Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-22 11:20:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

🔍 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

41
client/src/components/Chat/Input/Files/SourceIcon.tsx
View file

@ -1,3 +1,4 @@
import { Terminal, Type, Database } from 'lucide-react';
import { EModelEndpoint, FileSources } from 'librechat-data-provider';
import { MinimalIcon } from '~/components/Endpoints';
import { cn } from '~/utils';
@ -6,9 +7,13 @@ const sourceToEndpoint = {
[FileSources.openai]: EModelEndpoint.openAI,
[FileSources.azure]: EModelEndpoint.azureOpenAI,
};
const sourceToClassname = {
[FileSources.openai]: 'bg-white/75 dark:bg-black/65',
[FileSources.azure]: 'azure-bg-color opacity-85',
[FileSources.execute_code]: 'bg-black text-white opacity-85',
[FileSources.text]: 'bg-blue-100 dark:bg-blue-900 opacity-85 text-white',
[FileSources.vectordb]: 'bg-yellow-100 dark:bg-yellow-900 opacity-85 text-white',
};
const defaultClassName =
@ -16,13 +21,41 @@ const defaultClassName =
export default function SourceIcon({
source,
isCodeFile,
className = defaultClassName,
}: {
source?: FileSources;
isCodeFile?: boolean;
className?: string;
}) {
if (source === FileSources.local || source === FileSources.firebase) {
return null;
if (isCodeFile === true) {
return (
<div className={cn(className, sourceToClassname[FileSources.execute_code] ?? '')}>
<span className="flex items-center justify-center">
<Terminal className="h-3 w-3" />
</span>
</div>
);
}
if (source === FileSources.text) {
return (
<div className={cn(className, sourceToClassname[source] ?? '')}>
<span className="flex items-center justify-center">
<Type className="h-3 w-3" />
</span>
</div>
);
}
if (source === FileSources.vectordb) {
return (
<div className={cn(className, sourceToClassname[source] ?? '')}>
<span className="flex items-center justify-center">
<Database className="h-3 w-3" />
</span>
</div>
);
}
const endpoint = sourceToEndpoint[source ?? ''];
@ -31,7 +64,7 @@ export default function SourceIcon({
return null;
}
return (
<button type="button" className={cn(className, sourceToClassname[source ?? ''] ?? '')}>
<div className={cn(className, sourceToClassname[source ?? ''] ?? '')}>
<span className="flex items-center justify-center">
<MinimalIcon
endpoint={endpoint}
@ -40,6 +73,6 @@ export default function SourceIcon({
iconClassName="h-3 w-3"
/>
</span>
</button>
</div>
);
}