Comments (13)
I have manually downloaded the model from https://huggingface.co/orel12/ggml-gpt4all-j-v1.3-groovy/tree/main
And i've put it in the server folder inside models/ folder.
When i click on Download it displays Download Complete.
It uploads the document and Ingests successfully.
This is the console log from inspect tab
{response: 'Download completed'}
ConfigSideNav.js:77 {response: 'Document upload successful'}
ConfigSideNav.js:23 {response: 'Success'}
And then this error
app-index.js:32 Warning: Each child in a list should have a unique "key" prop.
from embedai.
问题是因为它需要 cpu 上的 avx2 支持。我只是为它使用了另一个支持 avx2 的系统,它工作正常。 对于那些在 cpu 上没有 avx2 支持的人也可以参考这个线程。 nomic-ai/pygpt4all#71
The cpu of my server supports AVX2, but the same error is reported, so strange
from embedai.
Do you observe any other errors ?
Also what is the configuration of your system ? It needs 16 GB of RAM, otherwise the process might get killed
from embedai.
I found this in the console by inspecting the webpage.
I have 64gb RAM and high end processor too. I don't think hardware will be the issue.
Warning: Each child in a list should have a unique "key" prop.
Check the render method of MainContainer
. See https://reactjs.org/link/warning-keys for more information.
at eval (webpack-internal:///(app-client)/./node_modules/react-bootstrap/esm/Stack.js:15:7)
at MainContainer (webpack-internal:///(app-client)/./components/MainContainer.js:22:76)
at div
at eval (webpack-internal:///(app-client)/./node_modules/react-bootstrap/esm/Col.js:65:8)
at div
at eval (webpack-internal:///(app-client)/./node_modules/react-bootstrap/esm/Row.js:13:3)
at Home
at InnerLayoutRouter (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/layout-router.js:227:11)
at RedirectErrorBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/redirect-boundary.js:73:9)
at RedirectBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/redirect-boundary.js:81:11)
at NotFoundBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/not-found-boundary.js:59:11)
at LoadingBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/layout-router.js:332:11)
at ErrorBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/error-boundary.js:106:11)
at InnerScrollAndFocusHandler (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/layout-router.js:139:9)
at ScrollAndFocusHandler (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/layout-router.js:213:11)
at RenderFromTemplateContext (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/render-from-template-context.js:15:44)
at OuterLayoutRouter (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/layout-router.js:342:11)
at body
at html
at RedirectErrorBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/redirect-boundary.js:73:9)
at RedirectBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/redirect-boundary.js:81:11)
at NotFoundErrorBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/not-found-boundary.js:51:9)
at NotFoundBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/not-found-boundary.js:59:11)
at ReactDevOverlay (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/react-dev-overlay/internal/ReactDevOverlay.js:66:9)
at HotReload (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/react-dev-overlay/hot-reloader-client.js:276:11)
at Router (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/app-router.js:90:11)
at ErrorBoundaryHandler (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/error-boundary.js:80:9)
at ErrorBoundary (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/error-boundary.js:106:11)
at AppRouter (webpack-internal:///(app-client)/./node_modules/next/dist/client/components/app-router.js:374:13)
at ServerRoot (webpack-internal:///(app-client)/./node_modules/next/dist/client/app-index.js:154:11)
at RSCComponent
at Root (webpack-internal:///(app-client)/./node_modules/next/dist/client/app-index.js:171:11)
window.console.error @ app-index.js:32
console.error @ hydration-error-info.js:45
printWarning @ react-jsx-dev-runtime.development.js:89
error @ react-jsx-dev-runtime.development.js:63
validateExplicitKey @ react-jsx-dev-runtime.development.js:1092
validateChildKeys @ react-jsx-dev-runtime.development.js:1119
jsxWithValidation @ react-jsx-dev-runtime.development.js:1285
MainContainer @ MainContainer.js:62
renderWithHooks @ react-dom.development.js:10648
updateFunctionComponent @ react-dom.development.js:15175
beginWork$1 @ react-dom.development.js:17320
beginWork @ react-dom.development.js:25650
performUnitOfWork @ react-dom.development.js:24501
workLoopSync @ react-dom.development.js:24217
renderRootSync @ react-dom.development.js:24182
performSyncWorkOnRoot @ react-dom.development.js:23677
flushSyncWorkAcrossRoots_impl @ react-dom.development.js:9965
flushSyncWorkOnAllRoots @ react-dom.development.js:9923
processRootScheduleInMicrotask @ react-dom.development.js:10067
eval @ react-dom.development.js:10238
MainContainer.js:29 POST http://localhost:5000/get_answer 400 (BAD REQUEST)
from embedai.
@swapatel06 This can happen when the model is not downloaded. Can you download the model by clicking on "Download model" in the UI. Model size is 3.2 GB and can take some time to download. Once done, you will be able to do queries to your data
from embedai.
From the client side, it doesn't look like there is any error. Warning is not an error and can be ignored
But from the server side it is possible the model is not being run well on the system. Which OS are you using ? And can you check the errors on server terminal
from embedai.
I'm using centos 7 and there is just this is the only log on the server terminal
127.0.0.1 - - [26/May/2023 18:06:44] "OPTIONS /get_answer HTTP/1.1" 200 -
Using embedded DuckDB with persistence: data will be stored in: db/
127.0.0.1 - - [26/May/2023 18:06:44] "POST /get_answer HTTP/1.1" 400 -
from embedai.
Have added now error messages on the client side to indicate what the error was instead of a generic unable to answer message. From what I see it looks like it is unable to find the model but you can check once on your system
from embedai.
Actually i retried everything and I realized that when i start the server with the models/ folder inside server directory it gives me the error Illegal instruction(core dumped)
And the server starts up without the models/ folder and then copy/pasting the model was making it work. But due to this it generates no errors and still doesn't work.
I'll be following these threads for now which are regarding this Illegal instruction issue
zylon-ai/private-gpt#203
zylon-ai/private-gpt#326
from embedai.
Looks like an issue with model compatibility with the OS. Keeping this thread until a solution is found
from embedai.
same problem.127.0.0.1 - - "POST /get_answer HTTP/1.1" 400 -
from embedai.
The issue was because it requires avx2 support on the cpu. I just used another system for it which had avx2 support it works fine.
Also for those who don't have avx2 support on the cpu may refer to this thread.
nomic-ai/pygpt4all#71
from embedai.
@swapatel06 Thanks for sharing
from embedai.
Related Issues (20)
- error fetching answer | model not loaded. HOT 1
- 'Connection aborted.', ConnectionResetError(54, 'Connection reset by peer' HOT 2
- Is there anyone that succesfully run the code ? HOT 4
- Change ports HOT 3
- Use any small models, like LaMini, Flan-T5-783M etc.
- error fetching answer please try again HOT 4
- Missing Docker Files?
- Use CUDA
- Question: Is there a way to load a nfs or cifs fileshare to prepopulate it instead of using the flask front end? HOT 2
- Encoded responses HOT 1
- Semantic Information
- ERROR: The prompt size exceeds the context window size and cannot be processed. HOT 1
- Mount Instead of upload?
- ValidationError: 1 validation error for GPT4All n_ctx. extra fields not permitted (type=value_error.extra)
- Unhandled Runtime Error on Ingest Data
- Implementing LangChain CustomLLM Class for use with other Models
- 404 - Not Found error after running privateGPT.py HOT 2
- Run slowly...in my 16G notebook
- Bot just hangs after a few question
- Source Document 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 embedai.