fix: point VLLM_BASE_URL to Ollama (10.1.1.12:2701) and update model name
vLLM service on 192.168.42.254:8000 was down causing extraction failures. Also updated ai_agents table to use ollama provider directly.
This commit is contained in:
@@ -181,8 +181,8 @@ config:
|
|||||||
OLLAMA_RETRY_BASE_DELAY: "1.0"
|
OLLAMA_RETRY_BASE_DELAY: "1.0"
|
||||||
OLLAMA_RETRY_MAX_DELAY: "10.0"
|
OLLAMA_RETRY_MAX_DELAY: "10.0"
|
||||||
OLLAMA_RETRY_BACKOFF_MULTIPLIER: "2.0"
|
OLLAMA_RETRY_BACKOFF_MULTIPLIER: "2.0"
|
||||||
VLLM_BASE_URL: "http://192.168.42.254:8000"
|
VLLM_BASE_URL: "http://10.1.1.12:2701"
|
||||||
VLLM_MODEL: "AxionML/Qwen3.5-9B-NVFP4"
|
VLLM_MODEL: "qwen3.5:9b-fast"
|
||||||
VLLM_TIMEOUT: "120"
|
VLLM_TIMEOUT: "120"
|
||||||
VLLM_MAX_RETRIES: "2"
|
VLLM_MAX_RETRIES: "2"
|
||||||
VLLM_TEMPERATURE: "0.7"
|
VLLM_TEMPERATURE: "0.7"
|
||||||
|
|||||||
Reference in New Issue
Block a user