Server: format error to json (#5961)

* server: format error to json

* server: do not crash on grammar error

* fix api key test case

* revert limit max n_predict

* small fix

* correct coding style

* update completion.js

* launch_slot_with_task

* update docs

* update_slots

* update webui

* update readme

1 files changed, 10 insertions, 10 deletions

diff --git a/examples/server/public/completion.js b/examples/server/public/completion.js
index ab38a7b4..835ce6e6 100644
--- a/examples/server/public/completion.js
+++ b/examples/server/public/completion.js
@@ -96,18 +96,18 @@ export async function* llama(prompt, params = {}, config = {}) {
             }
           }
           if (result.error) {
-            result.error = JSON.parse(result.error);
-            if (result.error.content.includes('slot unavailable')) {
-              // Throw an error to be caught by upstream callers
-              throw new Error('slot unavailable');
-            } else {
-              console.error(`llama.cpp error: ${result.error.content}`);
+            try {
+              result.error = JSON.parse(result.error);
+              if (result.error.message.includes('slot unavailable')) {
+                // Throw an error to be caught by upstream callers
+                throw new Error('slot unavailable');
+              } else {
+                console.error(`llama.cpp error [${result.error.code} - ${result.error.type}]: ${result.error.message}`);
+              }
+            } catch(e) {
+              console.error(`llama.cpp error ${result.error}`)
             }
           }
-          if (result.error) {
-            result.error = JSON.parse(result.error);
-            console.error(`llama.cpp error: ${result.error.content}`);
-          }
         }
       }
     }