Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Spaces:

khubchand
/

ai-assistant-engine

Sleeping

App Files Files Community

Fetching metadata from the HF Docker repository...

ai-assistant-engine

154 kB

Ctrl+K

Ctrl+K

1 contributor

History: 23 commits

khubchand's picture

remove wiki

1b0a90a 14 days ago

database
Initial clean release 17 days ago
documents
add tools support 14 days ago
embeddings
Optimize startup speed and query latency 17 days ago
llm
add tools support 14 days ago
rag
remove wiki 14 days ago
routes
add tools support 14 days ago
utils
Initial clean release 17 days ago
.dockerignore

102 Bytes
Initial clean release 17 days ago
.gitignore

132 Bytes
Initial clean release 17 days ago
Dockerfile

1.58 kB
Update system model to Gemma 3 1B Instruct and humanize responses 16 days ago
Modelfile

47 Bytes
Update system model to Gemma 3 1B Instruct and humanize responses 16 days ago
README.md

231 Bytes
add README.md with Hugging Face Space metadata 17 days ago
config.py

302 Bytes
Update system model to Gemma 3 1B Instruct and humanize responses 16 days ago
main.py

1.96 kB
Optimize Hugging Face Space: add eager model loading, reduce max tokens, fix stop tokens, limit CPU threads 17 days ago
requirements.txt

302 Bytes
feat: optimize response time by offloading translation to deep-translator and reducing ctx/retrieval k size 16 days ago