Comments (10)
Is it possible to use Claude 3 as a custom model?
from chatgpt-next-web.
Sample for anyone having issues, until the update arrived with better built in support for Claude-3
* `CUSTOM_MODELS="+claude-3-haiku-20240307"` * `ANTHROPIC_API_KEY="{your-api-key}"` * `ANTHROPIC_API_VERSION="2023-06-01"` (currently the latest version) * `ANTHROPIC_URL="https://api.anthropic.com/v1/messages"`
If you want to use selected models, add CUSTOM_MODELS=-all,+claude-3-sonnet-20240229,+[other models you need]
in docker-compose.yml
or all default models will be included in settings. Find exact model name in constant.ts.
For Claude, ANTHROPIC_API_KEY
is necessary (if you use official service), others like ANTHROPIC_API_VERSION
and ANTHROPIC_URL
are optional. Use ANTHROPIC_URL
if you access through a endpoint proxy (like third-party service provider).
from chatgpt-next-web.
try to open in InPrivate mode. Check whether it works.
from chatgpt-next-web.
try to open in InPrivate mode. Check whether it works.
I tried different broswer, it still doesn't work. Addtional, not only i can see the model list, but also can use it if the api key have permission.
from chatgpt-next-web.
Likely related issue, even after adding the ANTHROPIC_API_KEY
the Calude-3 models don't show up in model the list.
Using: docker
from chatgpt-next-web.
Likely related issue, even after adding the
ANTHROPIC_API_KEY
the Calude-3 models don't show up in model the list.
how did you start the container,docker run
or docker compose
?
Have you recreate the container after changing config?
Add ANTHROPIC_API_KEY
and CUSTOM_MODELS
(if you using), recreate(not restart) container, then refresh in browser.
from chatgpt-next-web.
Likely related issue, even after adding the
ANTHROPIC_API_KEY
the Calude-3 models don't show up in model the list.how did you start the container,
docker run
ordocker compose
? Have you recreate the container after changing config?Add
ANTHROPIC_API_KEY
andCUSTOM_MODELS
(if you using), recreate(not restart) container, then refresh in browser.
Sorry, after adding the CUSTOM_MODELS
environment variable, yes those custom models come through.
Although, I'm still not clear on how to add Anthropic's Claude-3 Haiku for instance to NextChat. I have the model open come in the GUI, however, I must be doing something wrong.
Could you provide a sample docker-compose.yml
or docker run
command that would add a Claude-3 model?
P.S. I was running NextChat with docker compose
from chatgpt-next-web.
I got it resolved.
Make sure to add of the following 3 environment variables to be able to use use Claude-3 (any model).
CUSTOM_MODELS
ANTHROPIC_API_KEY
ANTHROPIC_API_VERSION
ANTHROPIC_URL
Sample for anyone having issues, until the update arrived with better built in support for Claude-3
CUSTOM_MODELS="+claude-3-haiku-20240307"
ANTHROPIC_API_KEY="{your-api-key}"
ANTHROPIC_API_VERSION="2023-06-01"
(currently the latest version)ANTHROPIC_URL="https://api.anthropic.com/v1/messages"
from chatgpt-next-web.
Weird. It didn't work for me till I added the ANTHROPIC_API_VERSION
.
I already had the ANTHROPIC_API_KEY
, ANTHROPIC_URL
and CUSTOM_MODELS
, but without ANTHROPIC_API_VERSION
it would fallback to GPT-3
from chatgpt-next-web.
This bug has beed fixed in v2.12.2
from chatgpt-next-web.
Related Issues (20)
- [Bug] 配置了访问密码, 在vercel修改密码之后, 原来验证过密码的还是可以正常访问 HOT 1
- [Bug] netlify现在无法发布最新版,只要设置变量就报错 HOT 1
- [Bug] 无法使用v1beta接口 HOT 5
- [Bug] 同步或导入低版本的备份后,导致可选模型列表被修改 HOT 1
- [Feature Request]: support for gemini-1.5-flash-latest HOT 7
- [Feature Request]: openai官网已支持免登录使用,这个项目能否不用key也能使用 HOT 5
- [Bug] 使用gpt-4o模型无法调用图片上传 HOT 4
- x HOT 2
- 1 HOT 3
- 本地ollama无法聊天 HOT 2
- 无法调用.env文件的OPENAI_API_KEY HOT 2
- [Bug] 本地ollama无法聊天 HOT 5
- [错误].env文件已经配置OPENAI_API_KEY字段 HOT 8
- [Bug] gpt4o模型没有上传图片按钮 HOT 3
- [Bug] HOT 4
- [Bug] 使用gpt-4o模型时会出现错误 HOT 5
- [Feature Request]: 会考虑出一个ios app 吗? HOT 3
- [Bug] Setting `max_tokens` didn't work when using OpenAI models. HOT 1
- [Bug] signal is aborted without reason HOT 2
- [Bug] Icon is too large in macbook HOT 1
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 chatgpt-next-web.