fix: correct generator endpoint handling

docs/api-endpoints.md

@@ -90,7 +90,7 @@ models:
     provider: "ollama"
     models:
       - 'llama2:13b'
-    endpoint: "http://127.0.0.1:11434/v1/chat/completions"
+    endpoint: "http://127.0.0.1:11434"
 ```
 
 For online services using Chutes:
@@ -106,7 +106,7 @@ For online services using Chutes:
 #    provider: "chutes"
 #    models:
 #      - 'moonshotai/Kimi-K2-Instruct'
-#    endpoint: "https://llm.chutes.ai/v1/chat/completions"
+#    endpoint: "https://llm.chutes.ai/v1"
 #    token: "cpk_xxxx"
 ```
 

example/server/config/server.yaml

@@ -20,11 +20,11 @@ sync:
 
 provider:
   - name: ollama
-    endpoint: http://localhost:11434/v1/chat/completions
+    endpoint: http://localhost:11434
     models:
       - 'gpt-oss:20b'
   - name: chutes
-    endpoint: https://llm.chutes.ai/v1/chat/completions
+    endpoint: https://llm.chutes.ai/v1
     token: "cpk_xxxxxxxxxxxxxxxxxx"
     models:
       - 'moonshotai/Kimi-K2-Instruct'

server/api/askai.go

@@ -122,10 +122,14 @@ func loadConfig() (string, string, string, string, time.Duration, int) {
 	}
 	provider = strings.ToLower(provider)
 	endpoint = strings.TrimRight(endpoint, "/")
+	endpoint = strings.TrimSuffix(endpoint, "/chat/completions")
+	endpoint = strings.TrimRight(endpoint, "/")
 	switch provider {
 	case "ollama":
+		endpoint = strings.TrimSuffix(endpoint, "/v1")
+		endpoint = strings.TrimRight(endpoint, "/")
 		if endpoint == "" {
-			endpoint = "http://localhost:11434/v1/chat/completions"
+			endpoint = "http://localhost:11434"
 		}
 		if model == "" {
 			model = "llama2:13b"
@@ -133,7 +137,7 @@ func loadConfig() (string, string, string, string, time.Duration, int) {
 		return provider, token, model, endpoint, timeout, retries
 	case "chutes":
 		if endpoint == "" {
-			endpoint = "https://llm.chutes.ai/v1/chat/completions"
+			endpoint = "https://llm.chutes.ai/v1"
 		}
 		if model == "" {
 			model = "deepseek-ai/DeepSeek-R1"
@@ -141,7 +145,7 @@ func loadConfig() (string, string, string, string, time.Duration, int) {
 		return provider, token, model, endpoint, timeout, retries
 	default:
 		if endpoint == "" {
-			endpoint = "https://llm.chutes.ai/v1/chat/completions"
+			endpoint = "https://llm.chutes.ai/v1"
 		}
 		if model == "" {
 			model = "deepseek-ai/DeepSeek-R1"

server/config/server.yaml

@@ -29,7 +29,7 @@ models:
     provider: "ollama"
     models:
       - 'llama2:13b'
-    endpoint: "http://127.0.0.1:11434/v1/chat/completions"
+    endpoint: "http://127.0.0.1:11434"
     token: ""
 # For PROD
 #models:
@@ -42,7 +42,7 @@ models:
     #provider: "chutes"
     #models:
     #  - 'moonshotai/Kimi-K2-Instruct'
-    #endpoint: "https://llm.chutes.ai/v1/chat/completions"
+      #endpoint: "https://llm.chutes.ai/v1"
     #token: "cpk_xxxx"
 
 embedding: