LibreChat/api/server/services/Files/images/encode.js
Danny Avila d20970f5c5
🚀 Feat: Streamline File Strategies & GPT-4-Vision Settings (#1535)
* chore: fix `endpoint` typescript issues and typo in console info message

* feat(api): files GET endpoint and save only file_id references to messages

* refactor(client): `useGetFiles` query hook, update file types, optimistic update of filesQuery on file upload

* refactor(buildTree): update to use params object and accept fileMap

* feat: map files to messages; refactor(ChatView): messages only available after files are fetched

* fix: fetch files only when authenticated

* feat(api): AppService
- rename app.locals.configs to app.locals.paths
- load custom config use fileStrategy from yaml config in app.locals

* refactor: separate Firebase and Local strategies, call based on config

* refactor: modularize file strategies and employ with use of DALL-E

* refactor(librechat.yaml): add fileStrategy field

* feat: add source to MongoFile schema, as well as BatchFile, and ExtendedFile types

* feat: employ file strategies for upload/delete files

* refactor(deleteFirebaseFile): add user id validation for firebase file deletion

* chore(deleteFirebaseFile): update jsdocs

* feat: employ strategies for vision requests

* fix(client): handle messages with deleted files

* fix(client): ensure `filesToDelete` always saves/sends `file.source`

* feat(openAI): configurable `resendImages` and `imageDetail`

* refactor(getTokenCountForMessage): recursive process only when array of Objects and only their values (not keys) aside from `image_url` types

* feat(OpenAIClient): calculateImageTokenCost

* chore: remove comment

* refactor(uploadAvatar): employ fileStrategy for avatars, from social logins or user upload

* docs: update docs on how to configure fileStrategy

* fix(ci): mock winston and winston related modules, update DALLE3.spec.js with changes made

* refactor(redis): change terminal message to reflect current development state

* fix(DALL-E-2): pass fileStrategy to dall-e
2024-01-11 11:37:54 -05:00

73 lines
2 KiB
JavaScript

const { EModelEndpoint, FileSources } = require('librechat-data-provider');
const { getStrategyFunctions } = require('../strategies');
/**
* Encodes and formats the given files.
* @param {Express.Request} req - The request object.
* @param {Array<MongoFile>} files - The array of files to encode and format.
* @param {EModelEndpoint} [endpoint] - Optional: The endpoint for the image.
* @returns {Promise<Object>} - A promise that resolves to the result object containing the encoded images and file details.
*/
async function encodeAndFormat(req, files, endpoint) {
const promises = [];
const encodingMethods = {};
for (let file of files) {
const source = file.source ?? FileSources.local;
if (encodingMethods[source]) {
promises.push(encodingMethods[source](req, file));
continue;
}
const { prepareImagePayload } = getStrategyFunctions(source);
if (!prepareImagePayload) {
throw new Error(`Encoding function not implemented for ${source}`);
}
encodingMethods[source] = prepareImagePayload;
promises.push(prepareImagePayload(req, file));
}
const detail = req.body.imageDetail ?? 'auto';
/** @type {Array<[MongoFile, string]>} */
const formattedImages = await Promise.all(promises);
const result = {
files: [],
image_urls: [],
};
for (const [file, imageContent] of formattedImages) {
const imagePart = {
type: 'image_url',
image_url: {
url: imageContent.startsWith('http')
? imageContent
: `data:image/webp;base64,${imageContent}`,
detail,
},
};
if (endpoint && endpoint === EModelEndpoint.google) {
imagePart.image_url = imagePart.image_url.url;
}
result.image_urls.push(imagePart);
result.files.push({
file_id: file.file_id,
// filepath: file.filepath,
// filename: file.filename,
// type: file.type,
// height: file.height,
// width: file.width,
});
}
return result;
}
module.exports = {
encodeAndFormat,
};