Andrew McCracken
Claude
commited on
Commit
·
2a55dc3
1
Parent(s):
b7fb901
Disable RAG for faster inference
Browse files- Set USE_RAG=false to remove knowledge base overhead
- Should significantly reduce response time on CPU instance
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Dockerfile +1 -1
Dockerfile
CHANGED
|
@@ -6,7 +6,7 @@ FROM techdaskalos/cybersecchatbot:latest
|
|
| 6 |
ENV PYTHONUNBUFFERED=1
|
| 7 |
ENV MODEL_REPO=daskalos-apps/phi4-cybersec-Q4_K_M
|
| 8 |
ENV MODEL_FILENAME=phi4-mini-instruct-Q4_K_M.gguf
|
| 9 |
-
ENV USE_RAG=
|
| 10 |
ENV CACHE_ENABLED=true
|
| 11 |
|
| 12 |
# Set Hugging Face cache to /data for persistence and write permissions
|
|
|
|
| 6 |
ENV PYTHONUNBUFFERED=1
|
| 7 |
ENV MODEL_REPO=daskalos-apps/phi4-cybersec-Q4_K_M
|
| 8 |
ENV MODEL_FILENAME=phi4-mini-instruct-Q4_K_M.gguf
|
| 9 |
+
ENV USE_RAG=false
|
| 10 |
ENV CACHE_ENABLED=true
|
| 11 |
|
| 12 |
# Set Hugging Face cache to /data for persistence and write permissions
|