rixty/SillyTavern
1
0
Fork 0
mirror of https://github.com/SillyTavern/SillyTavern.git synced 2025-06-05 21:59:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

#371 Add llama.cpp inference server support

Browse Source
This commit is contained in:
Cohee
2023-12-18 22:38:28 +02:00
parent 6e8104873e
commit edd737e8bd
9 changed files with 136 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/endpoints/tokenizers.js
View File

@ -622,6 +622,10 @@ router.post('/remote/textgenerationwebui/encode', jsonParser, async function (re
url += '/api/extra/tokencount';
args.body = JSON.stringify({ 'prompt': text });
break;
case TEXTGEN_TYPES.LLAMACPP:
url += '/tokenize';
args.body = JSON.stringify({ 'content': text });
break;
default:
url += '/v1/internal/encode';
args.body = JSON.stringify({ 'text': text });
@ -637,7 +641,7 @@ router.post('/remote/textgenerationwebui/encode', jsonParser, async function (re
}
const data = await result.json();
const count = legacyApi ? data?.results[0]?.tokens : (data?.length ?? data?.value);
const count = legacyApi ? data?.results[0]?.tokens : (data?.length ?? data?.value ?? data?.tokens?.length);
const ids = legacyApi ? [] : (data?.tokens ?? data?.ids ?? []);
return response.send({ count, ids });