LibreChat/client/src/utils/forms.tsx
Danny Avila ded3cd8876
🔍 feat: Mistral OCR API / Upload Files as Text (#6274)
* 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
2025-03-10 17:23:46 -04:00

151 lines
3.9 KiB
TypeScript

import { EarthIcon } from 'lucide-react';
import {
alternateName,
EModelEndpoint,
FileSources,
EToolResources,
} from 'librechat-data-provider';
import type { Agent, TFile } from 'librechat-data-provider';
import type { DropdownValueSetter, TAgentOption, ExtendedFile } from '~/common';
/**
* Creates a Dropdown value setter that always passes a string value,
* for when options (object with label/value fields) are used for the
* available values, and a string value is expected when selected.
*
* Only necessary when the available values are objects with label/value fields
* and the selected value is expected to be a string.
**/
export const createDropdownSetter = (setValue: (value: string) => void): DropdownValueSetter => {
return (value) => {
if (!value) {
setValue('');
return;
}
if (typeof value === 'string') {
setValue(value);
return;
}
if (value.value) {
setValue(value.value + '');
}
};
};
/**
* Creates an Option object for a provider dropdown.
**/
export const createProviderOption = (provider: string) => ({
label: (alternateName[provider] as string | undefined) ?? provider,
value: provider,
});
export const processAgentOption = ({
agent: _agent,
fileMap,
instanceProjectId,
}: {
agent?: Agent;
fileMap?: Record<string, TFile | undefined>;
instanceProjectId?: string;
}): TAgentOption => {
const isGlobal =
(instanceProjectId != null && _agent?.projectIds?.includes(instanceProjectId)) ?? false;
const agent: TAgentOption = {
...(_agent ?? ({} as Agent)),
label: _agent?.name ?? '',
value: _agent?.id ?? '',
icon: isGlobal ? <EarthIcon className="icon-md text-green-400" /> : null,
context_files: _agent?.tool_resources?.ocr?.file_ids
? ([] as Array<[string, ExtendedFile]>)
: undefined,
knowledge_files: _agent?.tool_resources?.file_search?.file_ids
? ([] as Array<[string, ExtendedFile]>)
: undefined,
code_files: _agent?.tool_resources?.execute_code?.file_ids
? ([] as Array<[string, ExtendedFile]>)
: undefined,
};
if (!fileMap) {
return agent;
}
const handleFile = ({
file_id,
tool_resource,
list,
}: {
file_id: string;
tool_resource: EToolResources;
list?: Array<[string, ExtendedFile]>;
}) => {
const file = fileMap[file_id];
const source =
tool_resource === EToolResources.file_search
? FileSources.vectordb
: (file?.source ?? FileSources.local);
if (file) {
list?.push([
file_id,
{
file_id: file.file_id,
type: file.type,
filepath: file.filepath,
filename: file.filename,
width: file.width,
height: file.height,
size: file.bytes,
preview: file.filepath,
metadata: file.metadata,
progress: 1,
source,
},
]);
} else {
list?.push([
file_id,
{
file_id,
type: '',
filename: '',
size: 1,
progress: 1,
filepath: EModelEndpoint.agents,
source,
},
]);
}
};
if (agent.context_files && _agent?.tool_resources?.ocr?.file_ids) {
_agent.tool_resources.ocr.file_ids.forEach((file_id) =>
handleFile({
file_id,
list: agent.context_files,
tool_resource: EToolResources.ocr,
}),
);
}
if (agent.knowledge_files && _agent?.tool_resources?.file_search?.file_ids) {
_agent.tool_resources.file_search.file_ids.forEach((file_id) =>
handleFile({
file_id,
list: agent.knowledge_files,
tool_resource: EToolResources.file_search,
}),
);
}
if (agent.code_files && _agent?.tool_resources?.execute_code?.file_ids) {
_agent.tool_resources.execute_code.file_ids.forEach((file_id) =>
handleFile({ file_id, list: agent.code_files, tool_resource: EToolResources.execute_code }),
);
}
return agent;
};