{"id":14964682,"url":"https://github.com/tak-bro/aipick","last_synced_at":"2025-10-24T17:45:01.547Z","repository":{"id":250142905,"uuid":"832894937","full_name":"tak-bro/aipick","owner":"tak-bro","description":"An interactive CLI tool that leverages Ollama, ChatGPT, Gemini, Claude, Mistral and other AI.","archived":false,"fork":false,"pushed_at":"2024-08-16T06:11:09.000Z","size":7878,"stargazers_count":10,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-30T07:36:44.771Z","etag":null,"topics":["aicommit2","aipick","anthropic","chatgpt","claude","cli","codestral","cohere","command-line","gemini","groq","huggingface","llama3","llm","mistral","ollama","openai","perplexity"],"latest_commit_sha":null,"homepage":"https://www.npmjs.com/package/aipick","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tak-bro.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":"tak-bro"}},"created_at":"2024-07-24T00:22:08.000Z","updated_at":"2025-08-14T13:42:55.000Z","dependencies_parsed_at":"2024-09-01T00:01:12.652Z","dependency_job_id":"6fa77da9-6b38-4d65-b3ea-4df54a717663","html_url":"https://github.com/tak-bro/aipick","commit_stats":{"total_commits":17,"total_committers":2,"mean_commits":8.5,"dds":"0.17647058823529416","last_synced_commit":"6dca07b363d679ee07298ab7766c06ef02be5ed8"},"previous_names":["tak-bro/aipick"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/tak-bro/aipick","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tak-bro%2Faipick","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tak-bro%2Faipick/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tak-bro%2Faipick/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tak-bro%2Faipick/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tak-bro","download_url":"https://codeload.github.com/tak-bro/aipick/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tak-bro%2Faipick/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278592440,"owners_count":26012292,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-06T02:00:05.630Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aicommit2","aipick","anthropic","chatgpt","claude","cli","codestral","cohere","command-line","gemini","groq","huggingface","llama3","llm","mistral","ollama","openai","perplexity"],"created_at":"2024-09-24T13:33:37.421Z","updated_at":"2025-10-06T10:31:45.425Z","avatar_url":"https://github.com/tak-bro.png","language":"TypeScript","funding_links":["https://github.com/sponsors/tak-bro"],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cdiv\u003e\n    \u003cimg src=\"https://github.com/tak-bro/aipick/blob/main/img/demo_min.gif?raw=true\" alt=\"AIPick\"/\u003e\n    \u003ch1 align=\"center\"\u003eAIPick\u003c/h1\u003e\n  \u003c/div\u003e\n  \u003cp\u003e\n    An interactive CLI tool leveraging multiple AI models for quick handling of simple requests\n  \u003c/p\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\" markdown=\"1\"\u003e\n\n[![tak-bro](https://img.shields.io/badge/by-tak--bro-293462?logo=github)](https://github.com/tak-bro)\n[![license](https://img.shields.io/badge/license-MIT-211A4C.svg?logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIGZpbGw9Im5vbmUiIHN0cm9rZT0iI0ZGRiIgdmlld0JveD0iMCAwIDI0IDI0Ij48cGF0aCBzdHJva2UtbGluZWNhcD0icm91bmQiIHN0cm9rZS1saW5lam9pbj0icm91bmQiIHN0cm9rZS13aWR0aD0iMiIgZD0ibTMgNiAzIDFtMCAwLTMgOWE1IDUgMCAwIDAgNi4wMDEgME02IDdsMyA5TTYgN2w2LTJtNiAyIDMtMW0tMyAxLTMgOWE1IDUgMCAwIDAgNi4wMDEgME0xOCA3bDMgOW0tMy05LTYtMm0wLTJ2Mm0wIDE2VjVtMCAxNkg5bTMgMGgzIi8+PC9zdmc+)](https://github.com/tak-bro/aipick/blob/main/LICENSE)\n[![version](https://img.shields.io/npm/v/aipick?logo=semanticrelease\u0026label=release\u0026color=A51C2D)](https://www.npmjs.com/package/aipick)\n[![downloads](https://img.shields.io/npm/dt/aipick?color=F33535\u0026logo=npm)](https://www.npmjs.com/package/aipick)\n\n\u003c/div\u003e\n\n---\n\n## Introduction\n\n_aipick_ is an interactive CLI tool leveraging multiple AI models for quick and efficient handling of simple requests such as variable name recommendations.\n\n## Key Features\n\n- **Multi-AI Support**: Integrates with OpenAI, Anthropic Claude, Google Gemini, Mistral AI, and more.\n- **Reactive CLI**: Enables simultaneous requests to multiple AIs and selection of the best AI response.\n- **Custom System Prompt**: Supports user-defined system prompt templates.\n- **Clipboard Integration**: Automatically copies selected responses to the clipboard for easy use.\n\n## Supported Providers\n\n### Remote\n\n- [OpenAI](https://openai.com/)\n- [Anthropic Claude](https://console.anthropic.com/)\n- [Gemini](https://gemini.google.com/)\n- [Mistral AI](https://mistral.ai/) (including [Codestral](https://mistral.ai/news/codestral/))\n- [Cohere](https://cohere.com/)\n- [Groq](https://groq.com/)\n- [Perplexity](https://docs.perplexity.ai/)\n- [Huggingface **(Unofficial)**](https://huggingface.co/chat/)\n\n### Local\n\n- [Ollama](https://ollama.com/)\n\n## Setup\n\n\u003e The minimum supported version of Node.js is the v18. Check your Node.js version with `node --version`.\n\n1. Install _aipick_:\n\n```sh\nnpm install -g aipick\n```\n\n2. Set up API keys (**at least one key must be set**):\n\n```sh\naipick config set OPENAI.key=\u003cyour key\u003e\naipick config set ANTHROPIC.key=\u003cyour key\u003e\n# ... (similar commands for other providers)\n```\n\n3. Run aipick:\n\n```sh\naipick -m \"Why is the sky blue?\"\n```\n\n\u003e 👉 **Tip:** Use the `aip` alias if `aipick` is too long for you.\n\n## Using Locally\n\nYou can also use your model for free with [Ollama](https://ollama.com/) and it is available to use both Ollama and remote providers **simultaneously**.\n\n1. Install Ollama from [https://ollama.com](https://ollama.com/)\n\n2. Start it with your model\n\n```shell\nollama run llama3.1 # model you want use. ex) codestral, gemma2\n```\n\n3. Set the model and host\n\n```sh\naipick config set OLLAMA.model=\u003cyour model\u003e\n```\n\n\u003e If you want to use ollama, you must set **OLLAMA.model**.\n\n4. Run _aipick_ \n```shell\naipick -m \"Why is the sky blue?\"\n```\n\n\u003e 👉 **Tip:** Ollama can run LLMs **in parallel** from v0.1.33. Please see [this section](#loading-multiple-ollama-models).\n\n\n## Usage\n\n### CLI Options\n\n- `--message` or `-m`: Message to ask AI (required)\n- `--systemPrompt` or `-s`: System prompt for fine-tuning\n\nExample:\n```sh\naipick --message \"Explain quantum computing\" --systemPrompt \"You are a physics expert\"\n```\n\n### Configuration\n\n#### Reading and Setting Configuration\n\n- Read: `aipick config get \u003ckey\u003e`\n- Set: `aipick config set \u003ckey\u003e=\u003cvalue\u003e`\n\nExample:\n```sh\naipick config get OPENAI.key\naipick config set OPENAI.generate=3 GEMINI.temperature=0.5\n```\n\n#### How to Configure in detail\n\n1. Command-line arguments: **use the format** `--[ModelName].[SettingKey]=value`\n\n```sh\naipick -m \"Why is the sky blue?\" --OPENAI.generate=3\n```\n\n2. Configuration file: **use INI format in the `~/.aipick` file or use `set` command**.\n   Example `~/.aipick`:\n```ini\n# General Settings\nlogging=true\ntemperature=1.0\n\n[OPENAI]\n# Model-Specific Settings\nkey=\"\u003cyour-api-key\u003e\"\ntemperature=0.8\ngenerate=2\n\n[OLLAMA]\ntemperature=0.7\nmodel[]=llama3.1\nmodel[]=codestral\n```\n\n\u003e The priority of settings is: **Command-line Arguments \u003e Model-Specific Settings \u003e General Settings \u003e Default Values**.\n\n## General Settings\n\nThe following settings can be applied to most models, but support may vary.\nPlease check the documentation for each specific model to confirm which settings are supported.\n\n| Setting            | Description                          | Default  |\n|--------------------|--------------------------------------|----------|\n| `systemPrompt`     | System Prompt text                   | -        |\n| `systemPromptPath` | Path to system prompt file           | -        |\n| `timeout`          | Request timeout (milliseconds)       | 10000    |\n| `temperature`      | Model's creativity (0.0 - 2.0)       | 0.7      |\n| `maxTokens`        | Maximum number of tokens to generate | 1024     |\n| `logging`          | Enable logging                       | true     |\n\n\n\u003e 👉 **Tip:** To set the General Settings for each model, use the following command.\n\u003e ```shell\n\u003e aipick config set OPENAI.maxTokens=\"2048\"\n\u003e aipick config set ANTHROPIC.logging=false\n\u003e ```\n\n##### systemPrompt\n- Allow users to specify a custom system prompt\n\n```sh\naipick config set systemPrompt=\"Your communication style is friendly, engaging, and informative.\"\n```\n\n\u003e `systemPrompt` takes precedence over `SystemPromptPath` and does not apply at the same time.\n\n##### systemPromptPath\n- Allow users to specify a custom file path for their own system prompt template\n- Please see [Custom Prompt Template](#custom-prompt-template)\n\n```sh\naipick config set systemPromptPath=\"/path/to/user/prompt.txt\"\n```\n\n##### timeout\n\nThe timeout for network requests in milliseconds.\n\nDefault: `10_000` (10 seconds)\n\n```sh\naipick config set timeout=20000 # 20s\n```\n\n##### temperature\n\nThe temperature (0.0-2.0) is used to control the randomness of the output\n\nDefault: `0.7`\n\n```sh\naipick config set temperature=0\n```\n\n##### maxTokens\n\nThe maximum number of tokens that the AI models can generate.\n\nDefault: `1024`\n\n```sh\naipick config set maxTokens=3000\n```\n\n##### logging\n\nDefault: `true`\n\nOption that allows users to decide whether to generate a log file capturing the responses.\nThe log files will be stored in the `~/.aipick_log` directory(user's home).\n\n- You can remove all logs below comamnd.\n\n```sh\naipick log removeAll \n```\n\n## Model-Specific Settings\n\n\u003e Some models mentioned below are subject to change.\n\n### OpenAI\n\n| Setting            | Description                               | Default                |\n|--------------------|-------------------------------------------|------------------------|\n| `key`              | API key                                   | -                      |\n| `model`            | Model to use                              | `gpt-3.5-turbo`        |\n| `url`              | API endpoint URL                          | https://api.openai.com |\n| `path`             | API path                                  | /v1/chat/completions   |\n| `proxy`            | Proxy settings                            | -                      |\n| `generate`         | Number of responses to generate (1-5)     | 1                      |\n\n##### OPENAI.key\n\nThe OpenAI API key. You can retrieve it from [OpenAI API Keys page](https://platform.openai.com/account/api-keys).\n\n```sh\naipick config set OPENAI.key=\"your api key\"\n```\n\n##### OPENAI.model\n\nDefault: `gpt-3.5-turbo`\n\nThe Chat Completions (`/v1/chat/completions`) model to use. Consult the list of models available in the [OpenAI Documentation](https://platform.openai.com/docs/models/model-endpoint-compatibility).\n\n\u003e Tip: If you have access, try upgrading to [`gpt-4`](https://platform.openai.com/docs/models/gpt-4) for next-level code analysis. It can handle double the input size, but comes at a higher cost. Check out OpenAI's website to learn more.\n\n```sh\naipick config set OPENAI.model=gpt-4\n```\n\n##### OPENAI.url\n\nDefault: `https://api.openai.com`\n\nThe OpenAI URL. Both https and http protocols supported. It allows to run local OpenAI-compatible server.\n\n##### OPENAI.path\n\nDefault: `/v1/chat/completions`\n\nThe OpenAI Path.\n\n##### OPENAI.generate\n\nDefault: `1`\n\nThe number of commit messages to generate to pick from.\n\nNote, this will use more tokens as it generates more results.\n\n```sh\naipick config set OPENAI.generate=2\n```\n\n### Ollama\n\n| Setting            | Description                            | Default                |\n|--------------------|----------------------------------------|------------------------|\n| `model`            | Model(s) to use (comma-separated list) | -                      |\n| `host`             | Ollama host URL                        | http://localhost:11434 |\n| `timeout`          | Request timeout (milliseconds)         | 100_000                |\n\n##### OLLAMA.model\n\nThe Ollama Model. Please see [a list of models available](https://ollama.com/library)\n\n```sh\naipick config set OLLAMA.model=\"llama3\"\naipick config set OLLAMA.model=\"llama3,codellama\" # for multiple models\n\naipick config add OLLAMA.model=\"gemma2\" # Only Ollama.model can be added.\n```\n\n\u003e OLLAMA.model is only **string array** type to support multiple Ollama. Please see [this section](#loading-multiple-ollama-models).\n\n##### OLLAMA.host\n\nDefault: `http://localhost:11434`\n\nThe Ollama host\n\n```sh\naipick config set OLLAMA.host=\u003chost\u003e\n```\n\n##### OLLAMA.timeout\n\nDefault: `10_000` (10 seconds)\n\nRequest timeout for the Ollama.\n\n```sh\naipick config set OLLAMA.timeout=\u003ctimeout\u003e\n```\n\n##### Unsupported Options\n\nOllama does not support the following options in General Settings.\n\n- maxTokens\n\n### HuggingFace\n\n| Setting            | Description                                                                                                      | Default                                |\n|--------------------|------------------------------------------------------------------------------------------------------------------|----------------------------------------|\n| `cookie`           | Authentication cookie                                                                                            | -                                      |\n| `model`            | Model to use                                                                                                     | `CohereForAI/c4ai-command-r-plus`      |\n\n##### HUGGINGFACE.cookie\n\nThe [Huggingface Chat](https://huggingface.co/chat/) Cookie. Please check [how to get cookie](https://github.com/tak-bro/aipick?tab=readme-ov-file#how-to-get-cookieunofficial-api)\n\n```sh\n# Please be cautious of Escape characters(\\\", \\') in browser cookie string\naipick config set HUGGINGFACE.cookie=\"your-cooke\"\n```\n\n##### HUGGINGFACE.model\n\nDefault: `CohereForAI/c4ai-command-r-plus`\n\nSupported:\n- `CohereForAI/c4ai-command-r-plus`\n- `meta-llama/Meta-Llama-3-70B-Instruct`\n- `HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1`\n- `mistralai/Mixtral-8x7B-Instruct-v0.1`\n- `NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO`\n- `01-ai/Yi-1.5-34B-Chat`\n- `mistralai/Mistral-7B-Instruct-v0.2`\n- `microsoft/Phi-3-mini-4k-instruct`\n\n```sh\naipick config set HUGGINGFACE.model=\"mistralai/Mistral-7B-Instruct-v0.2\"\n```\n\n##### Unsupported Options\n\nHuggingface does not support the following options in General Settings.\n\n- maxTokens\n- timeout\n- temperature\n\n### Gemini\n\n| Setting            | Description      | Default                 |\n|--------------------|------------------|-------------------------|\n| `key`              | API key          | -                       |\n| `model`            | Model to use     | `gemini-1.5-pro-latest` |\n\n##### GEMINI.key\n\nThe Gemini API key. If you don't have one, create a key in [Google AI Studio](https://aistudio.google.com/app/apikey).\n\n```sh\naipick config set GEMINI.key=\"your api key\"\n```\n\n##### GEMINI.model\n\nDefault: `gemini-1.5-pro-latest`\n\nSupported:\n- `gemini-1.5-pro-latest`\n- `gemini-1.5-flash-latest`\n\n```sh\naipick config set GEMINI.model=\"gemini-1.5-flash-latest\"\n```\n\n##### Unsupported Options\n\nGemini does not support the following options in General Settings.\n\n- timeout\n \n### Anthropic\n\n| Setting            | Description              | Default                   |\n|--------------------|--------------------------|---------------------------|\n| `key`              | API key                  | -                         |\n| `model`            | Model to use             | `claude-3-haiku-20240307` |\n\n##### ANTHROPIC.key\n\nThe Anthropic API key. To get started with Anthropic Claude, request access to their API at [anthropic.com/earlyaccess](https://www.anthropic.com/earlyaccess).\n\n##### ANTHROPIC.model\n\nDefault: `claude-3-haiku-20240307`\n\nSupported:\n- `claude-3-haiku-20240307`\n- `claude-3-sonnet-20240229`\n- `claude-3-opus-20240229`\n- `claude-3-5-sonnet-20240620`\n\n```sh\naipick config set ANTHROPIC.model=\"claude-3-5-sonnet-20240620\"\n```\n\n##### Unsupported Options\n\nAnthropic does not support the following options in General Settings.\n\n- timeout\n \n### Mistral\n\n| Setting            | Description       | Default        |\n|--------------------|-------------------|----------------|\n| `key`              | API key           | -              |\n| `model`            | Model to use      | `mistral-tiny` |\n\n##### MISTRAL.key\n\nThe Mistral API key. If you don't have one, please sign up and subscribe in [Mistral Console](https://console.mistral.ai/).\n\n##### MISTRAL.model\n\nDefault: `mistral-tiny`\n\nSupported:\n- `open-mistral-7b`\n- `mistral-tiny-2312`\n- `mistral-tiny`\n- `open-mixtral-8x7b`\n- `mistral-small-2312`\n- `mistral-small`\n- `mistral-small-2402`\n- `mistral-small-latest`\n- `mistral-medium-latest`\n- `mistral-medium-2312`\n- `mistral-medium`\n- `mistral-large-latest`\n- `mistral-large-2402`\n- `mistral-embed`\n\n### Codestral\n\n| Setting            | Description     | Default            |\n|--------------------|-----------------|--------------------|\n| `key`              | API key         | -                  |\n| `model`            | Model to use    | `codestral-latest` |\n\n##### CODESTRAL.key\n\nThe Codestral API key. If you don't have one, please sign up and subscribe in [Mistral Console](https://console.mistral.ai/codestral).\n\n##### CODESTRAL.model\n\nDefault: `codestral-latest`\n\nSupported:\n- `codestral-latest`\n- `codestral-2405`\n\n```sh\naipick config set CODESTRAL.model=\"codestral-2405\"\n```\n\n#### Cohere\n\n| Setting            | Description             | Default           |\n|--------------------|-------------------------|-------------------|\n| `key`              | API key                 | -                 |\n| `model`            | Model to use            | `command`  |\n\n##### COHERE.key\n\nThe Cohere API key. If you don't have one, please sign up and get the API key in [Cohere Dashboard](https://dashboard.cohere.com/).\n\n##### COHERE.model\n\nDefault: `command`\n\nSupported models:\n- `command`\n- `command-nightly`\n- `command-light`\n- `command-light-nightly`\n\n```sh\naipick config set COHERE.model=\"command-r\"\n```\n\n##### Unsupported Options\n\nCohere does not support the following options in General Settings.\n\n- timeout\n\n### Groq\n\n| Setting            | Description                                                                                                      | Default       |\n|--------------------|------------------------------------------------------------------------------------------------------------------|---------------|\n| `key`              | API key                                                                                                          | -             |\n| `model`            | Model to use                                                                                                     | `gemma-7b-it` |\n\n##### GROQ.key\n\nThe Groq API key. If you don't have one, please sign up and get the API key in [Groq Console](https://console.groq.com).\n\n##### GROQ.model\n\nDefault: `gemma2-9b-it`\n\nSupported:\n- `gemma2-9b-it`\n- `gemma-7b-it`\n- `llama-3.1-70b-versatile`\n- `llama-3.1-8b-instant`\n- `llama3-70b-8192`\n- `llama3-8b-8192`\n- `llama3-groq-70b-8192-tool-use-preview`\n- `llama3-groq-8b-8192-tool-use-preview`\n\n```sh\naipick config set GROQ.model=\"llama3-8b-8192\"\n```\n\n### Perplexity\n\n| Setting            | Description      | Default                           |\n|--------------------|------------------|-----------------------------------|\n| `key`              | API key          | -                                 |\n| `model`            | Model to use     | `llama-3.1-sonar-small-128k-chat` |\n\n##### PERPLEXITY.key\n\nThe Perplexity API key. If you don't have one, please sign up and get the API key in [Perplexity](https://docs.perplexity.ai/)\n\n##### PERPLEXITY.model\n\nDefault: `llama-3.1-sonar-small-128k-chat`\n\nSupported:\n- `llama-3.1-sonar-small-128k-chat`\n- `llama-3.1-sonar-large-128k-chat`\n- `llama-3.1-sonar-large-128k-online`\n- `llama-3.1-sonar-small-128k-online`\n- `llama-3.1-8b-instruct`\n- `llama-3.1-70b-instruct`\n- `llama-3.1-8b`\n- `llama-3.1-70b`\n\n\u003e The models mentioned above are subject to change.\n\n```sh\naipick config set PERPLEXITY.model=\"llama-3.1-70b\"\n```\n\n## Upgrading\n\nCheck the installed version with:\n\n```\naipick --version\n```\n\nIf it's not the [latest version](https://github.com/tak-bro/aipick/releases/latest), run:\n\n```sh\nnpm update -g aipick\n```\n\n## Custom Prompt Template\n\n_aipick_ supports custom prompt templates through the `systemPromptPath` option. This feature allows you to define your own system prompt structure, giving you more control over the AI response generation process.\n\n#### Using the promptPath Option\nTo use a custom prompt template, specify the path to your template file when running the tool:\n\n```\naipick config set systemPromptPath=\"/path/to/user/prompt.txt\"\n```\n\n#### Example Template\n\nHere's an example of how your custom system template might look:\n\n```\nYou are a Software Development Tutor.\nYour mission is to guide users from zero knowledge to understanding the fundamentals of software.\nBe patient, clear, and thorough in your explanations, and adapt to the user's knowledge and pace of learning.\n```\n\n\u003e NOTE\n\u003e - For the `systemPromptPath` option, set the **template path**, not the template content.\n\u003e - If you want to set the template content, use [`systemPrompt`](#systemprompt) option\n\n## Loading Multiple Ollama Models\n\nYou can load and make simultaneous requests to multiple models using Ollama's experimental feature, the `OLLAMA_MAX_LOADED_MODELS` option.\n- `OLLAMA_MAX_LOADED_MODELS`: Load multiple models simultaneously\n\n#### Setup Guide\n\nFollow these steps to set up and utilize multiple models simultaneously:\n\n##### 1. Running Ollama Server\n\nFirst, launch the Ollama server with the `OLLAMA_MAX_LOADED_MODELS` environment variable set. This variable specifies the maximum number of models to be loaded simultaneously. \nFor example, to load up to 3 models, use the following command:\n\n```shell\nOLLAMA_MAX_LOADED_MODELS=3 ollama serve\n```\n\u003e Refer to [configuration](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-configure-ollama-server) for detailed instructions.\n\n##### 2. Configuring _aipick_\n\nNext, set up _aipick_ to specify multiple models. You can assign a list of models, separated by **commas(`,`)**, to the **OLLAMA.model** environment variable. Here's how you do it:\n\n```shell\naipick config set OLLAMA.model=\"mistral,llama3.1\"\n# or \naipick config add OLLAMA.model=\"mistral\"\naipick config add OLLAMA.model=\"llama3.1\"\n```\n\nWith this command, _aipick_ is instructed to utilize both the \"mistral\" and \"llama3.1\" models when making requests to the Ollama server.\n\n##### 3. Run _aipick_\n\n```shell\naipick\n```\n\n\u003e Note that this feature is available starting from Ollama version [**0.1.33**](https://github.com/ollama/ollama/releases/tag/v0.1.33).\n\n## How to get Cookie(**Unofficial API**)\n\n* Login to the site you want\n* You can get cookie from the browser's developer tools network tab\n* See for any requests check out the Cookie, **Copy whole value**\n* Check below image for the format of cookie\n\n\u003e When setting cookies with long string values, ensure to **escape characters** like \", ', and others properly.\n\u003e - For double quotes (\"), use \\\\\"\n\u003e - For single quotes ('), use \\\\'\n\n![how-to-get-cookie](https://github.com/tak-bro/aipick/blob/main/img/cookie-huggingface.png?raw=true)\n\n## Disclaimer and Risks\n\nThis project uses functionalities from external APIs but is not officially affiliated with or endorsed by their providers. Users are responsible for complying with API terms, rate limits, and policies.\n\n## Contributing\n\nFor bug fixes or feature implementations, please check the [Contribution Guide](CONTRIBUTING.md).\n\n---\n\nIf this project has been helpful, please consider giving it a Star ⭐️!\n\nMaintainer: [@tak-bro](https://env-tak.github.io/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftak-bro%2Faipick","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftak-bro%2Faipick","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftak-bro%2Faipick/lists"}