Rodrigo Rodriguez (Pragmatismo)
1f9100d3a5
- Simplified auth module by removing unused imports and code - Cleaned up shared models by removing unused structs (Organization, User, Bot, etc.) - Updated add-req.sh to comment out unused directories - Modified LLM fallback strategy in README with additional notes about model behaviors The changes focus on removing unused code and improving documentation while maintaining existing functionality. The auth module was significantly reduced by removing redundant code, and similar cleanup was applied to shared models. The build script was adjusted to reflect currently used directories.
826 B
826 B
| 1 | name | value |
|---|---|---|
| 2 | server_host | 0.0.0.0 |
| 3 | server_port | 8080 |
| 4 | sites_root | /tmp |
| 5 | llm-key | none |
| 6 | llm-url | http://localhost:8081 |
| 7 | llm-model | ../../../../data/llm/DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf |
| 8 | mcp-server | false |
| 9 | embedding-url | http://localhost:8082 |
| 10 | embedding-model | ../../../../data/llm/bge-small-en-v1.5-f32.gguf |
| 11 | llm-server | false |
| 12 | llm-server-path | botserver-stack/bin/llm/build/bin |
| 13 | llm-server-host | 0.0.0.0 |
| 14 | llm-server-port | 8081 |
| 15 | llm-server-gpu-layers | 0 |
| 16 | llm-server-n-moe | 0 |
| 17 | llm-server-ctx-size | 2048 |
| 18 | llm-server-n-predict | 512 |
| 19 | llm-server-parallel | 6 |
| 20 | llm-server-cont-batching | true |
| 21 | llm-server-mlock | false |
| 22 | llm-server-no-mmap | false |
| 23 | email-from | from@domain.com |
| 24 | email-server | mail.domain.com |
| 25 | email-port | 587 |
| 26 | email-user | user@domain.com |
| 27 | email-pass | |
| 28 | custom-server | localhost |
| 29 | custom-port | 5432 |
| 30 | custom-database | mycustomdb |
| 31 | custom-username | |
| 32 | custom-password |