Fix grounded assistant cross-domain responses
This commit is contained in:
+4
-2
@@ -1114,7 +1114,7 @@ OLLAMA_ENABLED=true
|
||||
OLLAMA_BASE_URL=http://host.docker.internal:11434
|
||||
OLLAMA_DEFAULT_MODEL=qwen3.5:9b
|
||||
OLLAMA_TIMEOUT_SECONDS=120
|
||||
OLLAMA_MAX_OUTPUT_TOKENS=700
|
||||
OLLAMA_MAX_OUTPUT_TOKENS=1200
|
||||
OLLAMA_CONTEXT_TOKENS=16384
|
||||
```
|
||||
|
||||
@@ -1125,7 +1125,9 @@ models with `GET /api/v1/assistant/models` and ask a grounded question through
|
||||
present in Ollama `/api/tags`. Missing water depth/bathymetry remains explicit;
|
||||
the assistant cannot turn 2D water geometry into volume. GeoIntel rejects an
|
||||
answer when Ollama reports `done_reason=length`, so a visibly truncated sentence
|
||||
is never presented as a complete result.
|
||||
is never presented as a complete result. The 1,200-token default leaves enough
|
||||
room for a compact cross-domain profile while the system prompt requires every
|
||||
explicitly requested theme and excludes unrelated themes.
|
||||
|
||||
## Agricultural-use parcel history
|
||||
|
||||
|
||||
Reference in New Issue
Block a user