mirror of
https://github.com/enricoros/big-AGI.git
synced 2026-05-10 21:50:14 -07:00
Compare commits
24 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Enrico Ros
|
cd421b2f6e | ||
|
Enrico Ros
|
41b66e009a | ||
|
Enrico Ros
|
d96467f850 | ||
|
Enrico Ros
|
258b19e2f4 | ||
|
Enrico Ros
|
01a87158b9 | ||
|
Enrico Ros
|
46b768f9cf | ||
|
Enrico Ros
|
4f0b6a5d09 | ||
|
Enrico Ros
|
bfbcdb70fe | ||
|
Enrico Ros
|
2c4602cf39 | ||
|
Enrico Ros
|
68f5d3946b | ||
|
Enrico Ros
|
14724a864c | ||
|
Enrico Ros
|
5e2b196c4d | ||
|
Enrico Ros
|
e7686f60b1 | ||
|
Enrico Ros
|
380f666d35 | ||
|
Enrico Ros
|
3e277b1a35 | ||
|
Enrico Ros
|
9bac46ea75 | ||
|
Enrico Ros
|
2af4ee7dbe | ||
|
Enrico Ros
|
590fc0d021 | ||
|
Enrico Ros
|
746b0dad40 | ||
|
Enrico Ros
|
b327da3ded | ||
|
Enrico Ros
|
7a818bdcd0 | ||
|
Enrico Ros
|
c92ee2e22a | ||
|
Enrico Ros
|
632a4a565f | ||
|
Enrico Ros
|
d712c275a0 |
@@ -11,11 +11,8 @@ name: Create and publish Docker images
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
#- main-stable # Disabled as the v* tag is used for stable releases
|
||||
tags:
|
||||
- 'v*' # Trigger on version tags (e.g., v1.7.0)
|
||||
- 'v1.1*' # V1 legacy tags only (v1.10.x - v1.19.x range)
|
||||
|
||||
env:
|
||||
REGISTRY: ghcr.io
|
||||
@@ -51,11 +48,13 @@ jobs:
|
||||
with:
|
||||
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
|
||||
tags: |
|
||||
type=raw,value=development,enable=${{ github.ref == 'refs/heads/main' }}
|
||||
type=raw,value=stable,enable=${{ github.ref == 'refs/heads/main-stable' }}
|
||||
type=ref,event=tag # Use the tag name as a tag for tag builds
|
||||
type=semver,pattern={{version}} # Generate semantic versioning tags for tag builds
|
||||
type=sha # Just in case none of the above applies
|
||||
# V1 legacy pointers
|
||||
type=raw,value=v1
|
||||
type=raw,value=v1-stable
|
||||
|
||||
# Exact version tags (v1.16.11 and 1.16.11)
|
||||
type=ref,event=tag
|
||||
type=semver,pattern={{version}}
|
||||
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
|
||||
@@ -65,5 +64,10 @@ jobs:
|
||||
platforms: linux/amd64,linux/arm64
|
||||
push: true
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
build-args: NEXT_PUBLIC_GA4_MEASUREMENT_ID=${{ secrets.GA4_MEASUREMENT_ID }}
|
||||
labels: |
|
||||
org.opencontainers.image.title=Big-AGI v1 (Legacy)
|
||||
org.opencontainers.image.description=Big-AGI v1 - Legacy version. For the latest version, see GitHub and big-agi.com
|
||||
org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}
|
||||
org.opencontainers.image.documentation=https://big-agi.com
|
||||
build-args: |
|
||||
NEXT_PUBLIC_GA4_MEASUREMENT_ID=${{ secrets.GA4_MEASUREMENT_ID }}
|
||||
|
||||
@@ -1,29 +1,29 @@
|
||||
# BIG-AGI 🧠✨
|
||||
# BIG-AGI Legacy ✨
|
||||
|
||||
Welcome to big-AGI, the AI suite for professionals that need function, form,
|
||||
simplicity, and speed. Powered by the latest models from 12 vendors and
|
||||
open-source servers, `big-AGI` offers best-in-class Chats,
|
||||
[Beams](https://github.com/enricoros/big-AGI/issues/470),
|
||||
and [Calls](https://github.com/enricoros/big-AGI/issues/354) with AI personas,
|
||||
visualizations, coding, drawing, side-by-side chatting, and more -- all wrapped in a polished UX.
|
||||
|
||||
Stay ahead of the curve with big-AGI. 🚀 Pros & Devs love big-AGI. 🤖
|
||||
|
||||
[](https://big-agi.com)
|
||||
|
||||
> 🚀 Big-AGI 2 is launching Q4 2024. Be the first to experience it before the public release.
|
||||
> **⚠️ IMPORTANT: `v1` Branch - End of Life**
|
||||
>
|
||||
> 👉 [Apply for Early Access](https://y2rjg0zillz.typeform.com/to/ZSADpr5u?utm_source=gh-stable&utm_medium=readme&utm_campaign=ea2)
|
||||
> This is the **v1** (formerly **v1-stable**) branch, which reached end-of-life in October 2025.
|
||||
> - **For the latest Big-AGI**, see the [**main** branch](https://github.com/enricoros/big-AGI/tree/main) and [**big-agi.com**](https://big-agi.com)
|
||||
> - **v1.16.11 is the final legacy release** - No further updates will be provided
|
||||
> - Docker users: `:stable`, `:development` and `:latest` point to the `main` branch
|
||||
|
||||
Or fork & run on Vercel
|
||||
---
|
||||
|
||||
[](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fenricoros%2Fbig-AGI&env=OPENAI_API_KEY&envDescription=Backend%20API%20keys%2C%20optional%20and%20may%20be%20overridden%20by%20the%20UI.&envLink=https%3A%2F%2Fgithub.com%2Fenricoros%2Fbig-AGI%2Fblob%2Fmain%2Fdocs%2Fenvironment-variables.md&project-name=big-AGI)
|
||||
**For the latest Big-AGI:**
|
||||
- [**Big-AGI Open**](https://github.com/enricoros/big-AGI/tree/main) - Open Source, for self-hosting, with bleeding edge models support
|
||||
- [**Big-AGI Pro**](https://big-agi.com) - Hosted for Professionals with extra services and Cloud Sync
|
||||
|
||||
### Quick links: 👉 [roadmap](https://github.com/users/enricoros/projects/4/views/2) 👉 [installation](docs/installation.md) 👉 [documentation](docs/README.md)
|
||||
---
|
||||
|
||||
### What's New in 1.16.1...1.16.8 · Sep 13, 2024 (patch releases)
|
||||
### What's New in 1.16.11 · October 2025
|
||||
|
||||
- 1.16.8: OpenAI ChatGPT-4o Latest (o1-preview and o1-mini are supported in Big-AGI 2)
|
||||
- Final v1 legacy release. Branch reaches end-of-life.
|
||||
|
||||
### What's New in 1.16.1...1.16.10 · 2024-2025 (patch releases)
|
||||
|
||||
- 1.16.10: Openrouter models fixes
|
||||
- 1.16.9: Docker Gemini fix (R1 models are supported in latest Big-AGI)
|
||||
- 1.16.8: OpenAI ChatGPT-4o Latest (o1 models are supported in latest Big-AGI)
|
||||
- 1.16.7: OpenAI support for GPT-4o 2024-08-06
|
||||
- 1.16.6: Groq support for Llama 3.1 models
|
||||
- 1.16.5: GPT-4o Mini support
|
||||
@@ -36,190 +36,6 @@ Or fork & run on Vercel
|
||||
- 1.16.2: Updates to Beam
|
||||
- 1.16.1: Support for the new OpenAI GPT-4o 2024-05-13 model
|
||||
|
||||
### What's New in 1.16.0 · May 9, 2024 · Crystal Clear
|
||||
|
||||
- [Beam](https://big-agi.com/blog/beam-multi-model-ai-reasoning) core and UX improvements based on user feedback
|
||||
- Chat cost estimation 💰 (enable it in Labs / hover the token counter)
|
||||
- Save/load chat files with Ctrl+S / Ctrl+O on desktop
|
||||
- Major enhancements to the Auto-Diagrams tool
|
||||
- YouTube Transcriber Persona for chatting with video content, [#500](https://github.com/enricoros/big-AGI/pull/500)
|
||||
- Improved formula rendering (LaTeX), and dark-mode diagrams, [#508](https://github.com/enricoros/big-AGI/issues/508), [#520](https://github.com/enricoros/big-AGI/issues/520)
|
||||
- Models update: **Anthropic**, **Groq**, **Ollama**, **OpenAI**, **OpenRouter**, **Perplexity**
|
||||
- Code soft-wrap, chat text selection toolbar, 3x faster on Apple silicon, and more [#517](https://github.com/enricoros/big-AGI/issues/517), [507](https://github.com/enricoros/big-AGI/pull/507)
|
||||
|
||||
#### 3,000 Commits Milestone · April 7, 2024
|
||||
|
||||
|
||||
|
||||
- 🥇 Today we <b>celebrate commit 3000</b> in just over one year, and going stronger 🚀
|
||||
- 📢️ Thanks everyone for your support and words of love for Big-AGI, we are committed to creating the best AI experiences for everyone.
|
||||
|
||||
### What's New in 1.15.0 · April 1, 2024 · Beam
|
||||
|
||||
- ⚠️ [**Beam**: the multi-model AI chat](https://big-agi.com/blog/beam-multi-model-ai-reasoning). find better answers, faster - a game-changer for brainstorming, decision-making, and creativity. [#443](https://github.com/enricoros/big-AGI/issues/443)
|
||||
- Managed Deployments **Auto-Configuration**: simplify the UI models setup with backend-set models. [#436](https://github.com/enricoros/big-AGI/issues/436)
|
||||
- Message **Starring ⭐**: star important messages within chats, to attach them later. [#476](https://github.com/enricoros/big-AGI/issues/476)
|
||||
- Enhanced the default Persona
|
||||
- Fixes to Gemini models and SVGs, improvements to UI and icons
|
||||
- 1.15.1: Support for Gemini Pro 1.5 and OpenAI Turbo models
|
||||
- Beast release, over 430 commits, 10,000+ lines changed: [release notes](https://github.com/enricoros/big-AGI/releases/tag/v1.15.0), and changes [v1.14.1...v1.15.0](https://github.com/enricoros/big-AGI/compare/v1.14.1...v1.15.0)
|
||||
|
||||
<details>
|
||||
<summary>What's New in 1.14.1 · March 7, 2024 · Modelmorphic</summary>
|
||||
|
||||
- **Anthropic** [Claude-3](https://www.anthropic.com/news/claude-3-family) model family support. [#443](https://github.com/enricoros/big-AGI/issues/443)
|
||||
- New **[Perplexity](https://www.perplexity.ai/)** and **[Groq](https://groq.com/)** integration (thanks @Penagwin). [#407](https://github.com/enricoros/big-AGI/issues/407), [#427](https://github.com/enricoros/big-AGI/issues/427)
|
||||
- **[LocalAI](https://localai.io/models/)** deep integration, including support for [model galleries](https://github.com/enricoros/big-AGI/issues/411)
|
||||
- **Mistral** Large and Google **Gemini 1.5** support
|
||||
- Performance optimizations: runs [much faster](https://twitter.com/enricoros/status/1756553038293303434?utm_source=localhost:3000&utm_medium=big-agi), saves lots of power, reduces memory usage
|
||||
- Enhanced UX with auto-sizing charts, refined search and folder functionalities, perfected scaling
|
||||
- And with more UI improvements, documentation, bug fixes (20 tickets), and developer enhancements
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>What's New in 1.13.0 · Feb 8, 2024 · Multi + Mind</summary>
|
||||
|
||||
https://github.com/enricoros/big-AGI/assets/32999/01732528-730e-41dc-adc7-511385686b13
|
||||
|
||||
- **Side-by-Side Split Windows**: multitask with parallel conversations. [#208](https://github.com/enricoros/big-AGI/issues/208)
|
||||
- **Multi-Chat Mode**: message everyone, all at once. [#388](https://github.com/enricoros/big-AGI/issues/388)
|
||||
- **Export tables as CSV**: big thanks to @aj47. [#392](https://github.com/enricoros/big-AGI/pull/392)
|
||||
- Adjustable text size: customize density. [#399](https://github.com/enricoros/big-AGI/issues/399)
|
||||
- Dev2 Persona Technology Preview
|
||||
- Better looking chats with improved spacing, fonts, and menus
|
||||
- More: new video player, [LM Studio tutorial](https://github.com/enricoros/big-AGI/blob/main/docs/config-local-lmstudio.md) (thanks @aj47), [MongoDB support](https://github.com/enricoros/big-AGI/blob/main/docs/deploy-database.md) (thanks @ranfysvalle02), and speedups
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>What's New in 1.12.0 · Jan 26, 2024 · AGI Hotline</summary>
|
||||
|
||||
https://github.com/enricoros/big-AGI/assets/32999/95ceb03c-945d-4fdd-9a9f-3317beb54f3f
|
||||
|
||||
- **Voice Calls**: real-time voice call your personas out of the blue or in relation to a chat [#354](https://github.com/enricoros/big-AGI/issues/354)
|
||||
- Support **OpenAI 0125** Models. [#364](https://github.com/enricoros/big-AGI/issues/364)
|
||||
- Rename or Auto-Rename chats. [#222](https://github.com/enricoros/big-AGI/issues/222), [#360](https://github.com/enricoros/big-AGI/issues/360)
|
||||
- More control over **Link Sharing** [#356](https://github.com/enricoros/big-AGI/issues/356)
|
||||
- **Accessibility** to screen readers [#358](https://github.com/enricoros/big-AGI/issues/358)
|
||||
- Export chats to Markdown [#337](https://github.com/enricoros/big-AGI/issues/337)
|
||||
- Paste tables from Excel [#286](https://github.com/enricoros/big-AGI/issues/286)
|
||||
- Ollama model updates and context window detection fixes [#309](https://github.com/enricoros/big-AGI/issues/309)
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>What's New in 1.11.0 · Jan 16, 2024 · Singularity</summary>
|
||||
|
||||
https://github.com/enricoros/big-AGI/assets/1590910/a6b8e172-0726-4b03-a5e5-10cfcb110c68
|
||||
|
||||
- **Find chats**: search in titles and content, with frequency ranking. [#329](https://github.com/enricoros/big-AGI/issues/329)
|
||||
- **Commands**: command auto-completion (type '/'). [#327](https://github.com/enricoros/big-AGI/issues/327)
|
||||
- **[Together AI](https://www.together.ai/products#inference)** inference platform support (good speed and newer models). [#346](https://github.com/enricoros/big-AGI/issues/346)
|
||||
- Persona Creator history, deletion, custom creation, fix llm API timeouts
|
||||
- Enable adding up to five custom OpenAI-compatible endpoints
|
||||
- Developer enhancements: new 'Actiles' framework
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>What's New in 1.10.0 · Jan 6, 2024 · The Year of AGI</summary>
|
||||
|
||||
- **New UI**: for both desktop and mobile, sets the stage for future scale. [#201](https://github.com/enricoros/big-AGI/issues/201)
|
||||
- **Conversation Folders**: enhanced conversation organization. [#321](https://github.com/enricoros/big-AGI/issues/321)
|
||||
- **[LM Studio](https://lmstudio.ai/)** support and improved token management
|
||||
- Resizable panes in split-screen conversations.
|
||||
- Large performance optimizations
|
||||
- Developer enhancements: new UI framework, updated documentation for proxy settings on browserless/docker
|
||||
|
||||
</details>
|
||||
|
||||
For full details and former releases, check out the [changelog](docs/changelog.md).
|
||||
|
||||
## 👉 Key Features ✨
|
||||
|
||||
|  |  |  |  |  |
|
||||
|---------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|
|
||||
| **Chat**<br/>**Call**<br/>**Beam**<br/>**Draw**, ... | Local & Cloud<br/>Open & Closed<br/>Cheap & Heavy<br/>Google, Mistral, ... | Attachments<br/>Diagrams<br/>Multi-Chat<br/>Mobile-first UI | Stored Locally<br/>Easy self-Host<br/>Local actions<br/>Data = Gold | AI Personas<br/>Voice Modes<br/>Screen Capture<br/>Camera + OCR |
|
||||
|
||||
|
||||
|
||||
You can easily configure 100s of AI models in big-AGI:
|
||||
|
||||
| **AI models** | _supported vendors_ |
|
||||
|:--------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| Opensource Servers | [LocalAI](https://localai.com) (multimodal) · [Ollama](https://ollama.com/) · [Oobabooga](https://github.com/oobabooga/text-generation-webui) |
|
||||
| Local Servers | [LM Studio](https://lmstudio.ai/) |
|
||||
| Multimodal services | [Azure](https://azure.microsoft.com/en-us/products/ai-services/openai-service) · [Google Gemini](https://ai.google.dev/) · [OpenAI](https://platform.openai.com/docs/overview) |
|
||||
| Language services | [Anthropic](https://anthropic.com) · [Groq](https://wow.groq.com/) · [Mistral](https://mistral.ai/) · [OpenRouter](https://openrouter.ai/) · [Perplexity](https://www.perplexity.ai/) · [Together AI](https://www.together.ai/) |
|
||||
| Image services | [Prodia](https://prodia.com/) (SDXL) |
|
||||
| Speech services | [ElevenLabs](https://elevenlabs.io) (Voice synthesis / cloning) |
|
||||
|
||||
Add extra functionality with these integrations:
|
||||
|
||||
| **More** | _integrations_ |
|
||||
|:-------------|:---------------------------------------------------------------------------------------------------------------|
|
||||
| Web Browse | [Browserless](https://www.browserless.io/) · [Puppeteer](https://pptr.dev/)-based |
|
||||
| Web Search | [Google CSE](https://programmablesearchengine.google.com/) |
|
||||
| Code Editors | [CodePen](https://codepen.io/pen/) · [StackBlitz](https://stackblitz.com/) · [JSFiddle](https://jsfiddle.net/) |
|
||||
| Sharing | [Paste.gg](https://paste.gg/) (Paste chats) |
|
||||
| Tracking | [Helicone](https://www.helicone.ai) (LLM Observability) |
|
||||
|
||||
[//]: # (- [x] **Flow-state UX** for uncompromised productivity)
|
||||
|
||||
[//]: # (- [x] **AI Personas**: Tailor your AI interactions with customizable personas)
|
||||
|
||||
[//]: # (- [x] **Sleek UI/UX**: A smooth, intuitive, and mobile-responsive interface)
|
||||
|
||||
[//]: # (- [x] **Efficient Interaction**: Voice commands, OCR, and drag-and-drop file uploads)
|
||||
|
||||
[//]: # (- [x] **Privacy First**: Self-host and use your own API keys for full control)
|
||||
|
||||
[//]: # (- [x] **Advanced Tools**: Execute code, import PDFs, and summarize documents)
|
||||
|
||||
[//]: # (- [x] **Seamless Integrations**: Enhance functionality with various third-party services)
|
||||
|
||||
[//]: # (- [x] **Open Roadmap**: Contribute to the progress of big-AGI)
|
||||
|
||||
<br/>
|
||||
|
||||
## 🚀 Installation
|
||||
|
||||
To get started with big-AGI, follow our comprehensive [Installation Guide](docs/installation.md).
|
||||
The guide covers various installation options, whether you're spinning it up on
|
||||
your local computer, deploying on Vercel, on Cloudflare, or rolling it out
|
||||
through Docker.
|
||||
|
||||
Whether you're a developer, system integrator, or enterprise user, you'll find step-by-step instructions
|
||||
to set up big-AGI quickly and easily.
|
||||
|
||||
[](docs/installation.md)
|
||||
|
||||
Or bring your API keys and jump straight into our free instance on [big-AGI.com](https://big-agi.com).
|
||||
|
||||
<br/>
|
||||
|
||||
# 🌟 Get Involved!
|
||||
|
||||
[//]: # ([](https://discord.gg/MkH4qj2Jp9))
|
||||
[](https://discord.gg/MkH4qj2Jp9)
|
||||
|
||||
- [ ] 📢️ [**Chat with us** on Discord](https://discord.gg/MkH4qj2Jp9)
|
||||
- [ ] ⭐ **Give us a star** on GitHub 👆
|
||||
- [ ] 🚀 **Do you like code**? You'll love this gem of a project! [_Pick up a task!_](https://github.com/users/enricoros/projects/4/views/4) - _easy_ to _pro_
|
||||
- [ ] 💡 Got a feature suggestion? [_Add your roadmap ideas_](https://github.com/enricoros/big-agi/issues/new?&template=roadmap-request.md)
|
||||
- [ ] ✨ [Deploy](docs/installation.md) your [fork](docs/customizations.md) for your friends and family, or [customize it for work](docs/customizations.md)
|
||||
|
||||
<br/>
|
||||
|
||||
[//]: # ([](https://github.com/enricoros/big-agi/stargazers))
|
||||
|
||||
[//]: # ([](https://github.com/enricoros/big-agi/network))
|
||||
|
||||
[//]: # ([](https://github.com/enricoros/big-agi/pulls))
|
||||
|
||||
[//]: # ([](https://github.com/enricoros/big-agi/LICENSE))
|
||||
|
||||
---
|
||||
|
||||
2023-2024 · Enrico Ros x [big-AGI](https://big-agi.com) · License: [MIT](LICENSE) · Made with 💙
|
||||
2023-2025 · Enrico Ros x [Big-AGI](https://big-agi.com) · License: [MIT](LICENSE) · Made with 💙
|
||||
|
||||
+6
-4
@@ -1,6 +1,8 @@
|
||||
# big-AGI Documentation
|
||||
# big-AGI v1 Documentation (Legacy)
|
||||
|
||||
Find all the information you need to get started, configure, and effectively use big-AGI.
|
||||
> **Note:** This is documentation for the **v1 legacy branch**. For the latest Big-AGI, see the [main branch](https://github.com/enricoros/big-AGI/tree/main) or visit [big-agi.com](https://big-agi.com).
|
||||
|
||||
Find all the information you need to get started, configure, and effectively use big-AGI v1.
|
||||
|
||||
[//]: # (## Quick Start)
|
||||
|
||||
@@ -33,7 +35,7 @@ Detailed guides to configure your big-AGI interface and models.
|
||||
|
||||
## Deployment
|
||||
|
||||
System integrators, administrators, whitelabelers: instead of using the public big-AGI instance on get.big-agi.com, you can deploy your own instance.
|
||||
System integrators, administrators, whitelabelers: instead of using the public big-AGI instance on app.big-agi.com, you can deploy your own instance.
|
||||
|
||||
Step-by-step deployment and system configuration instructions.
|
||||
|
||||
@@ -53,7 +55,7 @@ Step-by-step deployment and system configuration instructions.
|
||||
Join our community or get support:
|
||||
|
||||
- Visit our [GitHub repository](https://github.com/enricoros/big-AGI) for source code and issue tracking
|
||||
- Check the latest updates and features on [Changelog](changelog.md) or the in-app [News](https://get.big-agi.com/news)
|
||||
- Check the latest updates and features on [Changelog](changelog.md) or the in-app [News](https://big-agi.com/news)
|
||||
- Connect with us and other users on [Discord](https://discord.gg/MkH4qj2Jp9) for discussions, help, and sharing your experiences with big-AGI
|
||||
|
||||
Thank you for choosing big-AGI. We're excited to see what you'll build.
|
||||
|
||||
+7
-10
@@ -1,18 +1,15 @@
|
||||
## Changelog
|
||||
## Changelog (v1 Legacy Branch)
|
||||
|
||||
This is a high-level changelog. Calls out some of the high level features batched
|
||||
by release.
|
||||
This is a high-level changelog for the v1 legacy branch. For the latest Big-AGI, see the [main branch](https://github.com/enricoros/big-AGI).
|
||||
|
||||
- For the live roadmap, please see [the GitHub project](https://github.com/users/enricoros/projects/4/views/2)
|
||||
### 1.16.11 · October 2025 (Final Release)
|
||||
|
||||
### 1.17.0 - Jun 2024
|
||||
Final v1 legacy release. Branch reaches end-of-life.
|
||||
|
||||
- milestone: [1.17.0](https://github.com/enricoros/big-agi/milestone/17)
|
||||
- work in progress: [big-AGI open roadmap](https://github.com/users/enricoros/projects/4/views/2), [help here](https://github.com/users/enricoros/projects/4/views/4)
|
||||
### What's New in 1.16.1...1.16.10 · 2024-2025 (patch releases)
|
||||
|
||||
### What's New in 1.16.1...1.16.8 · Sep 13, 2024 (patch releases)
|
||||
|
||||
- 1.16.8: OpenAI ChatGPT-4o Latest (o1-preview and o1-mini are supported in Big-AGI 2)
|
||||
- 1.16.9: Docker Gemini fix (R1 models are supported in Big-AGI 2)
|
||||
- 1.16.8: OpenAI ChatGPT-4o Latest (o1 models are supported in Big-AGI 2)
|
||||
- 1.16.7: OpenAI support for GPT-4o 2024-08-06
|
||||
- 1.16.6: Groq support for Llama 3.1 models
|
||||
- 1.16.5: GPT-4o Mini support
|
||||
|
||||
@@ -1,4 +1,8 @@
|
||||
# Deploying `big-AGI` with Docker
|
||||
# Deploying `big-AGI` with Docker (v1 Legacy)
|
||||
|
||||
> **Note:** This documentation is for the **v1 legacy branch**. For the latest Big-AGI, use Docker tags `:latest`, `:stable`, or `:development` which point to the [main branch](https://github.com/enricoros/big-AGI/tree/main).
|
||||
>
|
||||
> To use v1 legacy specifically, use Docker tags `:v1` or `:v1-stable`.
|
||||
|
||||
Utilize Docker containers to deploy the big-AGI application for an efficient and automated deployment process.
|
||||
Docker ensures faster development cycles, easier collaboration, and seamless environment management.
|
||||
|
||||
Generated
+1
-1
@@ -79,7 +79,7 @@
|
||||
"typescript": "^5.4.5"
|
||||
},
|
||||
"engines": {
|
||||
"node": "^20.0.0 || ^18.0.0"
|
||||
"node": "^22.0.0 || ^20.0.0 || ^18.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/code-frame": {
|
||||
|
||||
+1
-1
@@ -88,6 +88,6 @@
|
||||
"typescript": "^5.4.5"
|
||||
},
|
||||
"engines": {
|
||||
"node": "^20.0.0 || ^18.0.0"
|
||||
"node": "^24.0.0 || ^22.0.0 || ^20.0.0 || ^18.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import * as React from 'react';
|
||||
import { useShallow } from 'zustand/react/shallow';
|
||||
|
||||
import { Box, Button, Dropdown, IconButton, ListDivider, ListItem, ListItemButton, ListItemDecorator, Menu, MenuButton, MenuItem, Tooltip, Typography } from '@mui/joy';
|
||||
import { Box, Button, Card, CardContent, Dropdown, IconButton, ListDivider, ListItem, ListItemButton, ListItemDecorator, Menu, MenuButton, MenuItem, Tooltip, Typography } from '@mui/joy';
|
||||
import AddIcon from '@mui/icons-material/Add';
|
||||
import CheckRoundedIcon from '@mui/icons-material/CheckRounded';
|
||||
import ClearIcon from '@mui/icons-material/Clear';
|
||||
@@ -10,6 +10,7 @@ import FileDownloadOutlinedIcon from '@mui/icons-material/FileDownloadOutlined';
|
||||
import FileUploadOutlinedIcon from '@mui/icons-material/FileUploadOutlined';
|
||||
import FolderIcon from '@mui/icons-material/Folder';
|
||||
import MoreVertIcon from '@mui/icons-material/MoreVert';
|
||||
import RocketLaunchRoundedIcon from '@mui/icons-material/RocketLaunchRounded';
|
||||
import StarOutlineRoundedIcon from '@mui/icons-material/StarOutlineRounded';
|
||||
|
||||
import type { DConversationId } from '~/common/state/store-chats';
|
||||
@@ -18,8 +19,10 @@ import { DFolder, useFolderStore } from '~/common/state/store-folders';
|
||||
import { DebounceInputMemo } from '~/common/components/DebounceInput';
|
||||
import { FoldersToggleOff } from '~/common/components/icons/FoldersToggleOff';
|
||||
import { FoldersToggleOn } from '~/common/components/icons/FoldersToggleOn';
|
||||
import { Link } from '~/common/components/Link';
|
||||
import { PageDrawerHeader } from '~/common/layout/optima/components/PageDrawerHeader';
|
||||
import { PageDrawerList } from '~/common/layout/optima/components/PageDrawerList';
|
||||
import { ROUTE_APP_NEWS } from '~/common/app.routes';
|
||||
import { capitalizeFirstLetter } from '~/common/util/textUtils';
|
||||
import { themeScalingMap, themeZIndexOverMobileDrawer } from '~/common/app.theme';
|
||||
import { useOptimaDrawers } from '~/common/layout/optima/useOptimaDrawers';
|
||||
@@ -78,6 +81,13 @@ function ChatDrawer(props: {
|
||||
const [searchSorting, setSearchSorting] = React.useState<ChatSearchSorting>('frequency');
|
||||
const [debouncedSearchQuery, setDebouncedSearchQuery] = React.useState('');
|
||||
const [folderChangeRequest, setFolderChangeRequest] = React.useState<FolderChangeRequest | null>(null);
|
||||
const [bigAgi2CalloutDismissed, setBigAgi2CalloutDismissed] = React.useState(() => {
|
||||
try {
|
||||
return localStorage.getItem('dismissedBA2ChatDrawerNotice') === 'true';
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
});
|
||||
|
||||
// external state
|
||||
const { closeDrawer, closeDrawerOnMobile } = useOptimaDrawers();
|
||||
@@ -125,6 +135,15 @@ function ChatDrawer(props: {
|
||||
props.activeConversationId && onConversationsExportDialog(props.activeConversationId, true);
|
||||
}, [onConversationsExportDialog, props.activeConversationId]);
|
||||
|
||||
const handleDismissBigAgi2Callout = React.useCallback(() => {
|
||||
setBigAgi2CalloutDismissed(true);
|
||||
try {
|
||||
localStorage.setItem('dismissedBA2ChatDrawerNotice', 'true');
|
||||
} catch {
|
||||
// ignore
|
||||
}
|
||||
}, []);
|
||||
|
||||
|
||||
// Folder change request
|
||||
|
||||
@@ -340,6 +359,45 @@ function ChatDrawer(props: {
|
||||
)}
|
||||
</Box>
|
||||
|
||||
{/* Big-AGI 2.0 Callout */}
|
||||
{!bigAgi2CalloutDismissed && (
|
||||
<Box sx={{ p: 2 }}>
|
||||
<Card variant='solid' color='primary' invertedColors>
|
||||
<CardContent sx={{ gap: 1, position: 'relative' }}>
|
||||
<IconButton
|
||||
size='sm'
|
||||
onClick={handleDismissBigAgi2Callout}
|
||||
sx={{
|
||||
position: 'absolute',
|
||||
top: -4,
|
||||
right: -8,
|
||||
}}
|
||||
>
|
||||
<ClearIcon />
|
||||
</IconButton>
|
||||
<Typography level='title-sm'>
|
||||
Big-AGI 2.0 ✨ is Live!
|
||||
</Typography>
|
||||
<Typography level='body-xs' sx={{ mb: 1 }}>
|
||||
Experience Beam 2, Personas, and Cloud Sync.
|
||||
</Typography>
|
||||
<Button
|
||||
fullWidth
|
||||
size='sm'
|
||||
variant='solid'
|
||||
color='neutral'
|
||||
endDecorator={<RocketLaunchRoundedIcon />}
|
||||
component={Link}
|
||||
href={ROUTE_APP_NEWS}
|
||||
noLinkStyle
|
||||
>
|
||||
Learn More
|
||||
</Button>
|
||||
</CardContent>
|
||||
</Card>
|
||||
</Box>
|
||||
)}
|
||||
|
||||
<ListDivider sx={{ my: 0 }} />
|
||||
|
||||
{/* Bottom commands */}
|
||||
|
||||
+53
-11
@@ -5,6 +5,8 @@ import TimeAgo from 'react-timeago';
|
||||
import { AspectRatio, Box, Button, Card, CardContent, CardOverflow, Container, Grid, Typography } from '@mui/joy';
|
||||
import ExpandMoreIcon from '@mui/icons-material/ExpandMore';
|
||||
import LaunchIcon from '@mui/icons-material/Launch';
|
||||
import ArrowForwardRoundedIcon from '@mui/icons-material/ArrowForwardRounded';
|
||||
import ArrowOutwardRoundedIcon from '@mui/icons-material/ArrowOutwardRounded';
|
||||
|
||||
import { Brand } from '~/common/app.config';
|
||||
import { Link } from '~/common/components/Link';
|
||||
@@ -14,7 +16,9 @@ import { capitalizeFirstLetter } from '~/common/util/textUtils';
|
||||
|
||||
import { NewsItems } from './news.data';
|
||||
import { beamNewsCallout } from './beam.data';
|
||||
import { bigAgi2NewsCallout } from './bigAgi2.data';
|
||||
import { bigAgi2NewsCallout, bigAgi2Url } from './bigAgi2.data';
|
||||
|
||||
import { downloadAllConversationsJson } from '~/modules/trade/trade.client';
|
||||
|
||||
|
||||
// number of news items to show by default, before the expander
|
||||
@@ -65,6 +69,8 @@ export function AppNews() {
|
||||
// show expander
|
||||
const canExpand = news.length < NewsItems.length;
|
||||
|
||||
const currentVer = '1.6.9'; // firstNews?.versionCode;
|
||||
|
||||
return (
|
||||
|
||||
<Box sx={{
|
||||
@@ -79,26 +85,41 @@ export function AppNews() {
|
||||
display: 'flex', flexDirection: 'column', alignItems: 'center',
|
||||
}}>
|
||||
|
||||
<Typography level='h1' sx={{ fontSize: '2.9rem', mb: 4 }}>
|
||||
Welcome to {Brand.Title.Base} <Box component='span' sx={{ animation: `${animationColorBlues} 10s infinite`, zIndex: 1 /* perf-opt */ }}>{firstNews?.versionCode}</Box>!
|
||||
<Typography level='h1' sx={{ fontSize: '2.7rem', mb: 4 }}>
|
||||
Welcome to {Brand.Title.Base} <Box component='span' sx={{ animation: `${animationColorBlues} 10s infinite`, zIndex: 1 /* perf-opt */ }}>{currentVer}</Box>!
|
||||
</Typography>
|
||||
|
||||
<Typography sx={{ mb: 2 }} level='title-sm'>
|
||||
{capitalizeFirstLetter(Brand.Title.Base)} has been updated to version {firstNews?.versionCode}
|
||||
<Typography level='title-sm' sx={{ mb: 2, textAlign: 'center', lineHeight: 'lg' }} >
|
||||
{capitalizeFirstLetter(Brand.Title.Base)} has been updated to version {currentVer}.<br/>
|
||||
<b>And a whole-new 2.0 is waiting!</b>
|
||||
</Typography>
|
||||
|
||||
<Box sx={{ mb: 5 }}>
|
||||
<Box sx={{ mb: 5, display: 'flex', gap: 2, flexWrap: 'wrap', justifyContent: 'center' }}>
|
||||
<Button
|
||||
variant='solid' color='primary' size='lg'
|
||||
variant='solid' color='neutral' size='lg'
|
||||
component={Link} href={ROUTE_INDEX} noLinkStyle
|
||||
endDecorator='✨'
|
||||
endDecorator={<ArrowForwardRoundedIcon />}
|
||||
// endDecorator='✨'
|
||||
sx={{
|
||||
boxShadow: '0 8px 24px -4px rgb(var(--joy-palette-primary-mainChannel) / 20%)',
|
||||
// boxShadow: '0 8px 24px -4px rgb(var(--joy-palette-primary-mainChannel) / 20%)',
|
||||
minWidth: 180,
|
||||
}}
|
||||
>
|
||||
Continue
|
||||
</Button>
|
||||
<Button
|
||||
variant='solid' color='primary' size='lg'
|
||||
component={Link} href={bigAgi2Url} noLinkStyle
|
||||
endDecorator={<><ArrowOutwardRoundedIcon /></>}
|
||||
// endDecorator='✨'
|
||||
sx={{
|
||||
boxShadow: '0 8px 24px -4px rgb(var(--joy-palette-primary-mainChannel) / 20%)',
|
||||
minWidth: 180,
|
||||
transform: 'translateY(-1px)',
|
||||
}}
|
||||
>
|
||||
Big-AGI 2 ✨
|
||||
</Button>
|
||||
</Box>
|
||||
|
||||
{/*<Typography level='title-sm' sx={{ mb: 1, placeSelf: 'start', ml: 1 }}>*/}
|
||||
@@ -107,7 +128,7 @@ export function AppNews() {
|
||||
|
||||
<Container disableGutters maxWidth='sm'>
|
||||
{news?.map((ni, idx) => {
|
||||
// const firstCard = idx === 0;
|
||||
const firstCard = idx === 0;
|
||||
const addPadding = false; //!firstCard; // || showExpander;
|
||||
return <React.Fragment key={idx}>
|
||||
|
||||
@@ -126,7 +147,7 @@ export function AppNews() {
|
||||
)}
|
||||
|
||||
{/* News Item */}
|
||||
<Card key={'news-' + idx} sx={{ mb: 3, minHeight: 32, gap: 1 }}>
|
||||
<Card color={firstCard ? 'primary' : undefined} key={'news-' + idx} sx={{ mb: 3, minHeight: 32, gap: 1 }}>
|
||||
<CardContent sx={{ position: 'relative', pr: addPadding ? 4 : 0 }}>
|
||||
<Box sx={{ display: 'flex', alignItems: 'center', justifyContent: 'space-between' }}>
|
||||
<Typography level='title-sm' component='div'>
|
||||
@@ -160,6 +181,27 @@ export function AppNews() {
|
||||
</ul>
|
||||
)}
|
||||
|
||||
{firstCard && <Box sx={{ mt: 2 }}>
|
||||
<Card variant='soft' color='primary' invertedColors>
|
||||
<CardContent>
|
||||
<Typography level='title-sm' sx={{ lineHeight: 'lg' }}>
|
||||
<b>Migrate your chats:</b> you can download all your conversations at any time by clicking
|
||||
on "Export" > "Download All" or the button below. Then open Big-AGI 2 and
|
||||
import the conversation by clicking "Organize" > "Import".
|
||||
</Typography>
|
||||
<Button
|
||||
size='sm'
|
||||
variant='soft'
|
||||
color='primary'
|
||||
sx={{ mt: 1 }}
|
||||
onClick={downloadAllConversationsJson}
|
||||
>
|
||||
Download All Conversations
|
||||
</Button>
|
||||
</CardContent>
|
||||
</Card>
|
||||
</Box>}
|
||||
|
||||
</CardContent>
|
||||
|
||||
{!!ni.versionCoverImage && (
|
||||
|
||||
@@ -3,38 +3,50 @@ import * as React from 'react';
|
||||
import { Button, Card, CardContent, Grid, Typography } from '@mui/joy';
|
||||
import AccessTimeIcon from '@mui/icons-material/AccessTime';
|
||||
import LaunchIcon from '@mui/icons-material/Launch';
|
||||
import RocketLaunchRounded from '@mui/icons-material/RocketLaunchRounded';
|
||||
import SupportAgentIcon from '@mui/icons-material/SupportAgent';
|
||||
|
||||
import { Link } from '~/common/components/Link';
|
||||
import { clientUtmSource } from '~/common/util/pwaUtils';
|
||||
|
||||
|
||||
const bigAgi2SurveyUrl = 'https://y2rjg0zillz.typeform.com/to/ZSADpr5u?utm_source=gh-stable&utm_medium=news&utm_campaign=ea2';
|
||||
export const bigAgi2Url = 'https://app.big-agi.com' + clientUtmSource('upgrade');
|
||||
const bigAgiSupport = 'https://form.typeform.com/to/nLf8gFmx?utm_source=big-agi-1&utm_medium=app&utm_campaign=support';
|
||||
|
||||
|
||||
export const bigAgi2NewsCallout =
|
||||
<Card variant='solid' invertedColors>
|
||||
<Card variant='solid' color='primary' invertedColors>
|
||||
<CardContent sx={{ gap: 2 }}>
|
||||
|
||||
<Typography level='title-lg'>
|
||||
Big-AGI 2.0 - In Development
|
||||
Big-AGI 2.0 ✨ - Now Live
|
||||
</Typography>
|
||||
<Typography level='body-sm'>
|
||||
We're building the next version of Big-AGI with your needs in mind. New features, better performance, enhanced AI interactions. Help us shape it.
|
||||
|
||||
<Typography level='title-sm' sx={{ lineHeight: 'xl' }}>
|
||||
Experience the <b>next generation of Big-AGI</b> with <b>Beam 2</b>, <b>Personas</b>, and <b>Cloud Sync</b> to never lose data.
|
||||
</Typography>
|
||||
|
||||
<Grid container spacing={1}>
|
||||
<Grid xs={12} sm={7}>
|
||||
<Button
|
||||
fullWidth variant='soft' color='primary' endDecorator={<LaunchIcon />}
|
||||
component={Link} href={bigAgi2SurveyUrl} noLinkStyle target='_blank'
|
||||
size='lg'
|
||||
fullWidth variant='solid' color='neutral' endDecorator={<RocketLaunchRounded />}
|
||||
component={Link} href={bigAgi2Url} noLinkStyle target='_blank'
|
||||
>
|
||||
Apply for Early Access
|
||||
Big-AGI 2.0
|
||||
</Button>
|
||||
</Grid>
|
||||
|
||||
<Grid xs={12} sm={5} sx={{ display: 'flex', flexAlign: 'center', justifyContent: 'center' }}>
|
||||
<Button
|
||||
fullWidth variant='outlined' color='primary' startDecorator={<AccessTimeIcon />}
|
||||
disabled
|
||||
fullWidth variant='soft' color='primary' endDecorator={<SupportAgentIcon />}
|
||||
component={Link} href={bigAgiSupport} noLinkStyle target='_blank'
|
||||
// disabled
|
||||
>
|
||||
Coming Fall 2024
|
||||
Support
|
||||
</Button>
|
||||
</Grid>
|
||||
|
||||
</Grid>
|
||||
</CardContent>
|
||||
</Card>;
|
||||
@@ -51,6 +51,19 @@ interface NewsItem {
|
||||
|
||||
// news and feature surfaces
|
||||
export const NewsItems: NewsItem[] = [
|
||||
{
|
||||
versionCode: '2.0',
|
||||
versionName: 'Big-AGI',
|
||||
versionDate: new Date('2025-10-06T00:00:00Z'),
|
||||
// text: <>Big-AGI 2.0 is now available at <B href='https://app.big-agi.com'>app.big-agi.com</B></>,
|
||||
items: [
|
||||
{ text: <>Big-AGI 2.0 is ready with top-notch AI models support and more productive and faster than ever, including:</> },
|
||||
{ text: <><B href='https://app.big-agi.com' wow>Beam 2</B>: multi-modal, program-based, follow-ups, save presets</>, icon: ChatBeamIcon },
|
||||
{ text: <><B wow>Personas</B>: craft your perfect AI assistants with data support</> },
|
||||
{ text: <><B wow>Cloud Sync</B>: never lose your data</> },
|
||||
{ text: <>Built for the future, madly optimized</> },
|
||||
],
|
||||
},
|
||||
/*{
|
||||
versionCode: '1.17.0',
|
||||
items: [
|
||||
@@ -61,7 +74,7 @@ export const NewsItems: NewsItem[] = [
|
||||
]
|
||||
}*/
|
||||
{
|
||||
versionCode: '1.16.8',
|
||||
versionCode: '1.16.9',
|
||||
versionName: 'Crystal Clear',
|
||||
versionDate: new Date('2024-06-07T05:00:00Z'),
|
||||
// versionDate: new Date('2024-05-13T19:00:00Z'),
|
||||
@@ -85,7 +98,8 @@ export const NewsItems: NewsItem[] = [
|
||||
{ text: <>1.16.6: Groq <B>Llama 3.1</B> support</> },
|
||||
{ text: <>1.16.7: Gpt-4o <B>2024-08-06</B></> },
|
||||
{ text: <>1.16.8: <B>ChatGPT-4o</B> latest</> },
|
||||
{ text: <>OpenAI <B>o1</B> and newer models require Big-AGI 2. <B href='https://y2rjg0zillz.typeform.com/to/ZSADpr5u?utm_source=gh-stable&utm_medium=news&utm_campaign=ea2'>Sign up here</B></> },
|
||||
{ text: <>1.16.9: <B>Gemini</B> fixes</> },
|
||||
{ text: <>OpenAI <B>o1</B>, DeepSeek R1, and newer models require Big-AGI 2. <B href='https://form.typeform.com/to/ZSADpr5u?utm_source=gh-stable&utm_medium=news&utm_campaign=ea2'>Sign up here</B></> },
|
||||
],
|
||||
},
|
||||
{
|
||||
|
||||
@@ -7,7 +7,7 @@ import { useAppStateStore } from '~/common/state/store-appstate';
|
||||
|
||||
|
||||
// update this variable every time you want to broadcast a new version to clients
|
||||
export const incrementalNewsVersion: number = 16.1; // not notifying for 1.16.8
|
||||
export const incrementalNewsVersion: number = 16.9; // not notifying for 1.16.9
|
||||
|
||||
|
||||
interface NewsState {
|
||||
|
||||
@@ -22,8 +22,20 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
|
||||
// },
|
||||
// },
|
||||
{
|
||||
id: 'claude-3-5-sonnet-20240620',
|
||||
id: 'claude-3-5-sonnet-20241022',
|
||||
label: 'Claude 3.5 Sonnet',
|
||||
created: roundTime('2024-10-22 06:00'),
|
||||
description: 'Most intelligent Claude model to date',
|
||||
contextWindow: 200000, // Characters
|
||||
maxCompletionTokens: 8192,
|
||||
trainingDataCutoff: 'Apr 2024',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
|
||||
pricing: { chatIn: 3, chatOut: 15 },
|
||||
benchmark: { cbaElo: 1269, cbaMmlu: 88.7 }, // moved from 3.5 Sonnet (Previous Version), TO UPDATE!!
|
||||
},
|
||||
{
|
||||
id: 'claude-3-5-sonnet-20240620',
|
||||
label: 'Claude 3.5 Sonnet (Previous)',
|
||||
created: roundTime('2024-06-20 06:00'),
|
||||
description: 'The most intelligent Claude model',
|
||||
contextWindow: 200000, // Characters
|
||||
@@ -31,13 +43,8 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
|
||||
trainingDataCutoff: 'Apr 2024',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
|
||||
pricing: { chatIn: 3, chatOut: 15 },
|
||||
benchmark: {
|
||||
heCode: 92.0,
|
||||
vqaMmmu: 68.3,
|
||||
// TODO: Update with official benchmarks when available
|
||||
cbaElo: 1256 - 1, // Placeholder
|
||||
cbaMmlu: 86.8 - 1, // Placeholder
|
||||
},
|
||||
benchmark: { cbaElo: 1269 - 0.1, cbaMmlu: 88.7 - 0.1 },
|
||||
hidden: true,
|
||||
},
|
||||
// {
|
||||
// id: 'claude-3.5-haiku', // ...
|
||||
@@ -81,6 +88,7 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
|
||||
pricing: { chatIn: 3, chatOut: 15 },
|
||||
benchmark: { cbaElo: 1203, cbaMmlu: 79 },
|
||||
hidden: true,
|
||||
isLegacy: true,
|
||||
},
|
||||
{
|
||||
id: 'claude-3-haiku-20240307',
|
||||
@@ -131,24 +139,4 @@ export const hardcodedAnthropicModels: (ModelDescriptionSchema & { isLegacy?: bo
|
||||
pricing: { chatIn: 0.8, chatOut: 2.4 },
|
||||
hidden: true,
|
||||
},
|
||||
// {
|
||||
// id: 'claude-instant-1.1',
|
||||
// label: 'Claude Instant 1.1',
|
||||
// created: roundTime('2023-03-14'),
|
||||
// description: 'Precise and fast',
|
||||
// contextWindow: 100000,
|
||||
// maxCompletionTokens: 2048,
|
||||
// interfaces: [LLM_IF_OAI_Chat],
|
||||
// hidden: true,
|
||||
// },
|
||||
// {
|
||||
// id: 'claude-1.3',
|
||||
// label: 'Claude 1.3',
|
||||
// created: roundTime('2023-03-14'),
|
||||
// description: 'Claude 1.3 is the latest version of Claude v1',
|
||||
// contextWindow: 100000,
|
||||
// maxCompletionTokens: 4096,
|
||||
// interfaces: [LLM_IF_OAI_Chat],
|
||||
// hidden: true,
|
||||
// },
|
||||
];
|
||||
@@ -1,6 +1,6 @@
|
||||
import type { GeminiModelSchema } from './gemini.wiretypes';
|
||||
import type { ModelDescriptionSchema } from '../llm.server.types';
|
||||
import { LLM_IF_OAI_Chat, LLM_IF_OAI_Json, LLM_IF_OAI_Vision } from '../../store-llms';
|
||||
import { LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Json, LLM_IF_OAI_Vision } from '../../store-llms';
|
||||
|
||||
|
||||
// dev options
|
||||
@@ -12,7 +12,21 @@ const geminiChatInterfaces: GeminiModelSchema['supportedGenerationMethods'] = ['
|
||||
|
||||
// unsupported interfaces
|
||||
const filterUnallowedNames = ['Legacy'];
|
||||
const filterUnallowedInterfaces: GeminiModelSchema['supportedGenerationMethods'] = ['generateAnswer', 'embedContent', 'embedText'];
|
||||
const filterUnallowedInterfaces: GeminiModelSchema['supportedGenerationMethods'] = [
|
||||
'generateAnswer', // e.g. removes "models/aqa"
|
||||
'embedContent', // e.g. removes "models/embedding-001"
|
||||
'embedText', // e.g. removes "models/text-embedding-004"
|
||||
'predict', // e.g. removes "models/imagen-3.0-generate-002" (appeared on 2025-02-09)
|
||||
];
|
||||
const filterLyingModelNames: GeminiModelSchema['name'][] = [
|
||||
// 2025-02-27: verified, old model is no more
|
||||
'models/gemini-2.0-flash-exp', // verified, replaced by gemini-2.0-flash, which is non-free anymore
|
||||
|
||||
// 2025-02-09 update: as of now they cleared the list, so we restart
|
||||
// 2024-12-10: name of models that are not what they say they are (e.g. 1114 is actually 1121 as of )
|
||||
'models/gemini-1.5-flash-8b-exp-0924', // replaced by non-free
|
||||
'models/gemini-1.5-flash-8b-exp-0827', // replaced by non-free
|
||||
];
|
||||
|
||||
|
||||
/* Manual models details
|
||||
@@ -20,175 +34,405 @@ const filterUnallowedInterfaces: GeminiModelSchema['supportedGenerationMethods']
|
||||
- Latest version gemini-1.0-pro-latest <model>-<generation>-<variation>-latest
|
||||
- Latest stable version gemini-1.0-pro <model>-<generation>-<variation>
|
||||
- Stable versions gemini-1.0-pro-001 <model>-<generation>-<variation>-<version>
|
||||
|
||||
Gemini capabilities chart (updated 2024-10-01):
|
||||
- [table stakes] System instructions
|
||||
- JSON Mode, with optional JSON Schema [NOTE: JSON Schema is poorly supported?]
|
||||
- Adjustable Safety Settings
|
||||
- Caching
|
||||
- Tuning
|
||||
- [good] Function calling, with configuration
|
||||
- [great] Code execution
|
||||
*/
|
||||
|
||||
// Experimental Gemini models are Free of charge
|
||||
const geminiExpPricingFree: ModelDescriptionSchema['pricing'] = {
|
||||
// input: 'free', output: 'free',
|
||||
};
|
||||
|
||||
const gemini20FlashPricing: ModelDescriptionSchema['pricing'] = {
|
||||
chatIn: 0.10, // inputAudio: 0.70,
|
||||
chatOut: 0.40,
|
||||
};
|
||||
|
||||
const gemini20FlashLitePricing: ModelDescriptionSchema['pricing'] = {
|
||||
chatIn: 0.075,
|
||||
chatOut: 0.30,
|
||||
};
|
||||
|
||||
const gemini15FlashPricing: ModelDescriptionSchema['pricing'] = {
|
||||
chatIn: 0.075,
|
||||
chatOut: 0.30,
|
||||
};
|
||||
|
||||
const gemini15Flash8BPricing: ModelDescriptionSchema['pricing'] = {
|
||||
chatIn: 0.0375,
|
||||
chatOut: 0.15,
|
||||
};
|
||||
|
||||
const gemini15ProPricing: ModelDescriptionSchema['pricing'] = {
|
||||
chatIn: 1.25,
|
||||
chatOut: 5.00,
|
||||
};
|
||||
|
||||
|
||||
const _knownGeminiModels: ({
|
||||
id: string,
|
||||
labelOverride?: string,
|
||||
isNewest?: boolean,
|
||||
isPreview?: boolean
|
||||
symLink?: string
|
||||
} & Pick<ModelDescriptionSchema, 'interfaces' | 'pricing' | 'trainingDataCutoff' | 'hidden'>)[] = [
|
||||
isPreview?: boolean,
|
||||
symLink?: string,
|
||||
deprecated?: string, // Gemini may provide deprecation dates
|
||||
_delete?: boolean, // some gemini models are not acknowledged by Google Docs anymore, and leaving them in the list will confuse users
|
||||
} & Pick<ModelDescriptionSchema, 'interfaces' | 'pricing' | 'hidden' | 'benchmark'>)[] = [
|
||||
|
||||
// Generation 1.5
|
||||
/// Generation 2.5
|
||||
|
||||
// 2.5 Pro Experimental
|
||||
{
|
||||
id: 'models/gemini-2.5-pro-exp-03-25',
|
||||
isPreview: true,
|
||||
pricing: geminiExpPricingFree,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1443 },
|
||||
},
|
||||
|
||||
/// Generation 2.0
|
||||
|
||||
// 2.0 Experimental - Pro
|
||||
{
|
||||
hidden: true, // showing the 2.5 instead
|
||||
id: 'models/gemini-2.0-pro-exp-02-05', // Base model: Gemini 2.0 Pro
|
||||
isPreview: true,
|
||||
pricing: geminiExpPricingFree,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1380 },
|
||||
},
|
||||
{
|
||||
hidden: true, // only keeping the latest
|
||||
id: 'models/gemini-2.0-pro-exp',
|
||||
symLink: 'models/gemini-2.0-pro-exp-02-05',
|
||||
// copied from symlink
|
||||
isPreview: true,
|
||||
pricing: geminiExpPricingFree,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1380 },
|
||||
},
|
||||
{
|
||||
_delete: true, // replaced by gemini-2.0-pro-exp-02-05, 2025-02-27: verified, old model is no more
|
||||
id: 'models/gemini-exp-1206',
|
||||
labelOverride: 'Gemini 2.0 Pro Experimental 1206',
|
||||
isPreview: true,
|
||||
pricing: geminiExpPricingFree,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1373 },
|
||||
},
|
||||
|
||||
// 2.0 Experimental - Flash Thinking
|
||||
{
|
||||
hidden: true, // only keeping the latest
|
||||
id: 'models/gemini-2.0-flash-thinking-exp', // alias to the latest Flash Thinking model
|
||||
labelOverride: 'Gemini 2.0 Flash Thinking Experimental',
|
||||
symLink: 'models/gemini-2.0-flash-thinking-exp-01-21',
|
||||
// copied from symlink
|
||||
pricing: geminiExpPricingFree,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
|
||||
benchmark: { cbaElo: 1385 },
|
||||
isPreview: true,
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-2.0-flash-thinking-exp-01-21',
|
||||
pricing: geminiExpPricingFree,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
|
||||
benchmark: { cbaElo: 1385 },
|
||||
isPreview: true,
|
||||
},
|
||||
{
|
||||
hidden: true, // replaced by gemini-2.0-flash-thinking-exp-01-21 - 2025-02-27: seems still different on the API, hence no deletion yet
|
||||
id: 'models/gemini-2.0-flash-thinking-exp-1219',
|
||||
labelOverride: 'Gemini 2.0 Flash Thinking Experimental 12-19',
|
||||
pricing: geminiExpPricingFree,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
|
||||
benchmark: { cbaElo: 1363 },
|
||||
isPreview: true,
|
||||
},
|
||||
|
||||
// 2.0 Experimental - Flash Image Generation
|
||||
{
|
||||
id: 'models/gemini-2.0-flash-exp-image-generation',
|
||||
// labelOverride: 'Gemini 2.0 Flash Native Image Generation',
|
||||
pricing: geminiExpPricingFree,
|
||||
interfaces: [
|
||||
LLM_IF_OAI_Chat, LLM_IF_OAI_Vision,
|
||||
// LLM_IF_HOTFIX_StripSys0, // This first Gemini Image Generation model does not support the developer instruction
|
||||
],
|
||||
isPreview: true,
|
||||
},
|
||||
|
||||
// 2.0 Flash
|
||||
{
|
||||
id: 'models/gemini-2.0-flash-001',
|
||||
pricing: gemini20FlashPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1358 },
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-2.0-flash',
|
||||
symLink: 'models/gemini-2.0-flash-001',
|
||||
// copied from symlink
|
||||
pricing: gemini20FlashPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1358 },
|
||||
},
|
||||
|
||||
// 2.0 Flash Lite
|
||||
{
|
||||
id: 'models/gemini-2.0-flash-lite',
|
||||
pricing: gemini20FlashLitePricing,
|
||||
symLink: 'models/gemini-2.0-flash-lite-001',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1309 },
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-2.0-flash-lite-001',
|
||||
pricing: gemini20FlashLitePricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1309 },
|
||||
},
|
||||
{
|
||||
hidden: true, // discouraged, as the official is out
|
||||
id: 'models/gemini-2.0-flash-lite-preview-02-05',
|
||||
isPreview: true,
|
||||
pricing: gemini20FlashLitePricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1309 },
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-2.0-flash-lite-preview',
|
||||
symLink: 'models/gemini-2.0-flash-lite-preview-02-05',
|
||||
// coped from symlink
|
||||
isPreview: true,
|
||||
pricing: gemini20FlashLitePricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1309 },
|
||||
},
|
||||
|
||||
|
||||
/// Generation 1.5
|
||||
|
||||
// Gemini 1.5 Flash Models
|
||||
{
|
||||
id: 'models/gemini-1.5-flash-latest', // updated regularly and might be a preview version
|
||||
isNewest: true,
|
||||
isPreview: true,
|
||||
pricing: {
|
||||
chatIn: 0.70, // 0.35 up to 128k tokens, 0.70 prompts > 128k tokens
|
||||
chatOut: 2.10, // 1.05 up to 128k tokens, 2.10 prompts > 128k tokens
|
||||
},
|
||||
trainingDataCutoff: 'May 2024',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json], // input: audio, images and text
|
||||
pricing: gemini15FlashPricing,
|
||||
// symLink: '-002 or newer',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-flash',
|
||||
// copied from above
|
||||
pricing: {
|
||||
chatIn: 0.70, // 0.35 up to 128k tokens, 0.70 prompts > 128k tokens
|
||||
chatOut: 2.10, // 1.05 up to 128k tokens, 2.10 prompts > 128k tokens
|
||||
},
|
||||
trainingDataCutoff: 'Apr 2024',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json], // input: audio, images and text
|
||||
// Defaults to version 002 on Oct 8, 2024
|
||||
symLink: 'models/gemini-1.5-flash-002',
|
||||
pricing: gemini15FlashPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1271 },
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-flash-002', // new stable version
|
||||
pricing: gemini15FlashPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1271 },
|
||||
hidden: true,
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-flash-001',
|
||||
// copied from above
|
||||
pricing: {
|
||||
chatIn: 0.70, // 0.35 up to 128k tokens, 0.70 prompts > 128k tokens
|
||||
chatOut: 2.10, // 1.05 up to 128k tokens, 2.10 prompts > 128k tokens
|
||||
},
|
||||
trainingDataCutoff: 'Apr 2024',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json], // input: audio, images and text
|
||||
id: 'models/gemini-1.5-flash-001', // previous stable version
|
||||
pricing: gemini15FlashPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1227 },
|
||||
hidden: true,
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-flash-001-tuning', // supports model tuning
|
||||
pricing: gemini15FlashPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn /* Tuning ... */],
|
||||
hidden: true,
|
||||
},
|
||||
|
||||
// Gemini 1.5 Flash-8B Models
|
||||
{
|
||||
id: 'models/gemini-1.5-pro-latest', // updated regularly and might be a preview version
|
||||
isNewest: true,
|
||||
isPreview: true,
|
||||
pricing: {
|
||||
chatIn: 7.00, // $3.50 / 1 million tokens (for prompts up to 128K tokens), $7.00 / 1 million tokens (for prompts longer than 128K)
|
||||
chatOut: 21.00, // $10.50 / 1 million tokens (128K or less), $21.00 / 1 million tokens (128K+)
|
||||
},
|
||||
trainingDataCutoff: 'May 2024',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json], // input: audio, images and text
|
||||
id: 'models/gemini-1.5-flash-8b-latest',
|
||||
isPreview: false,
|
||||
pricing: gemini15Flash8BPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-pro', // latest stable -> 001
|
||||
// copied from above
|
||||
pricing: {
|
||||
chatIn: 7.00, // $3.50 / 1 million tokens (for prompts up to 128K tokens), $7.00 / 1 million tokens (for prompts longer than 128K)
|
||||
chatOut: 21.00, // $10.50 / 1 million tokens (128K or less), $21.00 / 1 million tokens (128K+)
|
||||
},
|
||||
trainingDataCutoff: 'Apr 2024',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json],
|
||||
id: 'models/gemini-1.5-flash-8b',
|
||||
symLink: 'models/gemini-1.5-flash-8b-001',
|
||||
pricing: gemini15Flash8BPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1213 },
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-flash-8b-001',
|
||||
pricing: gemini15Flash8BPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1213 },
|
||||
hidden: true,
|
||||
},
|
||||
|
||||
// Gemini 1.5 Pro Models
|
||||
{
|
||||
id: 'models/gemini-1.5-pro-latest', // updated to latest stable version
|
||||
pricing: gemini15ProPricing,
|
||||
// symLink: '-002 or newer',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-pro',
|
||||
symLink: 'models/gemini-1.5-pro-002',
|
||||
pricing: gemini15ProPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1302 },
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-pro-002',
|
||||
pricing: gemini15ProPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1302 },
|
||||
hidden: true,
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.5-pro-001', // stable snapshot
|
||||
// copied from above
|
||||
pricing: {
|
||||
chatIn: 7.00, // $3.50 / 1 million tokens (for prompts up to 128K tokens), $7.00 / 1 million tokens (for prompts longer than 128K)
|
||||
chatOut: 21.00, // $10.50 / 1 million tokens (128K or less), $21.00 / 1 million tokens (128K+)
|
||||
},
|
||||
trainingDataCutoff: 'Apr 2024',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json],
|
||||
id: 'models/gemini-1.5-pro-001',
|
||||
pricing: gemini15ProPricing,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Json, LLM_IF_OAI_Fn],
|
||||
benchmark: { cbaElo: 1260 },
|
||||
hidden: true,
|
||||
},
|
||||
|
||||
|
||||
// Generation 1.0
|
||||
{
|
||||
id: 'models/gemini-1.0-pro-latest',
|
||||
pricing: {
|
||||
chatIn: 0.50,
|
||||
chatOut: 1.50,
|
||||
},
|
||||
interfaces: [LLM_IF_OAI_Chat],
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.0-pro',
|
||||
pricing: {
|
||||
chatIn: 0.50,
|
||||
chatOut: 1.50,
|
||||
},
|
||||
interfaces: [LLM_IF_OAI_Chat],
|
||||
hidden: true,
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-1.0-pro-001',
|
||||
pricing: {
|
||||
chatIn: 0.50,
|
||||
chatOut: 1.50,
|
||||
},
|
||||
interfaces: [LLM_IF_OAI_Chat],
|
||||
hidden: true,
|
||||
},
|
||||
/// Generation 1.0
|
||||
|
||||
// Generation 1.0 + Vision
|
||||
// Gemini 1.0 Pro Vision Model
|
||||
{
|
||||
id: 'models/gemini-1.0-pro-vision-latest',
|
||||
pricing: {
|
||||
chatIn: 0.50,
|
||||
chatOut: 1.50,
|
||||
},
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision], // Text and Images
|
||||
hidden: true,
|
||||
},
|
||||
|
||||
// Older symlinks
|
||||
{
|
||||
id: 'models/gemini-pro',
|
||||
symLink: 'models/gemini-1.0-pro',
|
||||
// copied from symlinked
|
||||
pricing: {
|
||||
chatIn: 0.50,
|
||||
chatOut: 1.50,
|
||||
},
|
||||
interfaces: [LLM_IF_OAI_Chat],
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
|
||||
hidden: true,
|
||||
_delete: true, // confusing
|
||||
},
|
||||
{
|
||||
id: 'models/gemini-pro-vision',
|
||||
// copied from symlinked
|
||||
symLink: 'models/gemini-1.0-pro-vision',
|
||||
pricing: {
|
||||
chatIn: 0.50,
|
||||
chatOut: 1.50,
|
||||
},
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision], // Text and Images
|
||||
hidden: true,
|
||||
_delete: true, // confusing
|
||||
},
|
||||
|
||||
|
||||
/// Experimental
|
||||
|
||||
// LearnLM Experimental Model
|
||||
{
|
||||
id: 'models/learnlm-1.5-pro-experimental',
|
||||
isPreview: true,
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision],
|
||||
pricing: geminiExpPricingFree,
|
||||
// hidden: true,
|
||||
// _delete: true,
|
||||
},
|
||||
|
||||
{
|
||||
id: 'models/gemma-3-27b-it',
|
||||
isPreview: true,
|
||||
interfaces: [
|
||||
LLM_IF_OAI_Chat,
|
||||
// LLM_IF_HOTFIX_StripImages, /* "Image input modality is not enabled for models/gemma-3-27b-it" */
|
||||
// LLM_IF_HOTFIX_Sys0ToUsr0, /* "Developer instruction is not enabled for models/gemma-3-27b-it" */
|
||||
],
|
||||
// pricing: geminiExpPricingFree,
|
||||
// hidden: true,
|
||||
// _delete: true,
|
||||
},
|
||||
|
||||
];
|
||||
|
||||
|
||||
export function geminiFilterModels(geminiModel: GeminiModelSchema): boolean {
|
||||
const isAllowed = !filterUnallowedNames.some(name => geminiModel.displayName.includes(name));
|
||||
const isSupported = !filterUnallowedInterfaces.some(iface => geminiModel.supportedGenerationMethods.includes(iface));
|
||||
return isAllowed && isSupported;
|
||||
const isWhatItSaysItIs = !filterLyingModelNames.includes(geminiModel.name);
|
||||
return isAllowed && isSupported && isWhatItSaysItIs;
|
||||
}
|
||||
|
||||
|
||||
const _sortOderIdPrefix: string[] = [
|
||||
'models/gemini-exp',
|
||||
'models/gemini-2.5-pro',
|
||||
'models/gemini-2.0-pro',
|
||||
'models/gemini-2.0-flash-exp-image-generation',
|
||||
'models/gemini-2.0-flash-thinking',
|
||||
'models/gemini-2.0-flash-0',
|
||||
'models/gemini-2.0-flash',
|
||||
'models/gemini-2.0-flash-lite',
|
||||
'models/gemini-1.5-pro',
|
||||
'models/gemini-1.5-flash',
|
||||
'models/gemini-1.5-flash-8b',
|
||||
'models/gemini-1.0-pro',
|
||||
'models/gemini-pro',
|
||||
'models/gemma',
|
||||
'models/learnlm',
|
||||
] as const;
|
||||
|
||||
export function geminiSortModels(a: ModelDescriptionSchema, b: ModelDescriptionSchema): number {
|
||||
// links to the bottom
|
||||
const aIsLink = a.label.startsWith('🔗');
|
||||
const bIsLink = b.label.startsWith('🔗');
|
||||
if (aIsLink && !bIsLink) return 1;
|
||||
if (!aIsLink && bIsLink) return -1;
|
||||
|
||||
// hidden to the bottom, then names descending
|
||||
if (a.hidden && !b.hidden) return 1;
|
||||
if (!a.hidden && b.hidden) return -1;
|
||||
// if (a.hidden && !b.hidden) return 1;
|
||||
// if (!a.hidden && b.hidden) return -1;
|
||||
|
||||
// models beginning with 'gemini-' to the top
|
||||
// const aGemini = a.label.startsWith('Gemini');
|
||||
// const bGemini = b.label.startsWith('Gemini');
|
||||
// if (aGemini && !bGemini) return -1;
|
||||
// if (!aGemini && bGemini) return 1;
|
||||
|
||||
// sort by sortOrderIdPrefix
|
||||
const aSortIdx = _sortOderIdPrefix.findIndex(p => a.id.startsWith(p));
|
||||
const bSortIdx = _sortOderIdPrefix.findIndex(p => b.id.startsWith(p));
|
||||
if (aSortIdx !== -1 && bSortIdx !== -1) {
|
||||
if (aSortIdx < bSortIdx) return -1;
|
||||
if (aSortIdx > bSortIdx) return 1;
|
||||
}
|
||||
|
||||
// sort by label descending
|
||||
return b.label.localeCompare(a.label);
|
||||
}
|
||||
|
||||
export function geminiModelToModelDescription(geminiModel: GeminiModelSchema): ModelDescriptionSchema {
|
||||
|
||||
export function geminiModelToModelDescription(geminiModel: GeminiModelSchema): ModelDescriptionSchema | null {
|
||||
const { description, displayName, name: modelId, supportedGenerationMethods } = geminiModel;
|
||||
|
||||
if (DEV_DEBUG_GEMINI_MODELS)
|
||||
console.log('geminiModelToModelDescription', geminiModel);
|
||||
// if (DEV_DEBUG_GEMINI_MODELS)
|
||||
// console.log('geminiModelToModelDescription', geminiModel);
|
||||
|
||||
// find known manual mapping
|
||||
const knownModel = _knownGeminiModels.find(m => m.id === modelId);
|
||||
if (!knownModel && DEV_DEBUG_GEMINI_MODELS)
|
||||
console.warn('geminiModelToModelDescription: unknown model', modelId, geminiModel);
|
||||
|
||||
// handle _delete
|
||||
if (knownModel?._delete)
|
||||
return null;
|
||||
|
||||
// handle symlinks
|
||||
const label = knownModel?.symLink
|
||||
? `🔗 ${displayName.replace('1.0', '')} → ${knownModel.symLink}`
|
||||
: displayName;
|
||||
let label = knownModel?.symLink
|
||||
? `🔗 ${knownModel?.labelOverride || displayName} → ${knownModel.symLink}`
|
||||
: knownModel?.labelOverride || displayName;
|
||||
|
||||
// FIX: the Gemini 1114 model now returns 1121 as the version.. highlight the issue
|
||||
// if (geminiModel.name.endsWith('1114') && label.endsWith('1121'))
|
||||
// label += ' (really: 1114)';
|
||||
|
||||
// handle hidden models
|
||||
const hasChatInterfaces = supportedGenerationMethods.some(iface => geminiChatInterfaces.includes(iface));
|
||||
@@ -200,14 +444,13 @@ export function geminiModelToModelDescription(geminiModel: GeminiModelSchema): M
|
||||
|
||||
// description
|
||||
const { version, topK, topP, temperature } = geminiModel;
|
||||
const descriptionLong = description + ` (Version: ${version}, Defaults: temperature=${temperature}, topP=${topP}, topK=${topK}, interfaces=[${supportedGenerationMethods.join(',')}])`;
|
||||
const descriptionLong = (description || 'No description.') + ` (Version: ${version}, Defaults: temperature=${temperature}, topP=${topP}, topK=${topK}, interfaces=[${supportedGenerationMethods.join(',')}])`;
|
||||
|
||||
// use known interfaces, or add chat if this is a generateContent model
|
||||
const interfaces: ModelDescriptionSchema['interfaces'] = knownModel?.interfaces || [];
|
||||
if (!interfaces.length && hasChatInterfaces) {
|
||||
interfaces.push(LLM_IF_OAI_Chat);
|
||||
// if (geminiVisionNames.some(name => modelId.includes(name)))
|
||||
// interfaces.push(LLM_IF_OAI_Vision);
|
||||
// newer models get good capabilities by default
|
||||
interfaces.push(LLM_IF_OAI_Chat, LLM_IF_OAI_Fn, LLM_IF_OAI_Vision, LLM_IF_OAI_Json);
|
||||
}
|
||||
|
||||
return {
|
||||
@@ -218,11 +461,13 @@ export function geminiModelToModelDescription(geminiModel: GeminiModelSchema): M
|
||||
description: descriptionLong,
|
||||
contextWindow: contextWindow,
|
||||
maxCompletionTokens: outputTokenLimit,
|
||||
trainingDataCutoff: knownModel?.trainingDataCutoff,
|
||||
// trainingDataCutoff: knownModel?.trainingDataCutoff, // disabled as we don't get this from Gemini
|
||||
interfaces,
|
||||
// parameterSpecs: knownModel?.parameterSpecs,
|
||||
// rateLimits: isGeminiPro ? { reqPerMinute: 60 } : undefined,
|
||||
// benchmarks: ...
|
||||
pricing: knownModel?.pricing, // TODO: needs <>128k, and per-character and per-image pricing
|
||||
benchmark: knownModel?.benchmark,
|
||||
pricing: knownModel?.pricing,
|
||||
hidden,
|
||||
// deprecated: knownModel?.deprecated,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -8,7 +8,7 @@ import { createTRPCRouter, publicProcedure } from '~/server/api/trpc.server';
|
||||
import { fetchJsonOrTRPCError } from '~/server/api/trpc.router.fetchers';
|
||||
|
||||
import { fixupHost } from '~/common/util/urlUtils';
|
||||
import { llmsChatGenerateOutputSchema, llmsGenerateContextSchema, llmsListModelsOutputSchema } from '../llm.server.types';
|
||||
import { llmsChatGenerateOutputSchema, llmsGenerateContextSchema, llmsListModelsOutputSchema, type ModelDescriptionSchema } from '../llm.server.types';
|
||||
|
||||
import { OpenAIHistorySchema, openAIHistorySchema, OpenAIModelSchema, openAIModelSchema } from '../openai/openai.router';
|
||||
|
||||
@@ -148,9 +148,10 @@ export const llmGeminiRouter = createTRPCRouter({
|
||||
// as the List API already all the info on all the models
|
||||
|
||||
// map to our output schema
|
||||
const models = detailedModels
|
||||
const models = (detailedModels
|
||||
.filter(geminiFilterModels)
|
||||
.map(geminiModel => geminiModelToModelDescription(geminiModel))
|
||||
.filter(model => !!model) as ModelDescriptionSchema[])
|
||||
.sort(geminiSortModels);
|
||||
|
||||
return {
|
||||
|
||||
@@ -9,28 +9,30 @@ export const geminiModelsStreamGenerateContentPath = '/v1beta/{model=models/*}:s
|
||||
|
||||
|
||||
// models.list = /v1beta/models
|
||||
const Methods_enum = z.enum([
|
||||
'bidiGenerateContent', // appeared on 2024-12, see https://github.com/enricoros/big-AGI/issues/700
|
||||
'createCachedContent', // appeared on 2024-06-10, see https://github.com/enricoros/big-AGI/issues/565
|
||||
'countMessageTokens',
|
||||
'countTextTokens',
|
||||
'countTokens',
|
||||
'createTunedModel',
|
||||
'createTunedTextModel',
|
||||
'embedContent',
|
||||
'embedText',
|
||||
'generateAnswer',
|
||||
'generateContent',
|
||||
'generateMessage',
|
||||
'generateText',
|
||||
]);
|
||||
|
||||
const geminiModelSchema = z.object({
|
||||
name: z.string(),
|
||||
version: z.string(),
|
||||
displayName: z.string(),
|
||||
description: z.string(),
|
||||
description: z.string().optional(),
|
||||
inputTokenLimit: z.number().int().min(1),
|
||||
outputTokenLimit: z.number().int().min(1),
|
||||
supportedGenerationMethods: z.array(z.enum([
|
||||
'createCachedContent', // appeared on 2024-06-10, see https://github.com/enricoros/big-AGI/issues/565
|
||||
'countMessageTokens',
|
||||
'countTextTokens',
|
||||
'countTokens',
|
||||
'createTunedModel',
|
||||
'createTunedTextModel',
|
||||
'embedContent',
|
||||
'embedText',
|
||||
'generateAnswer',
|
||||
'generateContent',
|
||||
'generateMessage',
|
||||
'generateText',
|
||||
])),
|
||||
supportedGenerationMethods: z.array(z.union([Methods_enum, z.string()])), // relaxed with z.union to not break on expansion
|
||||
temperature: z.number().optional(),
|
||||
topP: z.number().optional(),
|
||||
topK: z.number().optional(),
|
||||
@@ -172,7 +174,7 @@ export const geminiGeneratedContentResponseSchema = z.object({
|
||||
// either all requested candidates are returned or no candidates at all
|
||||
// no candidates are returned only if there was something wrong with the prompt (see promptFeedback)
|
||||
candidates: z.array(z.object({
|
||||
index: z.number(),
|
||||
index: z.number().optional(),
|
||||
content: geminiContentSchema.optional(), // this can be missing if the finishReason is not 'MAX_TOKENS'
|
||||
finishReason: geminiFinishReasonSchema.optional(),
|
||||
safetyRatings: z.array(geminiSafetyRatingSchema).optional(), // undefined when finishReason is 'RECITATION'
|
||||
|
||||
@@ -16,16 +16,16 @@ const _knownOpenAIChatModels: ManualMappings = [
|
||||
{
|
||||
idPrefix: 'gpt-4o',
|
||||
label: 'GPT-4o',
|
||||
description: 'Currently points to gpt-4o-2024-05-13.',
|
||||
symLink: 'gpt-4o-2024-05-13',
|
||||
description: 'Points to gpt-4o-2024-08-06 starting on Oct 2, 2024.',
|
||||
symLink: 'gpt-4o-2024-08-06',
|
||||
hidden: true,
|
||||
// copied from symlinked
|
||||
contextWindow: 128000,
|
||||
maxCompletionTokens: 4096,
|
||||
maxCompletionTokens: 16384,
|
||||
trainingDataCutoff: 'Oct 2023',
|
||||
interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Vision, LLM_IF_OAI_Fn, LLM_IF_OAI_Json],
|
||||
pricing: { chatIn: 5, chatOut: 15 },
|
||||
benchmark: { cbaElo: 1286 },
|
||||
pricing: { chatIn: 2.5, chatOut: 10 },
|
||||
benchmark: { cbaElo: 1286 + 1 },
|
||||
},
|
||||
{
|
||||
isLatest: true,
|
||||
@@ -742,10 +742,14 @@ export function openRouterModelFamilySortFn(a: { id: string }, b: { id: string }
|
||||
return aPrefixIndex !== -1 ? -1 : 1;
|
||||
}
|
||||
|
||||
export function openRouterModelToModelDescription(wireModel: object): ModelDescriptionSchema {
|
||||
export function openRouterModelToModelDescription(wireModel: object): ModelDescriptionSchema | null {
|
||||
|
||||
// parse the model
|
||||
const model = wireOpenrouterModelsListOutputSchema.parse(wireModel);
|
||||
const { data: model, error } = wireOpenrouterModelsListOutputSchema.safeParse(wireModel);
|
||||
if (error) {
|
||||
console.warn(`openrouterModelToModelDescription: Failed to parse model: ${error}`);
|
||||
return null;
|
||||
}
|
||||
|
||||
// parse pricing
|
||||
const pricing: ModelDescriptionSchema['pricing'] = {
|
||||
|
||||
@@ -256,7 +256,8 @@ export const llmOpenAIRouter = createTRPCRouter({
|
||||
case 'openrouter':
|
||||
models = openAIModels
|
||||
.sort(openRouterModelFamilySortFn)
|
||||
.map(openRouterModelToModelDescription);
|
||||
.map(openRouterModelToModelDescription)
|
||||
.filter(desc => !!desc) as ModelDescriptionSchema[];
|
||||
break;
|
||||
|
||||
}
|
||||
|
||||
@@ -5,16 +5,20 @@ export const wireOpenrouterModelsListOutputSchema = z.object({
|
||||
id: z.string(),
|
||||
name: z.string(),
|
||||
description: z.string(),
|
||||
// NOTE: for 'openrouter/auto', this is: {
|
||||
// "prompt": "-1",
|
||||
// "completion": "-1"
|
||||
// }
|
||||
pricing: z.object({
|
||||
prompt: z.string(),
|
||||
completion: z.string(),
|
||||
image: z.string(),
|
||||
request: z.string(),
|
||||
image: z.string().optional(),
|
||||
request: z.string().optional(),
|
||||
}),
|
||||
context_length: z.number(),
|
||||
architecture: z.object({
|
||||
modality: z.string(), // z.enum(['text', 'multimodal']),
|
||||
tokenizer: z.string(), // e.g. 'Mistral'
|
||||
modality: z.string(), // z.enum(['text', 'multimodal', 'text+image->text]),
|
||||
tokenizer: z.string(), // e.g. 'Mistral', 'Claude'
|
||||
instruct_type: z.string().nullable(),
|
||||
}),
|
||||
top_provider: z.object({
|
||||
|
||||
@@ -157,7 +157,7 @@ export async function downloadAllConversationsJson() {
|
||||
|
||||
// save file
|
||||
await fileSave(blob, {
|
||||
fileName: `conversations_${window?.location?.hostname || 'all'}_${payload.conversations.length}_${prettyTimestampForFilenames(false)}.agi.json`,
|
||||
fileName: `big-agi-1_conversations_${window?.location?.hostname || 'all'}_${payload.conversations.length}_${prettyTimestampForFilenames(false)}.agi.json`,
|
||||
// mimeTypes: ['application/json', 'application/big-agi'],
|
||||
extensions: ['.json'],
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user