Changes to allow user to enter host GPU for component to get potential nims to use; README changes#10
Open
jtcasablanca wants to merge 42 commits intoNVIDIA:mainfrom
Open
Changes to allow user to enter host GPU for component to get potential nims to use; README changes#10jtcasablanca wants to merge 42 commits intoNVIDIA:mainfrom
jtcasablanca wants to merge 42 commits intoNVIDIA:mainfrom
Conversation
- Created app 'Visual Studio Code' - Updated Requested GPUs to '0' - Modified files: .project/configpacks, code/chatui/utils/database.py, code/output.log
- Modified files: code/chatui/pages/converse.py, code/chatui/utils/database.py, variables.env Added LLAMA and MISTRAL constants at top of file to centralize model identifiers - Updated model_list to use the new constants - Kept match/case pattern for maintainable model selection logic - Ensures consistent model identifier usage with API_PREFIX throughout code This change improves maintainability by centralizing model identifiers and makes it easier to add new models in the future.
…ented. - Modified files: code/chatui/pages/converse.py, code/output.log, variables.env - Fixed API_PREFIX to properly handle trailing slashes with rstrip() - Updated pattern matching to use guard clauses for model comparison - Changed from direct variable matching to str() type with equality guards APPLICATION SUCCESSFULLY STARTED.
- Modified files: code/chatui/pages/converse.py, code/chatui/utils/database.py, code/output.log, variables.env - Fix incorrect Llama model endpoint string (llama3-70b-instruct -> llama-3.1-70b-instruct) - Simplify API prefix logic by using INTERNAL_API environment variable - Move model identifiers to top-level constants for better maintainability - Update model string construction to handle internal API paths more cleanly This change fixes endpoint resolution issues and improves code organization around API path handling.
- Modified files: code/output.log
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md Update README structure and content - Reorder workflow description for logical flow - Adjust agentic workflow explanation for clarity - Add details about prompt configuration and pipeline routing - Update router LLM evaluation process description
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
- Updated storage in layout 'data/' - Deleted layout 'data/scratch/' - Modified files: .gitignore, code/chatui/utils/database.py, code/output.log
still changes needed to deep dive.
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md, code/output.log
- Modified files: README.md
- Added files: code/nim_disk_size.json, code/nim_gpu_support_matrix.json
- Added files: code/chatui/utils/gpu_compatibility.py - Modified files: .gitignore, code/chatui/pages/converse.py, code/chatui/utils/graph.py, code/chatui/utils/nim.py - Add GPU type and count selection UI for all NIM components - Implement GPU compatibility checking and validation - Add dynamic model selection based on GPU configuration - Update state management to include GPU settings - Add error handling for GPU configuration issues - Improve API key handling in NIM client The changes allow users to: - Select GPU type and count for each NIM endpoint - See compatible models based on GPU configuration - Get warnings for incompatible configurations - Validate GPU settings before making API calls Technical changes: - Add gpu_compatibility module for GPU support matrix - Update CustomChatOpenAI to handle GPU configuration - Add GPU fields to GraphState - Add GPU validation in NIM client - Implement dynamic UI updates based on GPU selection
…nted yet. - Modified files: README.md, code/output.log
- Modified files: README.md
- Modified files: README.md - Clarify that each pipeline component can be independently configured for self-hosting - List all available components that support self-hosting (Router, Generator, Retrieval, etc.) - Emphasize ability to mix between hosted and self-hosted components - Restructure setup steps to better explain component-specific configuration - Remove outdated GPU sizing guide
- Modified files: README.md
- Modified files: README.md
- Modified files: README.md
… buttons) - Modified files: README.md, code/chatui/pages/converse.py, code/output.log
- Modified files: code/chatui/pages/converse.py
- Modified files: code/chatui/pages/converse.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.