Dify: Version 0.3.14
Dify 0.3.14. Source highlight: update llms
1172 tracked entries. Older history is imported progressively; see source coverage.
Dify 0.3.14. Source highlight: update llms
Dify 0.3.13. Source highlight: Support editing OPENAI_API_BASE in configuration modal.
LocalAI v1.24.1. Source highlight: This is a patch release - images were not correctly pushed by the CI in 1.24.0
LocalAI v.1.24.0. Source highlight: fix: upgrade pip
Ollama v0.0.14. Source highlight: **Ollama 🦜️🔗 LangChain Integration!** https://python.langchain.com/docs/integrations/llms/ollama
LocalAI v1.23.2. Source highlight: fix: do not break on newlines on function returns
vLLM v0.1.3. Source highlight: More model support: LLaMA 2, Falcon, GPT-J, Baichuan, etc.
LocalAI v1.23.1. Source highlight: Fix: Model Gallery Downloads
Ollama v0.0.13. Source highlight: Using Ollama CLI without Ollama running will now start Ollama
LocalAI v1.23.0. Source highlight: feat: add rope settings and negative prompt, drop grammar backend
Dify 0.3.12. Source highlight: dataset supports QA-style segmentation.
Dify 0.3.11. Source highlight: 🤖 We have released the **universal chat**, which now supports searching, reading web pages and wikipedia. We implemented this using the `function call` or `ReACT` agent strategy.
Ollama v0.0.12. Source highlight: You can now rename models you've pulled or created with `ollama cp`
LocalAI v1.22.0. Source highlight: refactor: rename "llama-master" to "llama" and "llama" to "llama-grammar"
Ollama v0.0.11. Source highlight: `ollama list`: stay organized: see which models you have and their size
Ollama v0.0.10 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Ollama v0.0.9 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Ollama v0.0.8 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Ollama v0.0.7. Source highlight: Performance improvements with `ollama create`: it now uses less memory and will create custom models in less time
Hugging Face Transformers v4.31.0. Source highlight: Llama 2 was proposed in LLaMA: Open Foundation and Fine-Tuned Chat Models by Hugo Touvron et al. It builds upon the Llama architecture adding Grouped Query Attention for efficient inference.
Ollama v0.0.6 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Dify 0.3.10. Source highlight: Update README.md
Dify 0.3.9. Source highlight: We supported the latest `Anthropic Claude-2` LLM! 🤩
LocalAI v1.21.0. Source highlight: fix: make first stream message to send empty content
Dify 0.3.8. Source highlight: Chat apps can be embedded into webpages 💻
Ollama v0.0.5. Source highlight: Show performance details, such as tokens per second with `ollama run --verbose`
Ollama v0.0.4 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Ollama v0.0.3. Source highlight: Much faster performance
Ollama v0.0.2. Source highlight: Improved reliability in cases where Ollama would encounter an error
Dify 0.3.7. Source highlight: 🎙️ Chat App support voice (OpenAI whisper)
Ollama v0.0.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
vLLM v0.1.2. Source highlight: Initial support for GPTBigCode
LocalAI v1.20.1. Source highlight: Update README.md
LocalAI v1.20.0. Source highlight: fix: return index and delta in stream token
Dify 0.3.6. Source highlight: bugfix: conversation parameters
vLLM v0.1.1. Source highlight: Fix Ray node resources error
Dify 0.3.5. Source highlight: 📁 dataset supports multi-file uploads
LocalAI v1.19.2. Source highlight: fix(deps): update module github.com/valyala/fasthttp to v1.48.0
LocalAI v1.19.1. Source highlight: :arrow_up: Update go-skynet/go-ggml-transformers.cpp
vLLM v0.1.0. Source highlight: The first official release of vLLM!
LocalAI v1.19.0. Source highlight: fix: set default batch size
Dify 0.3.4. Source highlight: 📃 Dataset support integration with **Notion**
Dify 0.3.3. Source highlight: 🤖 Support gpt-3.5-turbo-16k
Hugging Face Transformers v4.30.2. Source highlight: Fix push to hubby @NielsRogge in #24187
Hugging Face Transformers v4.30.1. Source highlight: Fix bnb config json serialization in #24137
Dify 0.3.2. Source highlight: 🤖 Auto-arrangement app: Input your intended audience & hoping AI can save scenes to quickly generate pipeline for app
Hugging Face Transformers v4.30.0. Source highlight: Transformers has just reached 100k stars on GitHub, and to celebrate we wanted to highlight 100 projects in the vicinity of `transformers` and we have decided to create an awesome-transformers page to do just that.
LocalAI v1.18.0. Source highlight: feat: Update gpt4all, support multiple implementations in runtime
LocalAI v1.17.1. Source highlight: ci: fix typo in variable name
Dify 0.3.1. Source highlight: Fix/shared lock