Commit Graph

19 Commits

Author SHA1 Message Date
based 34bca69950 system prompt support for gemini 1.5 2024-04-11 16:38:20 +10:00
Cohee 30c52b5b27 Move prompt-converters.js 1 level up 2024-03-20 01:18:51 +02:00
Cohee bd223486de Include additional headers for all supported Text Completion types. 2024-03-14 00:48:08 +02:00
based 04bb882e90 implement messages api and selector for nuclaude models 2024-03-05 04:40:19 +10:00
Cohee 10d78f9a25 Aphrodite tokenizer 2024-02-02 01:09:03 +02:00
khanon 60044c18a4 Implement Token Probabilities UI using logprobs 2024-01-25 18:34:46 -06:00
Cohee edd737e8bd #371 Add llama.cpp inference server support 2023-12-18 22:38:28 +02:00
based 698850b514 Merge remote-tracking branch 'fork/staging' into gemini
# Conflicts:
#	server.js
#	src/endpoints/prompt-converters.js
#	src/endpoints/tokenizers.js
2023-12-15 01:35:17 +10:00
Cohee 2a5340232d Move prompt converters to a separate module. Camelcase local variables and add missing JSDocs. 2023-12-14 16:00:17 +02:00
Cohee 348253fd98 Fix import path 2023-12-14 15:36:44 +02:00
based 3e82a7d439 tokenizer changes and fixes. + a toggle 2023-12-14 16:31:08 +10:00
based e26159c00d refactor and rework palm request to work with the 'content' format and added an endpoint for googles tokenizer 2023-12-14 15:49:50 +10:00
valadaptive dba66e756a Move chat completions API endpoints to module 2023-12-13 18:53:22 -05:00
Cohee cebd6e9e0f Add API token ids from KoboldCpp 2023-12-14 01:28:18 +02:00
valadaptive 30502ac949 Split up Kobold and textgenerationwebui endpoints
The endpoint was one big if/else statement that did two entirely
different things depending on the value of main_api. It makes more sense
for those to be two separate endpoints.
2023-12-09 20:26:24 -05:00
valadaptive 04e92efe29 Move API tokenization endpoint into /tokenizers
Requires extracting some more functions out of server.js.
2023-12-09 19:35:49 -05:00
valadaptive 4e073250a2 Use Express router for tokenizers endpoint 2023-12-04 13:00:13 -05:00
valadaptive 57bc95133e Rename tokenizer routes
They're all under tokenizers/ now, and there are "count", "encode", and
"decode" endpoints. This forms a clearer hierarchy.
2023-12-04 10:17:43 -05:00
valadaptive c073a89e2c Move endpoints into their own folder 2023-12-04 10:17:43 -05:00