Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-17 08:50:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

🤖 feat: Gemini 1.5 Support (+Vertex AI) (#2383)

Browse source 
* WIP: gemini-1.5 support

* feat: extended vertex ai support

* fix: handle possibly undefined modelName

* fix: gpt-4-turbo-preview invalid vision model

* feat: specify `fileConfig.imageOutputType` and make PNG default image conversion type

* feat: better truncation for errors including base64 strings

* fix: gemini inlineData formatting

* feat: RAG augmented prompt for gemini-1.5

* feat: gemini-1.5 rates and token window

* chore: adjust tokens, update docs, update vision Models

* chore: add back `ChatGoogleVertexAI` for chat models via vertex ai

* refactor: ask/edit controllers to not use `unfinished` field for google endpoint

* chore: remove comment

* chore(ci): fix AppService test

* chore: remove comment

* refactor(GoogleSearch): use `GOOGLE_SEARCH_API_KEY` instead, issue warning for old variable

* chore: bump data-provider to 0.5.4

* chore: update docs

* fix: condition for gemini-1.5 using generative ai lib

* chore: update docs

* ci: add additional AppService test for `imageOutputType`

* refactor: optimize new config value `imageOutputType`

* chore: bump CONFIG_VERSION

* fix(assistants): avatar upload
This commit is contained in:
Danny Avila 2024-04-16 08:32:40 -04:00 • committed by GitHub
parent fce7246ac1
commit 9d854dac07
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
37 changed files with 1030 additions and 258 deletions
Download patch file Download diff file Expand all files Collapse all files

6
api/utils/tokens.js
View file

@ -65,12 +65,14 @@ const cohereModels = {
command: 4086, // -10 from max
'command-nightly': 8182, // -10 from max
'command-r': 127500, // -500 from max
'command-r-plus:': 127500, // -500 from max
'command-r-plus': 127500, // -500 from max
};
const googleModels = {
/* Max I/O is combined so we subtract the amount from max response tokens for actual total */
gemini: 32750, // -10 from max
gemini: 30720, // -2048 from max
'gemini-pro-vision': 12288, // -4096 from max
'gemini-1.5': 1048576, // -8192 from max
'text-bison-32k': 32758, // -10 from max
'chat-bison-32k': 32758, // -10 from max
'code-bison-32k': 32758, // -10 from max