fix more

docs/source/concepts/includes/arch_config.yaml

@@ -13,7 +13,6 @@ llm_providers:
     access_key: $OPENAI_API_KEY
     model: gpt-4o
     default: true
-    stream: true
 
 # default system prompt used by all prompt targets
 system_prompt: You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.

docs/source/guides/includes/arch_config.yaml

@@ -13,7 +13,6 @@ llm_providers:
     access_key: $OPENAI_API_KEY
     model: gpt-4o
     default: true
-    stream: true
 
 # default system prompt used by all prompt targets
 system_prompt: You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.

docs/source/resources/includes/arch_config_full_reference.yaml

@@ -1,16 +1,14 @@
 version: v0.1
 
-listener:
-  address: 0.0.0.0 # or 127.0.0.1
-  port: 10000
-  # Defines how Arch should parse the content from application/json or text/pain Content-type in the http request
-  message_format: huggingface
-  common_tls_context: # If you configure port 443, you'll need to update the listener with your TLS certificates
-    tls_certificates:
-      - certificate_chain:
-          filename: /etc/certs/cert.pem
-        private_key:
-          filename: /etc/certs/key.pem
+listeners:
+  prompt_gateway:
+    address: 0.0.0.0
+    port: 10000
+    message_format: openai
+    timeout: 5s
+  llm_gateway:
+    address: 0.0.0.0
+    port: 12000
 
 # Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
 endpoints:
@@ -35,7 +33,6 @@ llm_providers:
     access_key: $OPENAI_API_KEY
     model: gpt-4o
     default: true
-    stream: true
     rate_limits:
       selector: #optional headers, to add rate limiting based on http headers like JWT tokens or API keys
         http_header: