-
-
Notifications
You must be signed in to change notification settings - Fork 9.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
✨ feat: 支持用户自行定义 embedding model #4208
base: main
Are you sure you want to change the base?
Conversation
* 'main' of github.com:cookieY/lobe-chat: 🔖 chore(release): v1.20.5 [skip ci] 📝 docs: Update docker-compose to use new LOGTO env (lobehub#4199) 👷 build: optimize image size under glibc env (lobehub#4176) 🔖 chore(release): v1.20.4 [skip ci] ⚡ perf: remove some blur style to improve performance (lobehub#4085) Update dependency unstructured-client to ^0.18.0 (lobehub#4065) 📝 docs: Add deployment using ZITADEL authentication services (lobehub#4081) 🔖 chore(release): v1.20.3 [skip ci] 🐛 fix: improve delete orphan chunks when delete files (lobehub#4179) 📝 docs: add new configuration item of clerk singup (lobehub#4188) 📝 docs: update model-provider document (lobehub#4181) 🔖 chore(release): v1.20.2 [skip ci] 💄 style: add zhipu glm-4-flashx model (lobehub#4173) 👷 build: revert lobehub#4025 (lobehub#4175) 🔖 chore(release): v1.20.1 [skip ci] 👷 build: optimize image size under `glibc` env (lobehub#4025) 🔖 chore(release): v1.20.0 [skip ci] ✨ feat: add Hunyuan(Tencent) model provider (lobehub#4147) 🔖 chore(release): v1.19.36 [skip ci] 💄 style: add llama3.2 model for openrouter provider (lobehub#4151)
@cookieY is attempting to deploy a commit to the LobeChat Community Team on Vercel. A member of the Team first needs to authorize it. |
👍 @cookieY Thank you for raising your pull request and contributing to our Community |
💻 变更类型 | Change Type
🔀 变更说明 | Description of Change
本次变更主要实现了embedding 模型可配置性
通过新增环境变量DEFAULT_EMBEDDING_MODEL实现可自主配置embedding 模型, provider基于现有模型供应商列表
示例:
📝 补充信息 | Additional Information
目前已支持 openai bedrock ollama模型提供商 的 embedding 模型
可在agent-runtime下对各模型提供商实现 embeddings 方法从而增加 embedding 模型支持