Comments (1)
Pieces of Changelog; work in progress...
User-visible features
- Multipart
- Attach documents and images
- Edit documents (multi-part)
- Regenerate images, if generated
- Delete parts
- Multimodal
- Input images
- Image Gallery/manager for Draw/Chat
- Auto-UI (HTML web UIs)
- Beam: cleanups, +1, (Chat?, Remix?)
- Draw app
- Attach more types, more multi-modal
- Attach web pages: multi-type, with screenshots
- Code: show lines
- Deepseek vendor support
- Screen capture
- Docx files support
- Text Diff app
Smaller features:
- OpenRouter: option to remove non-free models
- HTML Attachments: cleaner html
- Better files drop, coexist with mic
- Browsing includes web page screenshots
Bugfixes:
- [NOT!] Fixed orders of attached files - dragging files from an IDE can result in reordered files
- Mac: cleaner and more usable shortcuts
- no double tap on the persona icon on mobile to edit
- do not remove leading spaces on code (esp. for Anthropic)
Developers
- tRPC 11
- trpc/trpc#5851
- Audio Generator
- nanoid, indexed
- Dexie for IndexedDB
- reverse proxy instructions
Notes
from big-agi.
Related Issues (20)
- [BUG] Skip "Auto diagram" - if a diagram is present? Otherwise it (9/10 times) duplicates the last diagram if one is already present. HOT 2
- [Roadmap] Expand should show the model. If you change models halfway, theres no obvious way to see which model generated what HOT 2
- Serving the app from subdirectory (mydomain.com/big-AGI) not working HOT 1
- Update all shortcuts
- Set server preference default HOT 3
- [Roadmap] Suggestion for obtaining available Anthropic models. HOT 1
- Three dots in zen appearence mode HOT 4
- [BUG] streaming doesnt work for me HOT 5
- Upload office documents such as .docx and .xlsx files HOT 2
- [BUG] ElevenLabs speach returns only in English if browser set to English HOT 1
- [Roadmap] Use OpenAI TTS models for speech generation to avoid having too many API keys HOT 1
- Question: Curious why only max output token counts are given rather than the precise count HOT 3
- consider tagging a release HOT 3
- [BUG] markdown: bulletpoints render without line breaks? HOT 11
- Allow only specific models HOT 2
- How OpenAI determines the client's IP and geographic location when the server forwards the API request. HOT 10
- Call the application via API? HOT 6
- [BUG] Image not uploading to OpenAI HOT 5
- [Roadmap] Add support for `response_format` type `json_object` HOT 1
- [BUG] Autotitle does not default to current chat model HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from big-agi.