17:19:45 |
| maintainer | None |
| docs_url | None |
| author | Katsutoshi Seki |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
ai
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# multiai
`multiai` is a Python library and command-line tool designed to interact with text-based generative AI models from the following providers:
| AI Provider | Web Service | Models Available |
|--------------|------------------------------------|----------------------------------------------------------------|
| **OpenAI** | [ChatGPT](https://chat.openai.com/) | [GPT Models](https://platform.openai.com/docs/models) |
| **Anthropic**| [Claude](https://claude.ai/) | [Claude Models](https://docs.anthropic.com/en/docs/about-claude/models) |
| **Google** | [Gemini](https://gemini.google.com/)| [Gemini Models](https://ai.google.dev/gemini-api/docs/models/gemini) |
| **Perplexity** | [Perplexity](https://www.perplexity.ai/) | [Perplexity Models](https://docs.perplexity.ai/docs/model-cards) |
| **Mistral** | [Mistral](https://chat.mistral.ai/chat) | [Mistral Models](https://docs.mistral.ai/getting-started/models/) |
## Key Features
- **Interactive Chat:** Communicate with AI directly from your terminal.
- **Multi-Line Input:** Supports multi-line prompts for complex queries.
- **Pager for Long Responses:** View lengthy responses conveniently using a pager.
- **Continuation Handling:** Automatically handle and request continuations if responses are cut off.
- **Automatic Chat Logging:** Automatically save your chat history for future reference.
## Usage
Install `multiai`, then configure your API keys for your chosen AI providers as environment variables or in a user-setting file. Once that's done, you can start interacting with the AI.
- To send a simple query:
```bash
ai hi
```
You should see a response like:
```bash
gpt-4o-mini>
Hello! How can I assist you today?
```
- For an interactive session, enter interactive mode:
```bash
ai
```
In this mode, you can continue the conversation:
```bash
user> hi
gpt-4o-mini>
Hello! How can I assist you today?
user> how are you
gpt-4o-mini>
I'm just a program, so I don't have feelings, but I'm here and ready to help you! How about you? How are you doing?
user>
```
To see a list of all command-line options, use:
```bash
ai -h
```
For more detailed documentation, you can open the [manual](https://sekika.github.io/multiai/) in a web browser with:
```bash
ai -d
```
## Using `multiai` as a Python Library
`multiai` can also be used as a Python library. Here’s a simple example:
```python
import multiai
# Initialize the client
client = multiai.Prompt()
client.set_model('openai', 'gpt-4o') # Set model
client.temperature = 0.5 # Set temperature
# Send a prompt and get a response
answer = client.ask('hi')
print(answer)
# Continue the conversation with context
answer = client.ask('how are you')
print(answer)
# Clear the conversation context
client.clear()
```
The manual includes the following sample codes:
- A script that translates a text file into English.
- A local chat app that allows you to easily select from various AI models provided by different providers and engage in conversations with them.
Raw data
{
"_id": null,
"home_page": null,
"name": "multiai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "AI",
"author": "Katsutoshi Seki",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/7e/61/418a26842823bdba3ddb9631acfbc1e4cd91e9c19dae989d801f2e1c6fb4/multiai-0.8.tar.gz",
"platform": null,
"description": "# multiai\n\n`multiai` is a Python library and command-line tool designed to interact with text-based generative AI models from the following providers:\n\n| AI Provider | Web Service | Models Available |\n|--------------|------------------------------------|----------------------------------------------------------------|\n| **OpenAI** | [ChatGPT](https://chat.openai.com/) | [GPT Models](https://platform.openai.com/docs/models) |\n| **Anthropic**| [Claude](https://claude.ai/) | [Claude Models](https://docs.anthropic.com/en/docs/about-claude/models) |\n| **Google** | [Gemini](https://gemini.google.com/)| [Gemini Models](https://ai.google.dev/gemini-api/docs/models/gemini) |\n| **Perplexity** | [Perplexity](https://www.perplexity.ai/) | [Perplexity Models](https://docs.perplexity.ai/docs/model-cards) |\n| **Mistral** | [Mistral](https://chat.mistral.ai/chat) | [Mistral Models](https://docs.mistral.ai/getting-started/models/) |\n\n## Key Features\n\n- **Interactive Chat:** Communicate with AI directly from your terminal.\n- **Multi-Line Input:** Supports multi-line prompts for complex queries.\n- **Pager for Long Responses:** View lengthy responses conveniently using a pager.\n- **Continuation Handling:** Automatically handle and request continuations if responses are cut off.\n- **Automatic Chat Logging:** Automatically save your chat history for future reference.\n\n## Usage\n\nInstall `multiai`, then configure your API keys for your chosen AI providers as environment variables or in a user-setting file. Once that's done, you can start interacting with the AI.\n\n- To send a simple query:\n\n ```bash\n ai hi\n ```\n\n You should see a response like:\n\n ```bash\n gpt-4o-mini>\n Hello! How can I assist you today?\n ```\n\n- For an interactive session, enter interactive mode:\n\n ```bash\n ai\n ```\n\n In this mode, you can continue the conversation:\n\n ```bash\n user> hi\n gpt-4o-mini>\n Hello! How can I assist you today?\n user> how are you\n gpt-4o-mini>\n I'm just a program, so I don't have feelings, but I'm here and ready to help you! How about you? How are you doing?\n user>\n ```\n\nTo see a list of all command-line options, use:\n\n```bash\nai -h\n```\n\nFor more detailed documentation, you can open the [manual](https://sekika.github.io/multiai/) in a web browser with:\n\n```bash\nai -d\n```\n\n## Using `multiai` as a Python Library\n\n`multiai` can also be used as a Python library. Here\u2019s a simple example:\n\n```python\nimport multiai\n\n# Initialize the client\nclient = multiai.Prompt()\nclient.set_model('openai', 'gpt-4o') # Set model\nclient.temperature = 0.5 # Set temperature\n\n# Send a prompt and get a response\nanswer = client.ask('hi')\nprint(answer)\n\n# Continue the conversation with context\nanswer = client.ask('how are you')\nprint(answer)\n\n# Clear the conversation context\nclient.clear()\n```\n\nThe manual includes the following sample codes:\n\n- A script that translates a text file into English.\n- A local chat app that allows you to easily select from various AI models provided by different providers and engage in conversations with them.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A Python library for text-based AI interactions",
"version": "0.8",
"project_urls": {
"Documentation": "https://sekika.github.io/multiai/",
"Homepage": "https://sekika.github.io/multiai/",
"Source": "https://github.com/sekika/multiai"
},
"split_keywords": [
"ai"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "962a2ebc653b5f78ed8bf8004f3761870681740476628a9d01f4ab31fd224d8b",
"md5": "c336f2b883ed4404e46fcc52e4f0729e",
"sha256": "a7554da7219f744f090d64a567e2ccd35535abf522e7cbac0d34eec14b56d8d4"
},
"downloads": -1,
"filename": "multiai-0.8-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c336f2b883ed4404e46fcc52e4f0729e",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 12201,
"upload_time": "2024-08-18T17:19:44",
"upload_time_iso_8601": "2024-08-18T17:19:44.013646Z",
"url": "https://files.pythonhosted.org/packages/96/2a/2ebc653b5f78ed8bf8004f3761870681740476628a9d01f4ab31fd224d8b/multiai-0.8-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "7e61418a26842823bdba3ddb9631acfbc1e4cd91e9c19dae989d801f2e1c6fb4",
"md5": "951c2a632945b3353217111ccbaa80ef",
"sha256": "86a991d2db94a64819a08d8d243a6363c29ad180493582d6037806daaba945b4"
},
"downloads": -1,
"filename": "multiai-0.8.tar.gz",
"has_sig": false,
"md5_digest": "951c2a632945b3353217111ccbaa80ef",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 12779,
"upload_time": "2024-08-18T17:19:45",
"upload_time_iso_8601": "2024-08-18T17:19:45.907892Z",
"url": "https://files.pythonhosted.org/packages/7e/61/418a26842823bdba3ddb9631acfbc1e4cd91e9c19dae989d801f2e1c6fb4/multiai-0.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-18 17:19:45",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "sekika",
"github_project": "multiai",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "multiai"
}
