Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-16 16:30:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

🚀 fix: Resolve Google Client Issues, CDN Screenshots, Update Models (#5703)

Browse source 
* 🤖 refactor: streamline model selection logic for title model in GoogleClient

* refactor: add options for empty object schemas in convertJsonSchemaToZod

* refactor: add utility function to check for empty object schemas in convertJsonSchemaToZod

* fix: Google MCP Tool errors, and remove Object Unescaping as Google fixed this

* fix: google safetySettings

* feat: add safety settings exclusion via GOOGLE_EXCLUDE_SAFETY_SETTINGS environment variable

* fix: rename environment variable for console JSON string length

* fix: disable portal for dropdown in ExportModal component

* fix: screenshot functionality to use image placeholder for remote images

* feat: add visionMode property to BaseClient and initialize in GoogleClient to fix resendFiles issue

* fix: enhance formatMessages to include image URLs in message content for Vertex AI

* fix: safety settings for titleChatCompletion

* fix: remove deprecated model assignment in GoogleClient and streamline title model retrieval

* fix: remove unused image preloading logic in ScreenshotContext

* chore: update default google models to latest models shared by vertex ai and gen ai

* refactor: enhance Google error messaging

* fix: update token values and model limits for Gemini models

* ci: fix model matching

* chore: bump version of librechat-data-provider to 0.7.699
This commit is contained in:
Danny Avila 2025-02-06 18:13:18 -05:00 • committed by GitHub
parent 33e60c379b
commit 63afb317c6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 939 additions and 720 deletions
Download patch file Download diff file Expand all files Collapse all files

13
api/utils/tokens.js
View file

@ -49,11 +49,14 @@ const cohereModels = {
const googleModels = {
/* Max I/O is combined so we subtract the amount from max response tokens for actual total */
gemini: 30720, // -2048 from max
'gemini-pro-vision': 12288, // -4096 from max
'gemini-exp': 8000,
'gemini-2.0-flash-thinking-exp': 30720, // -2048 from max
'gemini-2.0': 1048576,
'gemini-1.5': 1048576,
'gemini-pro-vision': 12288,
'gemini-exp': 2000000,
'gemini-2.0': 2000000,
'gemini-2.0-flash': 1000000,
'gemini-2.0-flash-lite': 1000000,
'gemini-1.5': 1000000,
'gemini-1.5-flash': 1000000,
'gemini-1.5-flash-8b': 1000000,
'text-bison-32k': 32758, // -10 from max
'chat-bison-32k': 32758, // -10 from max
'code-bison-32k': 32758, // -10 from max

18
api/utils/tokens.spec.js
View file

@ -154,6 +154,24 @@ describe('getModelMaxTokens', () => {
});
test('should return correct tokens for partial match - Google models', () => {
expect(getModelMaxTokens('gemini-2.0-flash-lite-preview-02-05', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-2.0-flash-lite'],
);
expect(getModelMaxTokens('gemini-2.0-flash-001', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-2.0-flash'],
);
expect(getModelMaxTokens('gemini-2.0-flash-exp', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-2.0-flash'],
);
expect(getModelMaxTokens('gemini-2.0-pro-exp-02-05', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-2.0'],
);
expect(getModelMaxTokens('gemini-1.5-flash-8b', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-1.5-flash-8b'],
);
expect(getModelMaxTokens('gemini-1.5-flash-thinking', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-1.5-flash'],
);
expect(getModelMaxTokens('gemini-1.5-pro-latest', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-1.5'],
);