|
|
@ -7,7 +7,7 @@ spring:
|
|
|
|
chat:
|
|
|
|
chat:
|
|
|
|
enabled: true
|
|
|
|
enabled: true
|
|
|
|
options:
|
|
|
|
options:
|
|
|
|
model: llama3-chinese:8b
|
|
|
|
model: qwen2:7b
|
|
|
|
# 控制模型在请求后加载到内存中的时间(稍微长一点的时间,避免重复加载浪费性能,加快处理速度)
|
|
|
|
# 控制模型在请求后加载到内存中的时间(稍微长一点的时间,避免重复加载浪费性能,加快处理速度)
|
|
|
|
keep_alive: 30m
|
|
|
|
keep_alive: 30m
|
|
|
|
# 例如0.3
|
|
|
|
# 例如0.3
|
|
|
@ -69,4 +69,6 @@ langChain-chat:
|
|
|
|
url: http://113.128.242.110:7861
|
|
|
|
url: http://113.128.242.110:7861
|
|
|
|
|
|
|
|
|
|
|
|
ocr:
|
|
|
|
ocr:
|
|
|
|
url: http://192.168.10.137:8866/
|
|
|
|
url: http://192.168.10.138:8866/
|
|
|
|
|
|
|
|
pool:
|
|
|
|
|
|
|
|
max-size: 20
|