diff --git a/.github/dependabot.yml b/.github/dependabot.yml
new file mode 100644
index 0000000..b38df29
--- /dev/null
+++ b/.github/dependabot.yml
@@ -0,0 +1,6 @@
+version: 2
+updates:
+ - package-ecosystem: "pip"
+ directory: "/"
+ schedule:
+ interval: "daily"
diff --git a/README.md b/README.md
index 17befe0..b662cd6 100644
--- a/README.md
+++ b/README.md
@@ -16,6 +16,20 @@ Here's a demo of RA.Aid adding a feature to itself:
+## Documentation
+
+Complete documentation is available at https://docs.ra-aid.ai
+
+Key sections:
+- [Installation Guide](https://docs.ra-aid.ai/quickstart/installation)
+- [Recommended Configuration](https://docs.ra-aid.ai/quickstart/recommended)
+- [Open Models Setup](https://docs.ra-aid.ai/quickstart/open-models)
+- [Usage Examples](https://docs.ra-aid.ai/category/usage)
+- [Contributing Guide](https://docs.ra-aid.ai/contributing)
+- [Getting Help](https://docs.ra-aid.ai/getting-help)
+
+## Table of Contents
+
- [Features](#features)
- [Installation](#installation)
- [Usage](#usage)
@@ -91,14 +105,7 @@ pip install ra-aid
### Prerequisites
-Before using RA.Aid, you'll need:
-
-1. Python package `aider` installed and available in your PATH:
-```bash
-pip install aider-chat
-```
-
-2. API keys for the required AI services:
+Before using RA.Aid, you'll need API keys for the required AI services:
```bash
# Set up API keys based on your preferred provider:
@@ -106,7 +113,7 @@ pip install aider-chat
# For Anthropic Claude models (recommended)
export ANTHROPIC_API_KEY=your_api_key_here
-# For OpenAI models
+# For OpenAI models (optional)
export OPENAI_API_KEY=your_api_key_here
# For OpenRouter provider (optional)
@@ -133,6 +140,8 @@ You can get your API keys from:
- OpenRouter API key: https://openrouter.ai/keys
- Gemini API key: https://aistudio.google.com/app/apikey
+Complete installation documentation is available in our [Installation Guide](https://docs.ra-aid.ai/quickstart/installation).
+
## Usage
RA.Aid is designed to be simple yet powerful. Here's how to use it:
@@ -148,6 +157,8 @@ ra-aid -m "Explain the authentication flow" --research-only
ra-aid -m "Add new feature" --verbose
```
+More information is available in our [Usage Examples](https://docs.ra-aid.ai/category/usage).
+
### Command Line Options
- `-m, --message`: The task or query to be executed (required except in chat mode)
@@ -428,6 +439,8 @@ Note: For `AIDER_FLAGS`, you can specify flags with or without the leading `--`.
- Model configuration is done via command line arguments: `--provider` and `--model`
- The `--model` argument is required for all providers except Anthropic (which defaults to `claude-3-5-sonnet-20241022`)
+More information is available in our [Open Models Setup](https://docs.ra-aid.ai/quickstart/open-models) guide.
+
## Architecture
RA.Aid implements a three-stage architecture for handling development and research tasks:
@@ -524,6 +537,8 @@ git push origin feature/your-feature-name
- Keep commits focused and message clear
- Ensure all tests pass before submitting PR
+More information is available in our [Contributing Guide](https://docs.ra-aid.ai/contributing).
+
## License
This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
diff --git a/assets/favicon.ico b/assets/favicon.ico
new file mode 100644
index 0000000..d933be3
Binary files /dev/null and b/assets/favicon.ico differ
diff --git a/docs/docs/contributing.md b/docs/docs/contributing.md
new file mode 100644
index 0000000..3d0e7a6
--- /dev/null
+++ b/docs/docs/contributing.md
@@ -0,0 +1,79 @@
+# Contributing to RA.Aid
+
+Welcome to the RA.Aid community! We're thrilled you're interested in contributing. This project thrives thanks to contributors like you, and we're excited to have you join us on this journey.
+
+## Ways to Contribute
+
+There are many valuable ways to contribute to RA.Aid:
+
+### 1. Join Our Community
+- Join our Discord community to connect with other users and contributors
+- Help answer questions from other users
+- Share your experiences and use cases
+- Provide feedback and suggestions
+
+### 2. Report Issues
+- Found a bug? Open an issue on our [GitHub repository](https://github.com/ai-christianson/RA.Aid/issues)
+- Before creating a new issue, please check if it already exists
+- Include as much detail as possible:
+ - Steps to reproduce
+ - Expected vs actual behavior
+ - Your environment (OS, Python version, etc.)
+ - Any relevant error messages
+
+### 3. Contribute to Documentation
+- Our documentation lives in the `docs/` folder
+- Found a typo? Have an idea for better explanations? Open a PR!
+- You can use RA.Aid itself to help draft documentation changes
+- Even small improvements are welcome
+
+### 4. Code Contributions
+- Look for issues labeled "help wanted" or "good first issue" on our GitHub
+- Feel free to pick up any open issue - don't be shy!
+- **You can even use RA.Aid to help understand the codebase and make changes**
+- Before starting work on larger changes, please open an issue to discuss
+
+## Making Your First Contribution
+
+1. Fork the repository
+2. Create a branch for your changes
+3. Make your changes
+4. Write/update tests if needed
+5. Submit a Pull Request
+6. Wait for review and address any feedback
+
+Don't hesitate to ask questions if you're unsure about anything. Remember: every expert was once a beginner!
+
+## Development Setup
+
+1. Clone the repository:
+
+```bash
+git clone https://github.com/ai-christianson/RA.Aid.git
+cd RA.Aid
+```
+
+2. Create and activate a virtual environment:
+
+```bash
+python -m venv venv
+source venv/bin/activate
+```
+
+3. Install in dev mode:
+
+```bash
+pip install -e .
+```
+
+4. Run RA.Aid:
+
+```bash
+ra-aid -m "Your task or query here"
+```
+
+## This is Your Project Too
+
+RA.Aid is a community project that grows stronger with each contribution. Whether it's fixing a typo in documentation, reporting a bug, or adding a new feature - every contribution matters and is valued.
+
+Don't feel like you need to make massive changes to contribute. Small, focused contributions are often the best way to start. Use what you know, and learn as you go!
diff --git a/docs/docs/getting-help.md b/docs/docs/getting-help.md
new file mode 100644
index 0000000..fe13d0f
--- /dev/null
+++ b/docs/docs/getting-help.md
@@ -0,0 +1,11 @@
+# Getting Help
+
+## Bug Reports and Feature Requests
+
+If you encounter any issues or have ideas for improvements, please file them on our [GitHub Issues page](https://github.com/ai-christianson/RA.Aid/issues).
+
+## Community Support
+
+Join our Discord community to chat with other users and get help:
+
+- [Join the Discord Server](https://discord.gg/f6wYbzHYxV)
diff --git a/docs/docs/getting-started.md b/docs/docs/getting-started.md
deleted file mode 100644
index 31f793a..0000000
--- a/docs/docs/getting-started.md
+++ /dev/null
@@ -1 +0,0 @@
----\nsidebar_position: 1\n---\n\n# Getting Started\n\nWelcome to the documentation. This page will help you get started.
diff --git a/docs/docs/intro.md b/docs/docs/intro.md
index acd2ad2..c529780 100644
--- a/docs/docs/intro.md
+++ b/docs/docs/intro.md
@@ -3,46 +3,54 @@ sidebar_position: 1
slug: /
---
-# Intro
+# Welcome to RA.Aid
-Let's discover **Docusaurus in less than 5 minutes**.
+RA.Aid (pronounced "raid") is your AI-powered development companion that helps you build software autonomously. Whether you're working on new features, refactoring code, or researching solutions, RA.Aid makes development faster and more efficient.
-## Getting Started
+## Why RA.Aid?
-Get started by **creating a new site**.
+- 🤖 **Autonomous Development**: Let RA.Aid handle complex programming tasks while you focus on the big picture
+- 🔍 **Smart Research**: Automatically researches solutions and best practices
+- 📋 **Intelligent Planning**: Breaks down complex tasks into manageable steps
+- 💬 **Interactive Mode**: Get help when you need it through natural conversation
-Or **try Docusaurus immediately** with **[docusaurus.new](https://docusaurus.new)**.
+## Quick Start
-### What you'll need
+Ready to get started? Jump right to:
-- [Node.js](https://nodejs.org/en/download/) version 18.0 or above:
- - When installing Node.js, you are recommended to check all checkboxes related to dependencies.
+- [Installation Guide](/quickstart/installation)
+- [Basic Usage Examples](/usage/modern-web-app)
-## Generate a new site
+### Basic Example
-Generate a new Docusaurus site using the **classic template**.
-
-The classic template will automatically be added to your project after you run the command:
+Here's how simple it is to use RA.Aid:
```bash
-npm init docusaurus@latest my-website classic
+# Install RA.Aid
+pip install ra-aid
+
+# Set up API keys
+export ANTHROPIC_API_KEY=your_key_here
+export OPENAI_API_KEY=your_key_here
+export TAVILY_API_KEY=your_key_here
+
+# Start using it
+ra-aid -m "Add input validation to the login form"
```
-You can type this command into Command Prompt, Powershell, Terminal, or any other integrated terminal of your code editor.
+## Key Features
-The command also installs all necessary dependencies you need to run Docusaurus.
+- **Three-Stage Workflow**: Research → Planning → Implementation
+- **Web Research**: Automatically searches for best practices and solutions
+- **Interactive Mode**: Get help when you need it through natural conversation
+- **Multiple AI Providers**: Support for various AI models to suit your needs
+- **Git Integration**: Works seamlessly with your version control
-## Start your site
+## Next Steps
-Run the development server:
+- Check out the [Installation Guide](/quickstart/installation) to set up RA.Aid
+- See [Usage Examples](/usage/modern-web-app) to get started quickly
+- Read our [Contributing Guide](/contributing) to get involved
+- Join our [Discord Community](https://discord.gg/f6wYbzHYxV) for help and discussions
-```bash
-cd my-website
-npm run start
-```
-
-The `cd` command changes the directory you're working with. In order to work with your newly created Docusaurus site, you'll need to navigate the terminal there.
-
-The `npm run start` command builds your website locally and serves it through a development server, ready for you to view at http://localhost:3000/.
-
-Open `docs/intro.md` (this page) and edit some lines: the site **reloads automatically** and displays your changes.
+Ready to revolutionize your development workflow? Let's get started! 🚀
diff --git a/docs/docs/quickstarts/_category_.json b/docs/docs/quickstart/_category_.json
similarity index 84%
rename from docs/docs/quickstarts/_category_.json
rename to docs/docs/quickstart/_category_.json
index 4e464dc..7a04160 100644
--- a/docs/docs/quickstarts/_category_.json
+++ b/docs/docs/quickstart/_category_.json
@@ -1,5 +1,5 @@
{
- "label": "Quick Starts",
+ "label": "Quick Start",
"position": 2,
"link": {
"type": "generated-index",
diff --git a/docs/docs/quickstart/installation.md b/docs/docs/quickstart/installation.md
new file mode 100644
index 0000000..d2bccea
--- /dev/null
+++ b/docs/docs/quickstart/installation.md
@@ -0,0 +1,70 @@
+---
+sidebar_position: 1
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Installation
+
+Getting started is easy! You can install RA.Aid using any of these three methods - pick the one that works best for you:
+
+
+
+
+Create a new Python 3.12 virtual environment and install RA.Aid:
+
+First install [uv](https://docs.astral.sh/uv/getting-started/installation/), then:
+
+```bash
+uv venv -p 3.12
+```
+
+
+
+
+```bash
+source .venv/bin/activate
+```
+
+
+
+
+```bash
+.venv\Scripts\activate
+```
+
+
+
+
+```bash
+uv pip install ra-aid
+```
+
+
+
+
+Install RA.Aid using pip:
+
+```bash
+pip install ra-aid
+```
+
+:::note
+If you're using Python 3.13 or newer, we recommend using the UV installation method instead due to compatibility issues with newer Python versions.
+:::
+
+
+
+
+Install RA.Aid using Homebrew:
+
+```bash
+brew tap ai-christianson/homebrew-ra-aid
+brew install ra-aid
+```
+
+
+
+
+Once installed, see the [Recommended Configuration](recommended) to set up RA.Aid with the recommended settings.
diff --git a/docs/docs/quickstart/open-models.md b/docs/docs/quickstart/open-models.md
new file mode 100644
index 0000000..42ce211
--- /dev/null
+++ b/docs/docs/quickstart/open-models.md
@@ -0,0 +1,180 @@
+---
+sidebar_position: 3
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Open Models Configuration
+
+RA.Aid supports a variety of open source and compatible model providers. This guide covers configuration options and best practices for using different models with RA.Aid.
+
+## Overview
+
+
+
+
+RA.Aid supports these model providers:
+
+| Provider | Description | Key Features |
+|----------|-------------|--------------|
+| DeepSeek | Chinese hedge fund who creates sophisticated LLMs | Strong, open models like R1 |
+| OpenRouter | Multi-model gateway service | Access to 100+ models, unified API interface, pay-per-token |
+| OpenAI-compatible | Self-hosted model endpoints | Compatible with Llama, Mistral and other open models |
+| Anthropic | Claude model series | 200k token context, strong tool use, JSON/XML parsing |
+| Gemini | Google's multimodal models | Code generation in 20+ languages, parallel request support |
+
+
+
+
+### Basic Configuration
+
+1. Set your provider's API key:
+```bash
+# Choose the appropriate provider
+export DEEPSEEK_API_KEY=your_key
+export OPENROUTER_API_KEY=your_key
+export OPENAI_API_KEY=your_key
+export ANTHROPIC_API_KEY=your_key
+export GEMINI_API_KEY=your_key
+```
+
+2. Run RA.Aid with your chosen provider:
+```bash
+ra-aid -m "Your task" --provider --model
+```
+
+
+
+
+## Provider Configuration
+
+
+
+
+### DeepSeek Models
+
+DeepSeek offers powerful reasoning models optimized for complex tasks.
+
+```bash
+# Environment setup
+export DEEPSEEK_API_KEY=your_api_key_here
+
+# Basic usage
+ra-aid -m "Your task" --provider deepseek --model deepseek-reasoner
+
+# With temperature control
+ra-aid -m "Your task" --provider deepseek --model deepseek-reasoner --temperature 0.7
+```
+
+**Available Models:**
+- `deepseek-reasoner`: Optimized for reasoning tasks
+- Access via OpenRouter: `deepseek/deepseek-r1`
+
+
+
+### OpenRouter Integration
+
+OpenRouter provides access to multiple open source models through a single API.
+
+```bash
+# Environment setup
+export OPENROUTER_API_KEY=your_api_key_here
+
+# Example commands
+ra-aid -m "Your task" --provider openrouter --model mistralai/mistral-large-2411
+ra-aid -m "Your task" --provider openrouter --model deepseek/deepseek-r1
+```
+
+**Popular Models:**
+- `mistralai/mistral-large-2411`
+- `anthropic/claude-3`
+- `deepseek/deepseek-r1`
+
+
+
+### OpenAI-compatible Endpoints
+
+Use OpenAI-compatible API endpoints with custom hosting solutions.
+
+```bash
+# Environment setup
+export OPENAI_API_KEY=your_api_key_here
+export OPENAI_API_BASE=https://your-api-endpoint
+
+# Usage
+ra-aid -m "Your task" --provider openai-compatible --model your-model-name
+```
+
+**Configuration Options:**
+- Set custom base URL with `OPENAI_API_BASE`
+- Supports temperature control
+- Compatible with most OpenAI-style APIs
+
+
+
+## Advanced Configuration
+
+
+
+
+### Expert Tool Configuration
+
+Configure the expert model for specialized tasks; this usually benefits from a more powerful, slower, reasoning model:
+
+```bash
+# DeepSeek expert
+export EXPERT_DEEPSEEK_API_KEY=your_key
+ra-aid -m "Your task" --expert-provider deepseek --expert-model deepseek-reasoner
+
+# OpenRouter expert
+export EXPERT_OPENROUTER_API_KEY=your_key
+ra-aid -m "Your task" --expert-provider openrouter --expert-model mistralai/mistral-large-2411
+```
+
+
+
+
+### Temperature Settings
+
+Control model creativity vs determinism:
+
+```bash
+# More deterministic (good for coding)
+ra-aid -m "Your task" --temperature 0.2
+
+# More creative (good for brainstorming)
+ra-aid -m "Your task" --temperature 0.8
+```
+
+**Note:** Not all models support temperature control. Check provider documentation.
+
+
+
+## Best Practices
+
+- Set environment variables in your shell configuration file
+- Use lower temperatures (0.1-0.3) for coding tasks
+- Test different models to find the best fit for your use case
+- Consider using expert mode for complex programming tasks
+
+## Environment Variables
+
+Complete list of supported environment variables:
+
+| Variable | Provider | Purpose |
+|----------|----------|----------|
+| `OPENROUTER_API_KEY` | OpenRouter | Main API access |
+| `DEEPSEEK_API_KEY` | DeepSeek | Main API access |
+| `OPENAI_API_KEY` | OpenAI-compatible | API access |
+| `OPENAI_API_BASE` | OpenAI-compatible | Custom endpoint |
+| `ANTHROPIC_API_KEY` | Anthropic | API access |
+| `GEMINI_API_KEY` | Gemini | API access |
+| `EXPERT_OPENROUTER_API_KEY` | OpenRouter | Expert tool |
+| `EXPERT_DEEPSEEK_API_KEY` | DeepSeek | Expert tool |
+
+## Troubleshooting
+
+- Verify API keys are set correctly
+- Check endpoint URLs for OpenAI-compatible setups
+- Monitor API rate limits and quotas
diff --git a/docs/docs/quickstarts/recommended.md b/docs/docs/quickstart/recommended.md
similarity index 98%
rename from docs/docs/quickstarts/recommended.md
rename to docs/docs/quickstart/recommended.md
index 4df30a7..38d519b 100644
--- a/docs/docs/quickstarts/recommended.md
+++ b/docs/docs/quickstart/recommended.md
@@ -1,3 +1,7 @@
+---
+sidebar_position: 2
+---
+
# Recommended Config
This configuration combines the strengths of multiple AI models to provide the best experience:
diff --git a/docs/docs/quickstarts/congratulations.md b/docs/docs/quickstarts/congratulations.md
deleted file mode 100644
index 04771a0..0000000
--- a/docs/docs/quickstarts/congratulations.md
+++ /dev/null
@@ -1,23 +0,0 @@
----
-sidebar_position: 6
----
-
-# Congratulations!
-
-You have just learned the **basics of Docusaurus** and made some changes to the **initial template**.
-
-Docusaurus has **much more to offer**!
-
-Have **5 more minutes**? Take a look at **[versioning](../tutorial-extras/manage-docs-versions.md)** and **[i18n](../tutorial-extras/translate-your-site.md)**.
-
-Anything **unclear** or **buggy** in this tutorial? [Please report it!](https://github.com/facebook/docusaurus/discussions/4610)
-
-## What's next?
-
-- Read the [official documentation](https://docusaurus.io/)
-- Modify your site configuration with [`docusaurus.config.js`](https://docusaurus.io/docs/api/docusaurus-config)
-- Add navbar and footer items with [`themeConfig`](https://docusaurus.io/docs/api/themes/configuration)
-- Add a custom [Design and Layout](https://docusaurus.io/docs/styling-layout)
-- Add a [search bar](https://docusaurus.io/docs/search)
-- Find inspirations in the [Docusaurus showcase](https://docusaurus.io/showcase)
-- Get involved in the [Docusaurus Community](https://docusaurus.io/community/support)
diff --git a/docs/docs/quickstarts/create-a-blog-post.md b/docs/docs/quickstarts/create-a-blog-post.md
deleted file mode 100644
index 550ae17..0000000
--- a/docs/docs/quickstarts/create-a-blog-post.md
+++ /dev/null
@@ -1,34 +0,0 @@
----
-sidebar_position: 3
----
-
-# Create a Blog Post
-
-Docusaurus creates a **page for each blog post**, but also a **blog index page**, a **tag system**, an **RSS** feed...
-
-## Create your first Post
-
-Create a file at `blog/2021-02-28-greetings.md`:
-
-```md title="blog/2021-02-28-greetings.md"
----
-slug: greetings
-title: Greetings!
-authors:
- - name: Joel Marcey
- title: Co-creator of Docusaurus 1
- url: https://github.com/JoelMarcey
- image_url: https://github.com/JoelMarcey.png
- - name: Sébastien Lorber
- title: Docusaurus maintainer
- url: https://sebastienlorber.com
- image_url: https://github.com/slorber.png
-tags: [greetings]
----
-
-Congratulations, you have made your first post!
-
-Feel free to play around and edit this post as much as you like.
-```
-
-A new blog post is now available at [http://localhost:3000/blog/greetings](http://localhost:3000/blog/greetings).
diff --git a/docs/docs/quickstarts/create-a-document.md b/docs/docs/quickstarts/create-a-document.md
deleted file mode 100644
index 28b0262..0000000
--- a/docs/docs/quickstarts/create-a-document.md
+++ /dev/null
@@ -1,57 +0,0 @@
----
-sidebar_position: 2
----
-
-# Create a Document
-
-Documents are **groups of pages** connected through:
-
-- a **sidebar**
-- **previous/next navigation**
-- **versioning**
-
-## Create your first Doc
-
-Create a Markdown file at `docs/hello.md`:
-
-```md title="docs/hello.md"
-# Hello
-
-This is my **first Docusaurus document**!
-```
-
-A new document is now available at [http://localhost:3000/docs/hello](http://localhost:3000/docs/hello).
-
-## Configure the Sidebar
-
-Docusaurus automatically **creates a sidebar** from the `docs` folder.
-
-Add metadata to customize the sidebar label and position:
-
-```md title="docs/hello.md" {1-4}
----
-sidebar_label: 'Hi!'
-sidebar_position: 3
----
-
-# Hello
-
-This is my **first Docusaurus document**!
-```
-
-It is also possible to create your sidebar explicitly in `sidebars.js`:
-
-```js title="sidebars.js"
-export default {
- tutorialSidebar: [
- 'intro',
- // highlight-next-line
- 'hello',
- {
- type: 'category',
- label: 'Tutorial',
- items: ['quickstarts/create-a-document'],
- },
- ],
-};
-```
diff --git a/docs/docs/quickstarts/create-a-page.md b/docs/docs/quickstarts/create-a-page.md
deleted file mode 100644
index e69de29..0000000
diff --git a/docs/docs/quickstarts/deploy-your-site.md b/docs/docs/quickstarts/deploy-your-site.md
deleted file mode 100644
index 1c50ee0..0000000
--- a/docs/docs/quickstarts/deploy-your-site.md
+++ /dev/null
@@ -1,31 +0,0 @@
----
-sidebar_position: 5
----
-
-# Deploy your site
-
-Docusaurus is a **static-site-generator** (also called **[Jamstack](https://jamstack.org/)**).
-
-It builds your site as simple **static HTML, JavaScript and CSS files**.
-
-## Build your site
-
-Build your site **for production**:
-
-```bash
-npm run build
-```
-
-The static files are generated in the `build` folder.
-
-## Deploy your site
-
-Test your production build locally:
-
-```bash
-npm run serve
-```
-
-The `build` folder is now served at [http://localhost:3000/](http://localhost:3000/).
-
-You can now deploy the `build` folder **almost anywhere** easily, **for free** or very small cost (read the **[Deployment Guide](https://docusaurus.io/docs/deployment)**).
diff --git a/docs/docs/quickstarts/installation.md b/docs/docs/quickstarts/installation.md
deleted file mode 100644
index 46d13d0..0000000
--- a/docs/docs/quickstarts/installation.md
+++ /dev/null
@@ -1,14 +0,0 @@
-# Installation
-
-Create a new Python 3.12 virtual environment and install RA.Aid:
-
-```bash
-uv venv -p 3.12
-source .venv/bin/activate # On Unix/macOS
-# or
-.venv\Scripts\activate # On Windows
-
-uv pip install ra-aid
-```
-
-Once installed, see the [Recommended Configuration](recommended) to set up RA.Aid with the recommended settings.
diff --git a/docs/docs/quickstarts/markdown-features.mdx b/docs/docs/quickstarts/markdown-features.mdx
deleted file mode 100644
index 1f42792..0000000
--- a/docs/docs/quickstarts/markdown-features.mdx
+++ /dev/null
@@ -1,152 +0,0 @@
----
-sidebar_position: 4
----
-
-# Markdown Features
-
-Docusaurus supports **[Markdown](https://daringfireball.net/projects/markdown/syntax)** and a few **additional features**.
-
-## Front Matter
-
-Markdown documents have metadata at the top called [Front Matter](https://jekyllrb.com/docs/front-matter/):
-
-```text title="my-doc.md"
-// highlight-start
----
-id: my-doc-id
-title: My document title
-description: My document description
-slug: /my-custom-url
----
-// highlight-end
-
-## Markdown heading
-
-Markdown text with [links](./hello.md)
-```
-
-## Links
-
-Regular Markdown links are supported, using url paths or relative file paths.
-
-```md
-Let's see how to [Create a page](/recommended).
-```
-
-```md
-Let's see how to [Create a page](./recommended.md).
-```
-
-**Result:** Let's see how to [Create a page](./recommended.md).
-
-## Images
-
-Regular Markdown images are supported.
-
-You can use absolute paths to reference images in the static directory (`static/img/docusaurus.png`):
-
-```md
-
-```
-
-
-
-You can reference images relative to the current file as well. This is particularly useful to colocate images close to the Markdown files using them:
-
-```md
-
-```
-
-## Code Blocks
-
-Markdown code blocks are supported with Syntax highlighting.
-
-````md
-```jsx title="src/components/HelloDocusaurus.js"
-function HelloDocusaurus() {
- return
Hello, Docusaurus!
;
-}
-```
-````
-
-```jsx title="src/components/HelloDocusaurus.js"
-function HelloDocusaurus() {
- return Hello, Docusaurus!
;
-}
-```
-
-## Admonitions
-
-Docusaurus has a special syntax to create admonitions and callouts:
-
-```md
-:::tip My tip
-
-Use this awesome feature option
-
-:::
-
-:::danger Take care
-
-This action is dangerous
-
-:::
-```
-
-:::tip My tip
-
-Use this awesome feature option
-
-:::
-
-:::danger Take care
-
-This action is dangerous
-
-:::
-
-## MDX and React Components
-
-[MDX](https://mdxjs.com/) can make your documentation more **interactive** and allows using any **React components inside Markdown**:
-
-```jsx
-export const Highlight = ({children, color}) => (
- {
- alert(`You clicked the color ${color} with label ${children}`)
- }}>
- {children}
-
-);
-
-This is Docusaurus green !
-
-This is Facebook blue !
-```
-
-export const Highlight = ({children, color}) => (
- {
- alert(`You clicked the color ${color} with label ${children}`);
- }}>
- {children}
-
-);
-
-This is Docusaurus green !
-
-This is Facebook blue !
diff --git a/docs/docs/tutorial-extras/_category_.json b/docs/docs/tutorial-extras/_category_.json
deleted file mode 100644
index a8ffcc1..0000000
--- a/docs/docs/tutorial-extras/_category_.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "label": "Tutorial - Extras",
- "position": 3,
- "link": {
- "type": "generated-index"
- }
-}
diff --git a/docs/docs/tutorial-extras/img/docsVersionDropdown.png b/docs/docs/tutorial-extras/img/docsVersionDropdown.png
deleted file mode 100644
index 97e4164..0000000
Binary files a/docs/docs/tutorial-extras/img/docsVersionDropdown.png and /dev/null differ
diff --git a/docs/docs/tutorial-extras/img/localeDropdown.png b/docs/docs/tutorial-extras/img/localeDropdown.png
deleted file mode 100644
index e257edc..0000000
Binary files a/docs/docs/tutorial-extras/img/localeDropdown.png and /dev/null differ
diff --git a/docs/docs/tutorial-extras/manage-docs-versions.md b/docs/docs/tutorial-extras/manage-docs-versions.md
deleted file mode 100644
index ccda0b9..0000000
--- a/docs/docs/tutorial-extras/manage-docs-versions.md
+++ /dev/null
@@ -1,55 +0,0 @@
----
-sidebar_position: 1
----
-
-# Manage Docs Versions
-
-Docusaurus can manage multiple versions of your docs.
-
-## Create a docs version
-
-Release a version 1.0 of your project:
-
-```bash
-npm run docusaurus docs:version 1.0
-```
-
-The `docs` folder is copied into `versioned_docs/version-1.0` and `versions.json` is created.
-
-Your docs now have 2 versions:
-
-- `1.0` at `http://localhost:3000/docs/` for the version 1.0 docs
-- `current` at `http://localhost:3000/docs/next/` for the **upcoming, unreleased docs**
-
-## Add a Version Dropdown
-
-To navigate seamlessly across versions, add a version dropdown.
-
-Modify the `docusaurus.config.js` file:
-
-```js title="docusaurus.config.js"
-export default {
- themeConfig: {
- navbar: {
- items: [
- // highlight-start
- {
- type: 'docsVersionDropdown',
- },
- // highlight-end
- ],
- },
- },
-};
-```
-
-The docs version dropdown appears in your navbar:
-
-
-
-## Update an existing version
-
-It is possible to edit versioned docs in their respective folder:
-
-- `versioned_docs/version-1.0/hello.md` updates `http://localhost:3000/docs/hello`
-- `docs/hello.md` updates `http://localhost:3000/docs/next/hello`
diff --git a/docs/docs/tutorial-extras/translate-your-site.md b/docs/docs/tutorial-extras/translate-your-site.md
deleted file mode 100644
index b5a644a..0000000
--- a/docs/docs/tutorial-extras/translate-your-site.md
+++ /dev/null
@@ -1,88 +0,0 @@
----
-sidebar_position: 2
----
-
-# Translate your site
-
-Let's translate `docs/intro.md` to French.
-
-## Configure i18n
-
-Modify `docusaurus.config.js` to add support for the `fr` locale:
-
-```js title="docusaurus.config.js"
-export default {
- i18n: {
- defaultLocale: 'en',
- locales: ['en', 'fr'],
- },
-};
-```
-
-## Translate a doc
-
-Copy the `docs/intro.md` file to the `i18n/fr` folder:
-
-```bash
-mkdir -p i18n/fr/docusaurus-plugin-content-docs/current/
-
-cp docs/intro.md i18n/fr/docusaurus-plugin-content-docs/current/intro.md
-```
-
-Translate `i18n/fr/docusaurus-plugin-content-docs/current/intro.md` in French.
-
-## Start your localized site
-
-Start your site on the French locale:
-
-```bash
-npm run start -- --locale fr
-```
-
-Your localized site is accessible at [http://localhost:3000/fr/](http://localhost:3000/fr/) and the `Getting Started` page is translated.
-
-:::caution
-
-In development, you can only use one locale at a time.
-
-:::
-
-## Add a Locale Dropdown
-
-To navigate seamlessly across languages, add a locale dropdown.
-
-Modify the `docusaurus.config.js` file:
-
-```js title="docusaurus.config.js"
-export default {
- themeConfig: {
- navbar: {
- items: [
- // highlight-start
- {
- type: 'localeDropdown',
- },
- // highlight-end
- ],
- },
- },
-};
-```
-
-The locale dropdown now appears in your navbar:
-
-
-
-## Build your localized site
-
-Build your site for a specific locale:
-
-```bash
-npm run build -- --locale fr
-```
-
-Or build your site to include all the locales at once:
-
-```bash
-npm run build
-```
diff --git a/docs/docs/usage/_category_.json b/docs/docs/usage/_category_.json
new file mode 100644
index 0000000..37b7b21
--- /dev/null
+++ b/docs/docs/usage/_category_.json
@@ -0,0 +1,8 @@
+{
+ "label": "Usage",
+ "position": 3,
+ "link": {
+ "type": "generated-index",
+ "description": "Learn how to use RA.Aid effectively in different scenarios."
+ }
+}
diff --git a/docs/docs/usage/cpp-game.md b/docs/docs/usage/cpp-game.md
new file mode 100644
index 0000000..7a68c8a
--- /dev/null
+++ b/docs/docs/usage/cpp-game.md
@@ -0,0 +1,19 @@
+# Create a Game using RA.Aid
+
+RA.Aid can work on almost any kind of software, including writing games in languages like C++.
+
+## Creating the Initial Game
+
+To get started with creating a game, you can use RA.Aid with a simple command like:
+
+```
+ra-aid -m "Create a basic breakout clone in C++ using opengl."
+```
+
+## Adding Features
+
+Once your base game is working, you can add features like this:
+
+```
+ra-aid -m "Add score tracking/display to the main screen."
+```
\ No newline at end of file
diff --git a/docs/docs/usage/modern-web-app.md b/docs/docs/usage/modern-web-app.md
new file mode 100644
index 0000000..083acea
--- /dev/null
+++ b/docs/docs/usage/modern-web-app.md
@@ -0,0 +1,45 @@
+# Create a Modern Web App
+
+When using AI tools like RA.Aid to create a modern web application, it's most effective to break down the work from a high level into discrete tasks. This guide will walk you through a practical example of building a Next.js application with common modern features.
+
+## Setting Up a Fresh Next.js Application
+
+To get started with a new Next.js project, you can use RA.Aid with a simple command like:
+
+```
+ra-aid -m "Initialize a new nextjs app."
+```
+
+RA.Aid will execute the necessary commands and set up a clean Next.js project for you with the latest best practices. It'll even search the web to read documentation about the latest version of Next.
+
+## Adding shadcn/ui Components
+
+Once your base Next.js application is ready, you can add the shadcn/ui component library. Tell RA.Aid:
+
+```
+ra-aid -m "Install shadcn into this project and put a few examples of shadcn components on the main page."
+```
+
+This will configure your project with shadcn/ui's CLI, set up the necessary styling, and add your first components.
+
+## Integrating Prisma with SQLite
+
+For database integration, you can add Prisma ORM with SQLite. Simply instruct RA.Aid:
+
+```
+ra-aid -m "Integrate prisma/sqlite into this project."
+```
+
+RA.Aid will handle the Prisma setup, create your database schema, and set up your first model.
+
+## Adding Features Incrementally
+
+With the foundation in place, you can start adding features one by one. Here's an example:
+
+```
+ra-aid -m "Add a simple user registration form. Include fields for email and password."
+```
+
+Keep your feature requests focused and specific. This allows RA.Aid to implement them effectively while maintaining code quality.
+
+Remember to build your application incrementally, testing each feature as it's added. This approach helps manage complexity and ensures a stable development process.
\ No newline at end of file
diff --git a/docs/docs/usage/monorepo.md b/docs/docs/usage/monorepo.md
new file mode 100644
index 0000000..6c2f3fd
--- /dev/null
+++ b/docs/docs/usage/monorepo.md
@@ -0,0 +1,17 @@
+# Work with an Existing Mono Repo using RA.Aid
+
+RA.Aid is good at handling complex monorepo projects. For example, if you you have an app set up like this:
+
+```
+app/
+web/
+backend/
+```
+
+You can run RA.Aid at the top level and give it commands like this:
+
+```
+ra-aid -m "Update the user form to support birthdates. Be sure to also update the DB model and migration scripts."
+```
+
+RA.Aid will proceed to work on multiple high-level components of your application.
\ No newline at end of file
diff --git a/docs/docusaurus.config.ts b/docs/docusaurus.config.ts
index a2f1392..4b3de14 100644
--- a/docs/docusaurus.config.ts
+++ b/docs/docusaurus.config.ts
@@ -17,6 +17,10 @@ const config: Config = {
locales: ['en'],
},
+ plugins: [
+ '@docusaurus/plugin-vercel-analytics'
+ ],
+
presets: [
[
'classic',
@@ -48,7 +52,7 @@ const config: Config = {
label: 'Docs',
},
{
- href: 'https://github.com/smallcloudai/refact-aide',
+ href: 'https://github.com/ai-christianson/RA.Aid',
label: 'GitHub',
position: 'right',
},
@@ -56,7 +60,7 @@ const config: Config = {
},
footer: {
style: 'dark',
- copyright: `Copyright © ${new Date().getFullYear()} My Project, Inc. Built with Docusaurus.`,
+ copyright: `Copyright © ${new Date().getFullYear()} AI Christianson. Built with RA.Aid and Docusaurus.`,
},
prism: {
theme: prismThemes.github,
diff --git a/docs/package-lock.json b/docs/package-lock.json
index d3a5f04..248e2d8 100644
--- a/docs/package-lock.json
+++ b/docs/package-lock.json
@@ -9,6 +9,7 @@
"version": "0.0.0",
"dependencies": {
"@docusaurus/core": "3.7.0",
+ "@docusaurus/plugin-vercel-analytics": "^3.7.0",
"@docusaurus/preset-classic": "3.7.0",
"@mdx-js/react": "^3.0.0",
"clsx": "^2.0.0",
@@ -3529,6 +3530,66 @@
"react-dom": "^18.0.0 || ^19.0.0"
}
},
+ "node_modules/@docusaurus/plugin-vercel-analytics": {
+ "version": "3.7.0",
+ "resolved": "https://registry.npmjs.org/@docusaurus/plugin-vercel-analytics/-/plugin-vercel-analytics-3.7.0.tgz",
+ "integrity": "sha512-zEOsqNI3oj4WRO9Dbzsar9fctwAl60PZJqhu14X5W3z5zT/E1TFKrHW/oJHU/a1r5o9K2cFsSNdDn2tyuaFJoQ==",
+ "license": "MIT",
+ "dependencies": {
+ "@docusaurus/core": "3.7.0",
+ "@docusaurus/logger": "3.7.0",
+ "@docusaurus/types": "3.7.0",
+ "@docusaurus/utils": "3.7.0",
+ "@docusaurus/utils-validation": "3.7.0",
+ "@vercel/analytics": "^1.1.1",
+ "tslib": "^2.6.0"
+ },
+ "engines": {
+ "node": ">=18.0"
+ },
+ "peerDependencies": {
+ "react": "^18.0.0 || ^19.0.0",
+ "react-dom": "^18.0.0 || ^19.0.0"
+ }
+ },
+ "node_modules/@docusaurus/plugin-vercel-analytics/node_modules/@vercel/analytics": {
+ "version": "1.5.0",
+ "resolved": "https://registry.npmjs.org/@vercel/analytics/-/analytics-1.5.0.tgz",
+ "integrity": "sha512-MYsBzfPki4gthY5HnYN7jgInhAZ7Ac1cYDoRWFomwGHWEX7odTEzbtg9kf/QSo7XEsEAqlQugA6gJ2WS2DEa3g==",
+ "license": "MPL-2.0",
+ "peerDependencies": {
+ "@remix-run/react": "^2",
+ "@sveltejs/kit": "^1 || ^2",
+ "next": ">= 13",
+ "react": "^18 || ^19 || ^19.0.0-rc",
+ "svelte": ">= 4",
+ "vue": "^3",
+ "vue-router": "^4"
+ },
+ "peerDependenciesMeta": {
+ "@remix-run/react": {
+ "optional": true
+ },
+ "@sveltejs/kit": {
+ "optional": true
+ },
+ "next": {
+ "optional": true
+ },
+ "react": {
+ "optional": true
+ },
+ "svelte": {
+ "optional": true
+ },
+ "vue": {
+ "optional": true
+ },
+ "vue-router": {
+ "optional": true
+ }
+ }
+ },
"node_modules/@docusaurus/preset-classic": {
"version": "3.7.0",
"resolved": "https://registry.npmjs.org/@docusaurus/preset-classic/-/preset-classic-3.7.0.tgz",
diff --git a/docs/package.json b/docs/package.json
index 32ddd41..8bf5596 100644
--- a/docs/package.json
+++ b/docs/package.json
@@ -16,6 +16,7 @@
},
"dependencies": {
"@docusaurus/core": "3.7.0",
+ "@docusaurus/plugin-vercel-analytics": "^3.7.0",
"@docusaurus/preset-classic": "3.7.0",
"@mdx-js/react": "^3.0.0",
"clsx": "^2.0.0",
diff --git a/docs/static/img/favicon.ico b/docs/static/img/favicon.ico
index c01d54b..d933be3 100644
Binary files a/docs/static/img/favicon.ico and b/docs/static/img/favicon.ico differ
diff --git a/ra_aid/models_params.py b/ra_aid/models_params.py
index 0d374ca..2124258 100644
--- a/ra_aid/models_params.py
+++ b/ra_aid/models_params.py
@@ -4,6 +4,7 @@ List of model parameters
DEFAULT_TOKEN_LIMIT = 100000
DEFAULT_TEMPERATURE = 0.7
+DEFAULT_BASE_LATENCY = 180
models_params = {
"openai": {
@@ -11,216 +12,281 @@ models_params = {
"token_limit": 16385,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-3.5": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-3.5-turbo": {
"token_limit": 16385,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-3.5-turbo-1106": {
"token_limit": 16385,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-3.5-turbo-instruct": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-0125-preview": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-turbo-preview": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-turbo": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-turbo-2024-04-09": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-1106-preview": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-vision-preview": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-0613": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-32k": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-32k-0613": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4o": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4o-2024-08-06": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4o-2024-05-13": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4o-mini": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
+ },
+ "o1-preview": {
+ "token_limit": 128000,
+ "supports_temperature": False,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
+ },
+ "o1-mini": {
+ "token_limit": 128000,
+ "supports_temperature": False,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
+ },
+ "o1": {
+ "token_limit": 200000,
+ "supports_temperature": False,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
+ },
+ "o3-mini": {
+ "token_limit": 200000,
+ "supports_temperature": False,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
- "o1-preview": {"token_limit": 128000, "supports_temperature": False},
- "o1-mini": {"token_limit": 128000, "supports_temperature": False},
- "o1": {"token_limit": 200000, "supports_temperature": False},
- "o3-mini": {"token_limit": 200000, "supports_temperature": False},
},
"azure_openai": {
"gpt-3.5-turbo-0125": {
"token_limit": 16385,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-3.5": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-3.5-turbo": {
"token_limit": 16385,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-3.5-turbo-1106": {
"token_limit": 16385,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-3.5-turbo-instruct": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-0125-preview": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-turbo-preview": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-turbo": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-turbo-2024-04-09": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-1106-preview": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-vision-preview": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-0613": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-32k": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4-32k-0613": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4o": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gpt-4o-mini": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"chatgpt-4o-latest": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
+ },
+ "o1-preview": {
+ "token_limit": 128000,
+ "supports_temperature": False,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
+ },
+ "o1-mini": {
+ "token_limit": 128000,
+ "supports_temperature": False,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
- "o1-preview": {"token_limit": 128000, "supports_temperature": False},
- "o1-mini": {"token_limit": 128000, "supports_temperature": False},
},
"google_genai": {
"gemini-pro": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gemini-1.5-flash-latest": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gemini-1.5-pro-latest": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"models/embedding-001": {
"token_limit": 2048,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"google_vertexai": {
@@ -228,16 +294,19 @@ models_params = {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gemini-1.5-pro": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gemini-1.0-pro": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"ollama": {
@@ -245,257 +314,308 @@ models_params = {
"token_limit": 12800,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"codellama": {
"token_limit": 16000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"dbrx": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"deepseek-coder:33b": {
"token_limit": 16000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"falcon": {
"token_limit": 2048,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama2": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama2:7b": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama2:13b": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama2:70b": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3:8b": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3:70b": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3.1": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3.1:8b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3.1:70b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"lama3.1:405b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3.2": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3.2:1b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3.2:3b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3.3:70b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"scrapegraph": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistral-small": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistral-openorca": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistral-large": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"grok-1": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llava": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mixtral:8x22b-instruct": {
"token_limit": 65536,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"nomic-embed-text": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"nous-hermes2:34b": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"orca-mini": {
"token_limit": 2048,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"phi3:3.8b": {
"token_limit": 12800,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"phi3:14b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"qwen:0.5b": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"qwen:1.8b": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"qwen:4b": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"qwen:14b": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"qwen:32b": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"qwen:72b": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"qwen:110b": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"stablelm-zephyr": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"wizardlm2:8x22b": {
"token_limit": 65536,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistral": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gemma2": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gemma2:9b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gemma2:27b": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
# embedding models
"shaw/dmeta-embedding-zh-small-q4": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"shaw/dmeta-embedding-zh-q4": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"chevalblanc/acge_text_embedding": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"martcreation/dmeta-embedding-zh": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"snowflake-arctic-embed": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mxbai-embed-large": {
"token_limit": 512,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"oneapi": {
@@ -503,6 +623,7 @@ models_params = {
"token_limit": 6000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
}
},
"nvidia": {
@@ -510,81 +631,97 @@ models_params = {
"token_limit": 419,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta/llama3-8b-instruct": {
"token_limit": 419,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"nemotron-4-340b-instruct": {
"token_limit": 1024,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"databricks/dbrx-instruct": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"google/codegemma-7b": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"google/gemma-2b": {
"token_limit": 2048,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"google/gemma-7b": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"google/recurrentgemma-2b": {
"token_limit": 2048,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta/codellama-70b": {
"token_limit": 16384,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta/llama2-70b": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"microsoft/phi-3-mini-128k-instruct": {
"token_limit": 122880,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistralai/mistral-7b-instruct-v0.2": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistralai/mistral-large": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistralai/mixtral-8x22b-instruct-v0.1": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistralai/mixtral-8x7b-instruct-v0.1": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"snowflake/arctic": {
"token_limit": 16384,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"groq": {
@@ -592,26 +729,31 @@ models_params = {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"llama3-70b-8192": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mixtral-8x7b-32768": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"gemma-7b-it": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude-3-haiku-20240307'": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"toghetherai": {
@@ -619,71 +761,85 @@ models_params = {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"stabilityai/stable-diffusion-xl-base-1.0": {
"token_limit": 2048,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"NousResearch/Hermes-3-Llama-3.1-405B-Turbo": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"Gryphe/MythoMax-L2-13b-Lite": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"Salesforce/Llama-Rank-V1": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta-llama/Meta-Llama-Guard-3-8B": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta-llama/Llama-3-8b-chat-hf": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta-llama/Llama-3-70b-chat-hf": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"Qwen/Qwen2-72B-Instruct": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"google/gemma-2-27b-it": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"anthropic": {
@@ -691,56 +847,67 @@ models_params = {
"token_limit": 100000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude2": {
"token_limit": 9000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude2.1": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude3": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude3.5": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude-3-opus-20240229": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude-3-sonnet-20240229": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude-3-haiku-20240307": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude-3-5-sonnet-20240620": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude-3-5-sonnet-20241022": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": 1.0,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude-3-5-haiku-latest": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"bedrock": {
@@ -748,101 +915,121 @@ models_params = {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"anthropic.claude-3-sonnet-20240229-v1:0": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"anthropic.claude-3-opus-20240229-v1:0": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"claude-3-5-haiku-latest": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"anthropic.claude-v2:1": {
"token_limit": 200000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"anthropic.claude-v2": {
"token_limit": 100000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"anthropic.claude-instant-v1": {
"token_limit": 100000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta.llama3-8b-instruct-v1:0": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta.llama3-70b-instruct-v1:0": {
"token_limit": 8192,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta.llama2-13b-chat-v1": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"meta.llama2-70b-chat-v1": {
"token_limit": 4096,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistral.mistral-7b-instruct-v0:2": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistral.mixtral-8x7b-instruct-v0:1": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistral.mistral-large-2402-v1:0": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"mistral.mistral-small-2402-v1:0": {
"token_limit": 32768,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"amazon.titan-embed-text-v1": {
"token_limit": 8000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"amazon.titan-embed-text-v2:0": {
"token_limit": 8000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"cohere.embed-english-v3": {
"token_limit": 512,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"cohere.embed-multilingual-v3": {
"token_limit": 512,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"mistralai": {
@@ -850,16 +1037,19 @@ models_params = {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"open-mistral-nemo": {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
"codestral-latest": {
"token_limit": 32000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
},
},
"togetherai": {
@@ -867,6 +1057,7 @@ models_params = {
"token_limit": 128000,
"supports_temperature": True,
"default_temperature": DEFAULT_TEMPERATURE,
+ "latency_coefficient": DEFAULT_BASE_LATENCY,
}
},
}