Timothy Carambat
e1ad9080de
Automatic mode is now default
2026-03-31 13:11:46 -07:00
Sean Hatfield
31a8ead823
Fix multimodal chats via openai compat api ( #4135 )
...
* fix multimodal chats via openai compat api
* lint
* add tests for multi-modal content in openai compat endpoint
* refactor to normalize how openai attachments are handled
* uncheck file
* rewrite tests, autodetect mime from dataurl, and spread attachments from prompt
* lint
* revert and fix tests
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
2025-07-22 09:57:32 -07:00
Sean Hatfield
f3ea21bcd1
Prompt variables ( #3359 )
...
* wip prompt variables
* refactor backend + add popup suggestions menu to frontend
* use processString to replace all variables in system prompts
* update translations
* fix translations
* wip highlight variables
* revert accidental name change
* rename everything, remove translations
* Update prompt var UI and backend logic
* Update form handler
linting
* linting
* normalize all translation files for prompt variables
* prompt vars dev image
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2025-03-25 12:44:19 -07:00
timothycarambat
a2264f46ff
add index to response object for marshalling
...
resolves #2956
2025-01-14 14:43:00 -08:00
Timothy Carambat
ad01df8790
Reranker option for RAG ( #2929 )
...
* Reranker WIP
* add cacheing and singleton loading
* Add field to workspaces for vectorSearchMode
Add UI for lancedb to change mode
update all search endpoints to pass in reranker prop if provider can use it
* update hint text
* When reranking, swap score to rerank score
* update optchain
2025-01-02 14:27:52 -08:00
timothycarambat
f417ffd5e0
resolves #2926
...
floor ms value
2025-01-01 15:54:44 -08:00
Timothy Carambat
ef71b95cf9
Return timestamps in OpenAI compat endpoints in proper format ( #2921 )
2024-12-31 09:35:52 -08:00
Timothy Carambat
dd7c4675d3
LLM performance metric tracking ( #2825 )
...
* WIP performance metric tracking
* fix: patch UI trying to .toFixed() null metric
Anthropic tracking migraiton
cleanup logs
* Apipie implmentation, not tested
* Cleanup Anthropic notes, Add support for AzureOpenAI tracking
* bedrock token metric tracking
* Cohere support
* feat: improve default stream handler to track for provider who are actually OpenAI compliant in usage reporting
add deepseek support
* feat: Add FireworksAI tracking reporting
fix: improve handler when usage:null is reported (why?)
* Add token reporting for GenericOpenAI
* token reporting for koboldcpp + lmstudio
* lint
* support Groq token tracking
* HF token tracking
* token tracking for togetherai
* LiteLLM token tracking
* linting + Mitral token tracking support
* XAI token metric reporting
* native provider runner
* LocalAI token tracking
* Novita token tracking
* OpenRouter token tracking
* Apipie stream metrics
* textwebgenui token tracking
* perplexity token reporting
* ollama token reporting
* lint
* put back comment
* Rip out LC ollama wrapper and use official library
* patch images with new ollama lib
* improve ollama offline message
* fix image handling in ollama llm provider
* lint
* NVIDIA NIM token tracking
* update openai compatbility responses
* UI/UX show/hide metrics on click for user preference
* update bedrock client
---------
Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
2024-12-16 14:31:17 -08:00
Sean Hatfield
910eb36cfe
[FIX] OpenAI compatible endpoints query mode developer API bug fix ( #1789 )
...
fix query mode always responding with refusal message on develop api openai compatible endpoints
2024-06-28 14:23:16 -07:00
Timothy Carambat
88a0335fd2
Add OpenAI compatible API support ( #1757 )
2024-06-24 18:28:21 -07:00
