Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Spaces:
dinely523
/
aidiot-proj
Running

App Files Files Community
Fetching metadata from the HF Docker repository...
aidiot-proj
122 kB
Ctrl+K
Ctrl+K
  • 3 contributors
History: 57 commits
dinely523
Revert: Back to RAG architecture for better CPU performance (keeping LiquidAI 350M)
fd657e1 3 months ago
  • company
    initial commit 6 months ago
  • .dockerignore
    81 Bytes
    initial commit 6 months ago
  • .gitattributes
    0 Bytes
    initial commit 6 months ago
  • .gitignore
    114 Bytes
    initial commit 6 months ago
  • CHANGELOG_MODEL.md
    1.4 kB
    Refactor: Switch from RAG to Full Context KV Caching for 100% accuracy and lower RAM usage 3 months ago
  • Dockerfile
    1.44 kB
    Redesign RAG with LlamaIndex: Add persistence, metadata indexing, and hierarchical retrieval 3 months ago
  • README.md
    2.07 kB
    fixing docker file 6 months ago
  • log.txt
    84.3 kB
    fixing docker file 6 months ago
  • main.py
    7.64 kB
    Revert: Back to RAG architecture for better CPU performance (keeping LiquidAI 350M) 3 months ago
  • model.py
    2.26 kB
    Revert: Back to RAG architecture for better CPU performance (keeping LiquidAI 350M) 3 months ago
  • rag.py
    1.99 kB
    Revert: Back to RAG architecture for better CPU performance (keeping LiquidAI 350M) 3 months ago
  • requirements.txt
    167 Bytes
    Revert: Back to RAG architecture for better CPU performance (keeping LiquidAI 350M) 3 months ago