Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-17 00:40:14 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

🔍 feat: Mistral OCR API / Upload Files as Text (#6274)

Browse source 
* refactor: move `loadAuthValues` to `~/services/Tools/credentials`

* feat: add createAxiosInstance function to configure axios with proxy support

* WIP: First pass mistral ocr

* refactor: replace getConvoFiles with getToolFiles for improved file retrieval logic

* refactor: improve document formatting in encodeAndFormat function

* refactor: remove unused resendFiles parameter from buildOptions function (this option comes from the agent config)

* fix: update getFiles call to include files with `text` property as well

* refactor: move file handling to `initializeAgentOptions`

* refactor: enhance addImageURLs method to handle OCR text and improve message formatting

* refactor: update message formatting to handle OCR text in various content types

* refactor: remove unused resendFiles property from compactAgentsSchema

* fix: add error handling for Mistral OCR document upload and logging

* refactor: integrate OCR capability into file upload options and configuration

* refactor: skip processing for text source files in delete request, as they are directly tied to database

* feat: add metadata field to ExtendedFile type and update PanelColumns and PanelTable components for localization and metadata handling

* fix: source icon styling

* wip: first pass, frontend file context agent resources

* refactor: add hover card with contextual information for File Context (OCR) in FileContext component

* feat: enhance file processing by integrating file retrieval for OCR resources in agent initialization

* feat: implement OCR config; fix: agent resource deletion for ocr files

* feat: enhance agent initialization by adding OCR capability check in resource priming

* ci: fix `~/config` module mock

* ci: add OCR property expectation in AppService tests

* refactor: simplify OCR config loading by removing environment variable extraction, to be done when OCR is actually performed

* ci: add unit test to ensure environment variable references are not parsed in OCR config

* refactor: disable base64 image inclusion in OCR request

* refactor: enhance OCR configuration handling by validating environment variables and providing defaults

* refactor: use file stream from disk for mistral ocr api
This commit is contained in:
Danny Avila 2025-03-10 17:23:46 -04:00 • committed by GitHub
parent 9db00edfc4
commit ded3cd8876
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
48 changed files with 1621 additions and 131 deletions
Download patch file Download diff file Expand all files Collapse all files

2
api/server/controllers/agents/callbacks.js
View file

@ -10,8 +10,8 @@ const {
ChatModelStreamHandler,
} = require('@librechat/agents');
const { processCodeOutput } = require('~/server/services/Files/Code/process');
const { loadAuthValues } = require('~/server/services/Tools/credentials');
const { saveBase64Image } = require('~/server/services/Files/process');
const { loadAuthValues } = require('~/app/clients/tools/util');
const { logger, sendEvent } = require('~/config');
/** @typedef {import('@librechat/agents').Graph} Graph */

27
api/server/controllers/agents/client.js
View file

@ -223,14 +223,23 @@ class AgentClient extends BaseClient {
};
}
/**
*
* @param {TMessage} message
* @param {Array<MongoFile>} attachments
* @returns {Promise<Array<Partial<MongoFile>>>}
*/
async addImageURLs(message, attachments) {
const { files, image_urls } = await encodeAndFormat(
const { files, text, image_urls } = await encodeAndFormat(
this.options.req,
attachments,
this.options.agent.provider,
VisionModes.agents,
);
message.image_urls = image_urls.length ? image_urls : undefined;
if (text && text.length) {
message.ocr = text;
}
return files;
}
@ -308,7 +317,21 @@ class AgentClient extends BaseClient {
assistantName: this.options?.modelLabel,
});
const needsTokenCount = this.contextStrategy && !orderedMessages[i].tokenCount;
if (message.ocr && i !== orderedMessages.length - 1) {
if (typeof formattedMessage.content === 'string') {
formattedMessage.content = message.ocr + '\n' + formattedMessage.content;
} else {
const textPart = formattedMessage.content.find((part) => part.type === 'text');
textPart
? (textPart.text = message.ocr + '\n' + textPart.text)
: formattedMessage.content.unshift({ type: 'text', text: message.ocr });
}
} else if (message.ocr && i === orderedMessages.length - 1) {
systemContent = [systemContent, message.ocr].join('\n');
}
const needsTokenCount =
(this.contextStrategy && !orderedMessages[i].tokenCount) || message.ocr;
/* If tokens were never counted, or, is a Vision request and the message has files, count again */
if (needsTokenCount || (this.isVisionModel && (message.image_urls || message.files))) {