mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-09-21 21:50:49 +02:00

* WIP: app.locals refactoring
WIP: appConfig
fix: update memory configuration retrieval to use getAppConfig based on user role
fix: update comment for AppConfig interface to clarify purpose
🏷️ refactor: Update tests to use getAppConfig for endpoint configurations
ci: Update AppService tests to initialize app config instead of app.locals
ci: Integrate getAppConfig into remaining tests
refactor: Update multer storage destination to use promise-based getAppConfig and improve error handling in tests
refactor: Rename initializeAppConfig to setAppConfig and update related tests
ci: Mock getAppConfig in various tests to provide default configurations
refactor: Update convertMCPToolsToPlugins to use mcpManager for server configuration and adjust related tests
chore: rename `Config/getAppConfig` -> `Config/app`
fix: streamline OpenAI image tools configuration by removing direct appConfig dependency and using function parameters
chore: correct parameter documentation for imageOutputType in ToolService.js
refactor: remove `getCustomConfig` dependency in config route
refactor: update domain validation to use appConfig for allowed domains
refactor: use appConfig registration property
chore: remove app parameter from AppService invocation
refactor: update AppConfig interface to correct registration and turnstile configurations
refactor: remove getCustomConfig dependency and use getAppConfig in PluginController, multer, and MCP services
refactor: replace getCustomConfig with getAppConfig in STTService, TTSService, and related files
refactor: replace getCustomConfig with getAppConfig in Conversation and Message models, update tempChatRetention functions to use AppConfig type
refactor: update getAppConfig calls in Conversation and Message models to include user role for temporary chat expiration
ci: update related tests
refactor: update getAppConfig call in getCustomConfigSpeech to include user role
fix: update appConfig usage to access allowedDomains from actions instead of registration
refactor: enhance AppConfig to include fileStrategies and update related file strategy logic
refactor: update imports to use normalizeEndpointName from @librechat/api and remove redundant definitions
chore: remove deprecated unused RunManager
refactor: get balance config primarily from appConfig
refactor: remove customConfig dependency for appConfig and streamline loadConfigModels logic
refactor: remove getCustomConfig usage and use app config in file citations
refactor: consolidate endpoint loading logic into loadEndpoints function
refactor: update appConfig access to use endpoints structure across various services
refactor: implement custom endpoints configuration and streamline endpoint loading logic
refactor: update getAppConfig call to include user role parameter
refactor: streamline endpoint configuration and enhance appConfig usage across services
refactor: replace getMCPAuthMap with getUserMCPAuthMap and remove unused getCustomConfig file
refactor: add type annotation for loadedEndpoints in loadEndpoints function
refactor: move /services/Files/images/parse to TS API
chore: add missing FILE_CITATIONS permission to IRole interface
refactor: restructure toolkits to TS API
refactor: separate manifest logic into its own module
refactor: consolidate tool loading logic into a new tools module for startup logic
refactor: move interface config logic to TS API
refactor: migrate checkEmailConfig to TypeScript and update imports
refactor: add FunctionTool interface and availableTools to AppConfig
refactor: decouple caching and DB operations from AppService, make part of consolidated `getAppConfig`
WIP: fix tests
* fix: rebase conflicts
* refactor: remove app.locals references
* refactor: replace getBalanceConfig with getAppConfig in various strategies and middleware
* refactor: replace appConfig?.balance with getBalanceConfig in various controllers and clients
* test: add balance configuration to titleConvo method in AgentClient tests
* chore: remove unused `openai-chat-tokens` package
* chore: remove unused imports in initializeMCPs.js
* refactor: update balance configuration to use getAppConfig instead of getBalanceConfig
* refactor: integrate configMiddleware for centralized configuration handling
* refactor: optimize email domain validation by removing unnecessary async calls
* refactor: simplify multer storage configuration by removing async calls
* refactor: reorder imports for better readability in user.js
* refactor: replace getAppConfig calls with req.config for improved performance
* chore: replace getAppConfig calls with req.config in tests for centralized configuration handling
* chore: remove unused override config
* refactor: add configMiddleware to endpoint route and replace getAppConfig with req.config
* chore: remove customConfig parameter from TTSService constructor
* refactor: pass appConfig from request to processFileCitations for improved configuration handling
* refactor: remove configMiddleware from endpoint route and retrieve appConfig directly in getEndpointsConfig if not in `req.config`
* test: add mockAppConfig to processFileCitations tests for improved configuration handling
* fix: pass req.config to hasCustomUserVars and call without await after synchronous refactor
* fix: type safety in useExportConversation
* refactor: retrieve appConfig using getAppConfig in PluginController and remove configMiddleware from plugins route, to avoid always retrieving when plugins are cached
* chore: change `MongoUser` typedef to `IUser`
* fix: Add `user` and `config` fields to ServerRequest and update JSDoc type annotations from Express.Request to ServerRequest
* fix: remove unused setAppConfig mock from Server configuration tests
420 lines
14 KiB
JavaScript
420 lines
14 KiB
JavaScript
const axios = require('axios');
|
|
const { v4 } = require('uuid');
|
|
const OpenAI = require('openai');
|
|
const FormData = require('form-data');
|
|
const { ProxyAgent } = require('undici');
|
|
const { tool } = require('@langchain/core/tools');
|
|
const { logger } = require('@librechat/data-schemas');
|
|
const { logAxiosError, oaiToolkit } = require('@librechat/api');
|
|
const { ContentTypes, EImageOutputType } = require('librechat-data-provider');
|
|
const { getStrategyFunctions } = require('~/server/services/Files/strategies');
|
|
const extractBaseURL = require('~/utils/extractBaseURL');
|
|
const { getFiles } = require('~/models/File');
|
|
|
|
const displayMessage =
|
|
"The tool displayed an image. All generated images are already plainly visible, so don't repeat the descriptions in detail. Do not list download links as they are available in the UI already. The user may download the images by clicking on them, but do not mention anything about downloading to the user.";
|
|
|
|
/**
|
|
* Replaces unwanted characters from the input string
|
|
* @param {string} inputString - The input string to process
|
|
* @returns {string} - The processed string
|
|
*/
|
|
function replaceUnwantedChars(inputString) {
|
|
return inputString
|
|
.replace(/\r\n|\r|\n/g, ' ')
|
|
.replace(/"/g, '')
|
|
.trim();
|
|
}
|
|
|
|
function returnValue(value) {
|
|
if (typeof value === 'string') {
|
|
return [value, {}];
|
|
} else if (typeof value === 'object') {
|
|
if (Array.isArray(value)) {
|
|
return value;
|
|
}
|
|
return [displayMessage, value];
|
|
}
|
|
return value;
|
|
}
|
|
|
|
function createAbortHandler() {
|
|
return function () {
|
|
logger.debug('[ImageGenOAI] Image generation aborted');
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Creates OpenAI Image tools (generation and editing)
|
|
* @param {Object} fields - Configuration fields
|
|
* @param {ServerRequest} fields.req - Whether the tool is being used in an agent context
|
|
* @param {boolean} fields.isAgent - Whether the tool is being used in an agent context
|
|
* @param {string} fields.IMAGE_GEN_OAI_API_KEY - The OpenAI API key
|
|
* @param {boolean} [fields.override] - Whether to override the API key check, necessary for app initialization
|
|
* @param {MongoFile[]} [fields.imageFiles] - The images to be used for editing
|
|
* @param {string} [fields.imageOutputType] - The image output type configuration
|
|
* @param {string} [fields.fileStrategy] - The file storage strategy
|
|
* @returns {Array<ReturnType<tool>>} - Array of image tools
|
|
*/
|
|
function createOpenAIImageTools(fields = {}) {
|
|
/** @type {boolean} Used to initialize the Tool without necessary variables. */
|
|
const override = fields.override ?? false;
|
|
/** @type {boolean} */
|
|
if (!override && !fields.isAgent) {
|
|
throw new Error('This tool is only available for agents.');
|
|
}
|
|
const { req } = fields;
|
|
const imageOutputType = fields.imageOutputType || EImageOutputType.PNG;
|
|
const appFileStrategy = fields.fileStrategy;
|
|
|
|
const getApiKey = () => {
|
|
const apiKey = process.env.IMAGE_GEN_OAI_API_KEY ?? '';
|
|
if (!apiKey && !override) {
|
|
throw new Error('Missing IMAGE_GEN_OAI_API_KEY environment variable.');
|
|
}
|
|
return apiKey;
|
|
};
|
|
|
|
let apiKey = fields.IMAGE_GEN_OAI_API_KEY ?? getApiKey();
|
|
const closureConfig = { apiKey };
|
|
|
|
let baseURL = 'https://api.openai.com/v1/';
|
|
if (!override && process.env.IMAGE_GEN_OAI_BASEURL) {
|
|
baseURL = extractBaseURL(process.env.IMAGE_GEN_OAI_BASEURL);
|
|
closureConfig.baseURL = baseURL;
|
|
}
|
|
|
|
// Note: Azure may not yet support the latest image generation models
|
|
if (
|
|
!override &&
|
|
process.env.IMAGE_GEN_OAI_AZURE_API_VERSION &&
|
|
process.env.IMAGE_GEN_OAI_BASEURL
|
|
) {
|
|
baseURL = process.env.IMAGE_GEN_OAI_BASEURL;
|
|
closureConfig.baseURL = baseURL;
|
|
closureConfig.defaultQuery = { 'api-version': process.env.IMAGE_GEN_OAI_AZURE_API_VERSION };
|
|
closureConfig.defaultHeaders = {
|
|
'api-key': process.env.IMAGE_GEN_OAI_API_KEY,
|
|
'Content-Type': 'application/json',
|
|
};
|
|
closureConfig.apiKey = process.env.IMAGE_GEN_OAI_API_KEY;
|
|
}
|
|
|
|
const imageFiles = fields.imageFiles ?? [];
|
|
|
|
/**
|
|
* Image Generation Tool
|
|
*/
|
|
const imageGenTool = tool(
|
|
async (
|
|
{
|
|
prompt,
|
|
background = 'auto',
|
|
n = 1,
|
|
output_compression = 100,
|
|
quality = 'auto',
|
|
size = 'auto',
|
|
},
|
|
runnableConfig,
|
|
) => {
|
|
if (!prompt) {
|
|
throw new Error('Missing required field: prompt');
|
|
}
|
|
const clientConfig = { ...closureConfig };
|
|
if (process.env.PROXY) {
|
|
const proxyAgent = new ProxyAgent(process.env.PROXY);
|
|
clientConfig.fetchOptions = {
|
|
dispatcher: proxyAgent,
|
|
};
|
|
}
|
|
|
|
/** @type {OpenAI} */
|
|
const openai = new OpenAI(clientConfig);
|
|
let output_format = imageOutputType;
|
|
if (
|
|
background === 'transparent' &&
|
|
output_format !== EImageOutputType.PNG &&
|
|
output_format !== EImageOutputType.WEBP
|
|
) {
|
|
logger.warn(
|
|
'[ImageGenOAI] Transparent background requires PNG or WebP format, defaulting to PNG',
|
|
);
|
|
output_format = EImageOutputType.PNG;
|
|
}
|
|
|
|
let resp;
|
|
/** @type {AbortSignal} */
|
|
let derivedSignal = null;
|
|
/** @type {() => void} */
|
|
let abortHandler = null;
|
|
|
|
try {
|
|
if (runnableConfig?.signal) {
|
|
derivedSignal = AbortSignal.any([runnableConfig.signal]);
|
|
abortHandler = createAbortHandler();
|
|
derivedSignal.addEventListener('abort', abortHandler, { once: true });
|
|
}
|
|
|
|
resp = await openai.images.generate(
|
|
{
|
|
model: 'gpt-image-1',
|
|
prompt: replaceUnwantedChars(prompt),
|
|
n: Math.min(Math.max(1, n), 10),
|
|
background,
|
|
output_format,
|
|
output_compression:
|
|
output_format === EImageOutputType.WEBP || output_format === EImageOutputType.JPEG
|
|
? output_compression
|
|
: undefined,
|
|
quality,
|
|
size,
|
|
},
|
|
{
|
|
signal: derivedSignal,
|
|
},
|
|
);
|
|
} catch (error) {
|
|
const message = '[image_gen_oai] Problem generating the image:';
|
|
logAxiosError({ error, message });
|
|
return returnValue(`Something went wrong when trying to generate the image. The OpenAI API may be unavailable:
|
|
Error Message: ${error.message}`);
|
|
} finally {
|
|
if (abortHandler && derivedSignal) {
|
|
derivedSignal.removeEventListener('abort', abortHandler);
|
|
}
|
|
}
|
|
|
|
if (!resp) {
|
|
return returnValue(
|
|
'Something went wrong when trying to generate the image. The OpenAI API may be unavailable',
|
|
);
|
|
}
|
|
|
|
// For gpt-image-1, the response contains base64-encoded images
|
|
// TODO: handle cost in `resp.usage`
|
|
const base64Image = resp.data[0].b64_json;
|
|
|
|
if (!base64Image) {
|
|
return returnValue(
|
|
'No image data returned from OpenAI API. There may be a problem with the API or your configuration.',
|
|
);
|
|
}
|
|
|
|
const content = [
|
|
{
|
|
type: ContentTypes.IMAGE_URL,
|
|
image_url: {
|
|
url: `data:image/${output_format};base64,${base64Image}`,
|
|
},
|
|
},
|
|
];
|
|
|
|
const file_ids = [v4()];
|
|
const response = [
|
|
{
|
|
type: ContentTypes.TEXT,
|
|
text: displayMessage + `\n\ngenerated_image_id: "${file_ids[0]}"`,
|
|
},
|
|
];
|
|
return [response, { content, file_ids }];
|
|
},
|
|
oaiToolkit.image_gen_oai,
|
|
);
|
|
|
|
/**
|
|
* Image Editing Tool
|
|
*/
|
|
const imageEditTool = tool(
|
|
async ({ prompt, image_ids, quality = 'auto', size = 'auto' }, runnableConfig) => {
|
|
if (!prompt) {
|
|
throw new Error('Missing required field: prompt');
|
|
}
|
|
|
|
const clientConfig = { ...closureConfig };
|
|
if (process.env.PROXY) {
|
|
const proxyAgent = new ProxyAgent(process.env.PROXY);
|
|
clientConfig.fetchOptions = {
|
|
dispatcher: proxyAgent,
|
|
};
|
|
}
|
|
|
|
const formData = new FormData();
|
|
formData.append('model', 'gpt-image-1');
|
|
formData.append('prompt', replaceUnwantedChars(prompt));
|
|
// TODO: `mask` support
|
|
// TODO: more than 1 image support
|
|
// formData.append('n', n.toString());
|
|
formData.append('quality', quality);
|
|
formData.append('size', size);
|
|
|
|
/** @type {Record<FileSources, undefined | NodeStreamDownloader<File>>} */
|
|
const streamMethods = {};
|
|
|
|
const requestFilesMap = Object.fromEntries(imageFiles.map((f) => [f.file_id, { ...f }]));
|
|
|
|
const orderedFiles = new Array(image_ids.length);
|
|
const idsToFetch = [];
|
|
const indexOfMissing = Object.create(null);
|
|
|
|
for (let i = 0; i < image_ids.length; i++) {
|
|
const id = image_ids[i];
|
|
const file = requestFilesMap[id];
|
|
|
|
if (file) {
|
|
orderedFiles[i] = file;
|
|
} else {
|
|
idsToFetch.push(id);
|
|
indexOfMissing[id] = i;
|
|
}
|
|
}
|
|
|
|
if (idsToFetch.length) {
|
|
const fetchedFiles = await getFiles(
|
|
{
|
|
user: req.user.id,
|
|
file_id: { $in: idsToFetch },
|
|
height: { $exists: true },
|
|
width: { $exists: true },
|
|
},
|
|
{},
|
|
{},
|
|
);
|
|
|
|
for (const file of fetchedFiles) {
|
|
requestFilesMap[file.file_id] = file;
|
|
orderedFiles[indexOfMissing[file.file_id]] = file;
|
|
}
|
|
}
|
|
for (const imageFile of orderedFiles) {
|
|
if (!imageFile) {
|
|
continue;
|
|
}
|
|
/** @type {NodeStream<File>} */
|
|
let stream;
|
|
/** @type {NodeStreamDownloader<File>} */
|
|
let getDownloadStream;
|
|
const source = imageFile.source || appFileStrategy;
|
|
if (!source) {
|
|
throw new Error('No source found for image file');
|
|
}
|
|
if (streamMethods[source]) {
|
|
getDownloadStream = streamMethods[source];
|
|
} else {
|
|
({ getDownloadStream } = getStrategyFunctions(source));
|
|
streamMethods[source] = getDownloadStream;
|
|
}
|
|
if (!getDownloadStream) {
|
|
throw new Error(`No download stream method found for source: ${source}`);
|
|
}
|
|
stream = await getDownloadStream(req, imageFile.filepath);
|
|
if (!stream) {
|
|
throw new Error('Failed to get download stream for image file');
|
|
}
|
|
formData.append('image[]', stream, {
|
|
filename: imageFile.filename,
|
|
contentType: imageFile.type,
|
|
});
|
|
}
|
|
|
|
/** @type {import('axios').RawAxiosHeaders} */
|
|
let headers = {
|
|
...formData.getHeaders(),
|
|
};
|
|
|
|
if (process.env.IMAGE_GEN_OAI_AZURE_API_VERSION && process.env.IMAGE_GEN_OAI_BASEURL) {
|
|
headers['api-key'] = apiKey;
|
|
} else {
|
|
headers['Authorization'] = `Bearer ${apiKey}`;
|
|
}
|
|
|
|
/** @type {AbortSignal} */
|
|
let derivedSignal = null;
|
|
/** @type {() => void} */
|
|
let abortHandler = null;
|
|
|
|
try {
|
|
if (runnableConfig?.signal) {
|
|
derivedSignal = AbortSignal.any([runnableConfig.signal]);
|
|
abortHandler = createAbortHandler();
|
|
derivedSignal.addEventListener('abort', abortHandler, { once: true });
|
|
}
|
|
|
|
/** @type {import('axios').AxiosRequestConfig} */
|
|
const axiosConfig = {
|
|
headers,
|
|
...clientConfig,
|
|
signal: derivedSignal,
|
|
baseURL,
|
|
};
|
|
|
|
if (process.env.PROXY) {
|
|
try {
|
|
const url = new URL(process.env.PROXY);
|
|
axiosConfig.proxy = {
|
|
host: url.hostname.replace(/^\[|\]$/g, ''),
|
|
port: url.port ? parseInt(url.port, 10) : undefined,
|
|
protocol: url.protocol.replace(':', ''),
|
|
};
|
|
} catch (error) {
|
|
logger.error('Error parsing proxy URL:', error);
|
|
}
|
|
}
|
|
|
|
if (process.env.IMAGE_GEN_OAI_AZURE_API_VERSION && process.env.IMAGE_GEN_OAI_BASEURL) {
|
|
axiosConfig.params = {
|
|
'api-version': process.env.IMAGE_GEN_OAI_AZURE_API_VERSION,
|
|
...axiosConfig.params,
|
|
};
|
|
}
|
|
const response = await axios.post('/images/edits', formData, axiosConfig);
|
|
|
|
if (!response.data || !response.data.data || !response.data.data.length) {
|
|
return returnValue(
|
|
'No image data returned from OpenAI API. There may be a problem with the API or your configuration.',
|
|
);
|
|
}
|
|
|
|
const base64Image = response.data.data[0].b64_json;
|
|
if (!base64Image) {
|
|
return returnValue(
|
|
'No image data returned from OpenAI API. There may be a problem with the API or your configuration.',
|
|
);
|
|
}
|
|
|
|
const content = [
|
|
{
|
|
type: ContentTypes.IMAGE_URL,
|
|
image_url: {
|
|
url: `data:image/${imageOutputType};base64,${base64Image}`,
|
|
},
|
|
},
|
|
];
|
|
|
|
const file_ids = [v4()];
|
|
const textResponse = [
|
|
{
|
|
type: ContentTypes.TEXT,
|
|
text:
|
|
displayMessage +
|
|
`\n\ngenerated_image_id: "${file_ids[0]}"\nreferenced_image_ids: ["${image_ids.join('", "')}"]`,
|
|
},
|
|
];
|
|
return [textResponse, { content, file_ids }];
|
|
} catch (error) {
|
|
const message = '[image_edit_oai] Problem editing the image:';
|
|
logAxiosError({ error, message });
|
|
return returnValue(`Something went wrong when trying to edit the image. The OpenAI API may be unavailable:
|
|
Error Message: ${error.message || 'Unknown error'}`);
|
|
} finally {
|
|
if (abortHandler && derivedSignal) {
|
|
derivedSignal.removeEventListener('abort', abortHandler);
|
|
}
|
|
}
|
|
},
|
|
oaiToolkit.image_edit_oai,
|
|
);
|
|
|
|
return [imageGenTool, imageEditTool];
|
|
}
|
|
|
|
module.exports = createOpenAIImageTools;
|