Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-17 17:00:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

📸 feat: Gemini vision, Improved Logs and Multi-modal Handling (#1368)

Browse source 
* feat: add GOOGLE_MODELS env var

* feat: add gemini vision support

* refactor(GoogleClient): adjust clientOptions handling depending on model

* fix(logger): fix redact logic and redact errors only

* fix(GoogleClient): do not allow non-multiModal messages when gemini-pro-vision is selected

* refactor(OpenAIClient): use `isVisionModel` client property to avoid calling validateVisionModel multiple times

* refactor: better debug logging by correctly traversing, redacting sensitive info, and logging condensed versions of long values

* refactor(GoogleClient): allow response errors to be thrown/caught above client handling so user receives meaningful error message
debug orderedMessages, parentMessageId, and buildMessages result

* refactor(AskController): use model from client.modelOptions.model when saving intermediate messages, which requires for the progress callback to be initialized after the client is initialized

* feat(useSSE): revert to previous model if the model was auto-switched by backend due to message attachments

* docs: update with google updates, notes about Gemini Pro Vision

* fix: redis should not be initialized without USE_REDIS and increase max listeners to 20
This commit is contained in:
Danny Avila 2023-12-16 20:45:27 -05:00 • committed by GitHub
parent 676f133545
commit 0c326797dd
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
21 changed files with 356 additions and 210 deletions
Download patch file Download diff file Expand all files Collapse all files

3
api/app/clients/BaseClient.js
View file

@ -357,11 +357,11 @@ class BaseClient {
const promptTokens = this.maxContextTokens - remainingContextTokens;
logger.debug('[BaseClient] Payload size:', payload.length);
logger.debug('[BaseClient] tokenCountMap:', tokenCountMap);
logger.debug('[BaseClient]', {
promptTokens,
remainingContextTokens,
payloadSize: payload.length,
maxContextTokens: this.maxContextTokens,
});
@ -414,7 +414,6 @@ class BaseClient {
logger.debug('[BaseClient] tokenCountMap', tokenCountMap);
if (tokenCountMap[userMessage.messageId]) {
userMessage.tokenCount = tokenCountMap[userMessage.messageId];
logger.debug('[BaseClient] userMessage.tokenCount', userMessage.tokenCount);
logger.debug('[BaseClient] userMessage', userMessage);
}