fix: prevent truncated Ollama answers
This commit is contained in:
@@ -201,6 +201,7 @@ OLLAMA_BASE_URL=http://host.docker.internal:11434
|
||||
OLLAMA_DEFAULT_MODEL=qwen3.5:9b
|
||||
OLLAMA_TIMEOUT_SECONDS=120
|
||||
OLLAMA_MAX_OUTPUT_TOKENS=700
|
||||
OLLAMA_CONTEXT_TOKENS=16384
|
||||
```
|
||||
|
||||
The model dropdown comes from Ollama `/api/tags`, so changing the installed
|
||||
|
||||
Reference in New Issue
Block a user