feat: increase read timeout of OpenAI Compatible API, Ollama, Nvidia LLM (#3538)

api/core/model_runtime/model_providers/nvidia/llm/llm.py

@@ -131,7 +131,7 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
                 endpoint_url,
                 headers=headers,
                 json=data,
-                timeout=(10, 60)
+                timeout=(10, 300)
             )
 
             if response.status_code != 200:
@@ -232,7 +232,7 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
             endpoint_url,
             headers=headers,
             json=data,
-            timeout=(10, 60),
+            timeout=(10, 300),
             stream=stream
         )
 

api/core/model_runtime/model_providers/ollama/llm/llm.py

@@ -201,7 +201,7 @@ class OllamaLargeLanguageModel(LargeLanguageModel):
             endpoint_url,
             headers=headers,
             json=data,
-            timeout=(10, 60),
+            timeout=(10, 300),
             stream=stream
         )
 

api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py

@@ -138,7 +138,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
                 endpoint_url,
                 headers=headers,
                 json=data,
-                timeout=(10, 60)
+                timeout=(10, 300)
             )
 
             if response.status_code != 200:
@@ -334,7 +334,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
             endpoint_url,
             headers=headers,
             json=data,
-            timeout=(10, 60),
+            timeout=(10, 300),
             stream=stream
         )