tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

Server: format error to json (#5961)

Browse Source 
* 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
This commit is contained in:
Xuan Son Nguyen
2024-03-11 10:56:41 +01:00
committed by GitHub
parent 3202361c5b
commit caa106d4e0
6 changed files with 430 additions and 317 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
examples/server/public/completion.js
View File

@ -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}`);
}
}
}
}