Comments (8)
version ChatWithRTX_Offline_2_11_mistral_Llama
from chatrtx.
same error on 3080 Ti Windows 11
from chatrtx.
@if-ai , can you confirm if there is space in your windows user name? Asking since we identified issues with path with spaces.
C:\Users\<USER>\AppData\Local\NVIDIA\MiniConda\Scripts
from chatrtx.
@BLSharda In my case, my username does NOT have a white space
but has a hyphen -
instead.
from chatrtx.
Same on RTX 4070 Ti, Windows 11 and NO spaces or dashes in
C:\Users\<USER>\AppData\Local\NVIDIA\MiniConda\Scripts
from chatrtx.
Same on 4070, no space on username, path is C:\Users\antho\AppData\Local\NVIDIA\MiniConda\Scripts
with 551.52 drivers on Windows 11 23H2.
from chatrtx.
@if-ai , can you confirm if there is space in your windows user name? Asking since we identified issues with path with spaces.
C:\Users\<USER>\AppData\Local\NVIDIA\MiniConda\Scripts
there is no space or symbols in my username just normal camelcase latin alphabet letters I activate the env in conda C:\Windows\system32>conda activate C:\Users\NvdiaUser\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag
installed the reqs
(C:\Users\NvdiaUser\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag) C:\Windows\system32>pip install -r "C:\Users\NvdiaUser\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\requirements.txt"
got some issue with grpcio WARNING: No metadata found in c:\users\nvdiauser\appdata\roaming\python\python310\site-packages
went to the folder manually removed the package and inastalled it again with pip install --force-reinstall --no-deps grpcio==1.48.1
confirmed it installed without error Started ChatWithRTX got again the message there is not LLama_Index module which is a called from \ChatWithRTX\RAG\trt-llm-rag-windows-main\app.py
or ChatWithRTX\RAG\trt-llm-rag-windows-main\trt_llama_api.py
try installing just llama index pip install llama-index==0.9.27
it again same message notice site package on the env was missing some folders like bridge inside the llama_index meaning probably got corrupted because I had the ChatwithRTX open to read the log error message Not sure if true but is my wild guess so I deleted the corrupted folder llama_index and and dist info manually and pip installed it again By the way I also added C:\Users\NvidiaUser\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\Lib\site-packages\llama_index
and C:\Users\NvidiaUser\AppData\Local\NVIDIA\MiniConda\Lib\site-packages\llama_index
to my global and user environment variables on windows and then did a final pip install llama-index==0.9.27
and bang it works now https://i.imgur.com/RZ3zsc8.png
from chatrtx.
I think I will close this since I found the solution posted above. I Tested the embedings are working too.
from chatrtx.
Related Issues (20)
- Improvement suggestions HOT 1
- [BUG] "Invalid session." casued by "key, value = cookie.split('=')" HOT 1
- Unable to build from source due to missing dependency HOT 6
- [BUG] Installing CLIP model breaks ChatRTX HOT 1
- How to add chatRTX support for edge model minicpm HOT 2
- Remote/shared link/ shared session do not allow for reference files opening HOT 6
- Build the Mistral TRT-LLM int4 AWQ Engine not working HOT 1
- No interface is running right now HOT 2
- AssertionError: Config has to be initialized with question_encoder and generator config
- Suggestion: print tokens/s and other stats like lm studio
- Suggestion: add phi3 mini and or phi3 medium..
- Event queue error when sharing ChatRTX on LAN
- Llama 3 HOT 1
- Workaround for ChatRTX on Linux HOT 5
- ChatRTX 4.0 - Sharing Capabilities? HOT 2
- Instalation failed HOT 2
- I was following your api instructions but then i got this error HOT 1
- Can ChatRTX be used for VS code extensions?
- infinite loading screen. HOT 12
- Reopen issue #90
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 chatrtx.