NVIDIA/ChatRTX

Issues

• Instalation failed

  #86 opened 4 months ago by Ericlebose
  4

• Update to Llama 3 8B model

  #55 opened 8 months ago by EwoutH
  4

• ChatRTX 4.0 - Sharing Capabilities?

  #85 opened 5 months ago by ttrandynamic
  3

• Invalid reference to app_config.json, file not being loaded.

  #95 opened 2 months ago by bormanst
  1

• "https://catalog.canary.ngc.nvidia.com/" is not accessible?

  #94 opened 3 months ago by Doormanstryd
  0

• infinite loading screen.

  #90 opened 4 months ago by 111100001
  21

• Data source may be empty or unsupported？

  #93 opened 3 months ago by leshan
  0

• Reopen issue #90

  #91 opened 4 months ago by NextdoorPsycho
  2

• feature request - home assistant, replace siri

  #66 opened 7 months ago by warlordattack
  3

• tokenization_chatglm.py

  #92 opened 4 months ago by GitHub-lql
  0

• I was following your api instructions but then i got this error

  #87 opened 5 months ago by PolyPenguinDev
  1

• Llama 3

  #83 opened 6 months ago by MAKSIM7
  1

• Can ChatRTX be used for VS code extensions?

  #89 opened 4 months ago by KandBM
  0

• Workaround for ChatRTX on Linux

  #84 opened 5 months ago by Hyphaed
  5

• Unable to build from source due to missing dependency

  #72 opened 6 months ago by metiscus
  6

• PDF Error?

  #67 opened 7 months ago by electro-logic
  3

• Event queue error when sharing ChatRTX on LAN

  #82 opened 6 months ago by eliasxlevy
  0

• Suggestion: add phi3 mini and or phi3 medium..

  #81 opened 6 months ago by oscarbg
  0

• Suggestion: print tokens/s and other stats like lm studio

  #80 opened 6 months ago by oscarbg
  0

• How to add chatRTX support for edge model minicpm

  #75 opened 6 months ago by LDLINGLINGLING
  2

• AssertionError: Config has to be initialized with question_encoder and generator config

  #79 opened 6 months ago by itsnotjoe
  0

• No interface is running right now

  #78 opened 6 months ago by tpc2233
  2

• Remote/shared link/ shared session do not allow for reference files opening

  #76 opened 6 months ago by ttrandynamic
  6

• Build the Mistral TRT-LLM int4 AWQ Engine not working

  #77 opened 6 months ago by kzpromo
  1

• [BUG] "Invalid session." casued by "key, value = cookie.split('=')"

  #71 opened 7 months ago by daxiongshu
  1

• [BUG] Installing CLIP model breaks ChatRTX

  #74 opened 6 months ago by sloomingbla
  1

• code

  #65 opened 7 months ago by Tyronedill99
  0

• Improvement suggestions

  #68 opened 7 months ago by electro-logic
  1

• already passed the verify_install.py but cant pass the app.py "ImportError: DLL load failed while importing tensorrt: 找不到指定的模块。"

  #63 opened 7 months ago by beeinwind
  2

• Simplified version?

  #64 opened 7 months ago by Crestina2001
  0

• Importing from langchain will no longer be supported

  #61 opened 7 months ago by rafalohaki
  1

• ⁉️ Benefit of using ChatRTX instead of LMStudio or Ollama and other similar tools❓❔

  #59 opened 7 months ago by computersrmyfriends
  2

• feat: can it read repository

  #39 opened 7 months ago by hrithiqball
  1

• Large amount of files get stuck before loading

  #41 opened 10 months ago by jeffersoncgo
  1

• Connection error

  #47 opened 7 months ago by okbckim
  4

• Not able to generate engine on RTX4060 Laptop 8GB 100% CPU being utilised

  #51 opened 9 months ago by Vishwa0703
  2

• How to switch language?!

  #53 opened 7 months ago by andresg97
  3

• Dtype value read by app.py empty. Gets error message : Unsupported dtype

  #56 opened 8 months ago by RoslinAdama
  2

• [Question] Would it be possible for the system to use spreadsheets as Dataset as well as .txt, .pdf, .doc

  #60 opened 7 months ago by LCRMAN
  1

• 'trtllm-build' is not recognized

  #58 opened 7 months ago by ethorpe
  1

• how do I define other large language models in the configuration?

  #57 opened 8 months ago by Bobtrumpg
  0

• How to implement chat history memory and system prompt?

  #40 opened 10 months ago by neohary
  1

• ChatWithRTX Installer is corrupt.

  #42 opened 8 months ago by fcodes0
  3

• [TensorRT-LLM][ERROR] CUDA runtime error in cudaDeviceGetDefaultMemPool

  #49 opened 8 months ago by jordiyeh
  2

• not able to debug this even with gdb

  #50 opened 9 months ago by nihalkumar2k21
  1

• default response language

  #52 opened 8 months ago by susl16c
  2

• What version of Cuda is needed?

  #54 opened 8 months ago by leandroMsouza
  5

• build TRT engine fail

  #43 opened 10 months ago by petersha0630
  6

• garbage output ?

  #48 opened 10 months ago by ZJLi2013
  1

• pycryotodome

  #45 opened 10 months ago by sarsharoid
  1