Rodrigo Rodriguez (Pragmatismo)
3befc141e5
- Add token-aware text truncation utility in core/shared/utils.rs - Fix embedding generators to use 600 token limit (safe under 768) - Fix LLM context limit detection for local models (768 vs 4096) - Prevent 'exceed context size' errors for both embeddings and chat
1 line
38 B
Bash
Executable file
1 line
38 B
Bash
Executable file
rm -rf botserver-stack/ ./work/ .env
|