merlyn/server/utils/helpers
jonathanortega2023 7a0c149d2e
fix: Use eval_duration for output TPS calculations in Ollama LLM provider (#4568)
* fix: Use eval_duration for output TPS calculations and add as a metric field

* refactor usage of eval_duration from ollama metrics

* move eval_duration to usage

* overwrite duration in ollama provider wip measureAsyncFunction optional param

* allow for overloaded duration in measureAsyncFunction

* simplify flow for duration tracking

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2025-11-20 13:02:47 -08:00
..
admin patch admin pwd update 2024-02-06 14:39:56 -08:00
chat fix: Use eval_duration for output TPS calculations in Ollama LLM provider (#4568) 2025-11-20 13:02:47 -08:00
camelcase.js Add support for Weaviate VectorDB (#181) 2023-08-08 18:02:30 -07:00
customModels.js Reimplement Cohere models for basic chat (#4489) 2025-10-03 18:28:20 -07:00
index.js Implement full chat and @agent chat user indentificiation for OpenRouter (#4668) 2025-11-20 12:38:43 -08:00
portAvailabilityChecker.js [FEAT] Check port access in docker before showing a default error (#961) 2024-04-02 10:34:50 -07:00
search.js Add ability to search workspace and threads (#4120) 2025-07-10 16:42:10 -07:00
tiktoken.js Add tokenizer improvments via Singleton class and estimation (#3072) 2025-01-30 17:55:03 -08:00
updateENV.js Model context limit auto-detection for LM Studio and Ollama LLM Providers (#4468) 2025-10-02 11:54:19 -07:00