LibreChat/api/server/services/Endpoints/openAI/initialize.js
Danny Avila 29ef91b4dd
🧠 feat: User Memories for Conversational Context (#7760)
* 🧠 feat: User Memories for Conversational Context

chore: mcp typing, use `t`

WIP: first pass, Memories UI

- Added MemoryViewer component for displaying, editing, and deleting user memories.
- Integrated data provider hooks for fetching, updating, and deleting memories.
- Implemented pagination and loading states for better user experience.
- Created unit tests for MemoryViewer to ensure functionality and interaction with data provider.
- Updated translation files to include new UI strings related to memories.

chore: move mcp-related files to own directory

chore: rename librechat-mcp to librechat-api

WIP: first pass, memory processing and data schemas

chore: linting in fileSearch.js query description

chore: rename librechat-api to @librechat/api across the project

WIP: first pass, functional memory agent

feat: add MemoryEditDialog and MemoryViewer components for managing user memories

- Introduced MemoryEditDialog for editing memory entries with validation and toast notifications.
- Updated MemoryViewer to support editing and deleting memories, including pagination and loading states.
- Enhanced data provider to handle memory updates with optional original key for better management.
- Added new localization strings for memory-related UI elements.

feat: add memory permissions management

- Implemented memory permissions in the backend, allowing roles to have specific permissions for using, creating, updating, and reading memories.
- Added new API endpoints for updating memory permissions associated with roles.
- Created a new AdminSettings component for managing memory permissions in the frontend.
- Integrated memory permissions into the existing roles and permissions schemas.
- Updated the interface to include memory settings and permissions.
- Enhanced the MemoryViewer component to conditionally render admin settings based on user roles.
- Added localization support for memory permissions in the translation files.

feat: move AdminSettings component to a new position in MemoryViewer for better visibility

refactor: clean up commented code in MemoryViewer component

feat: enhance MemoryViewer with search functionality and improve MemoryEditDialog integration

- Added a search input to filter memories in the MemoryViewer component.
- Refactored MemoryEditDialog to accept children for better customization.
- Updated MemoryViewer to utilize the new EditMemoryButton and DeleteMemoryButton components for editing and deleting memories.
- Improved localization support by adding new strings for memory filtering and deletion confirmation.

refactor: optimize memory filtering in MemoryViewer using match-sorter

- Replaced manual filtering logic with match-sorter for improved search functionality.
- Enhanced performance and readability of the filteredMemories computation.

feat: enhance MemoryEditDialog with triggerRef and improve updateMemory mutation handling

feat: implement access control for MemoryEditDialog and MemoryViewer components

refactor: remove commented out code and create runMemory method

refactor: rename role based files

feat: implement access control for memory usage in AgentClient

refactor: simplify checkVisionRequest method in AgentClient by removing commented-out code

refactor: make `agents` dir in api package

refactor: migrate Azure utilities to TypeScript and consolidate imports

refactor: move sanitizeFilename function to a new file and update imports, add related tests

refactor: update LLM configuration types and consolidate Azure options in the API package

chore: linting

chore: import order

refactor: replace getLLMConfig with getOpenAIConfig and remove unused LLM configuration file

chore: update winston-daily-rotate-file to version 5.0.0 and add object-hash dependency in package-lock.json

refactor: move primeResources and optionalChainWithEmptyCheck functions to resources.ts and update imports

refactor: move createRun function to a new run.ts file and update related imports

fix: ensure safeAttachments is correctly typed as an array of TFile

chore: add node-fetch dependency and refactor fetch-related functions into packages/api/utils, removing the old generators file

refactor: enhance TEndpointOption type by using Pick to streamline endpoint fields and add new properties for model parameters and client options

feat: implement initializeOpenAIOptions function and update OpenAI types for enhanced configuration handling

fix: update types due to new TEndpointOption typing

fix: ensure safe access to group parameters in initializeOpenAIOptions function

fix: remove redundant API key validation comment in initializeOpenAIOptions function

refactor: rename initializeOpenAIOptions to initializeOpenAI for consistency and update related documentation

refactor: decouple req.body fields and tool loading from initializeAgentOptions

chore: linting

refactor: adjust column widths in MemoryViewer for improved layout

refactor: simplify agent initialization by creating loadAgent function and removing unused code

feat: add memory configuration loading and validation functions

WIP: first pass, memory processing with config

feat: implement memory callback and artifact handling

feat: implement memory artifacts display and processing updates

feat: add memory configuration options and schema validation for validKeys

fix: update MemoryEditDialog and MemoryViewer to handle memory state and display improvements

refactor: remove padding from BookmarkTable and MemoryViewer headers for consistent styling

WIP: initial tokenLimit config and move Tokenizer to @librechat/api

refactor: update mongoMeili plugin methods to use callback for better error handling

feat: enhance memory management with token tracking and usage metrics

- Added token counting for memory entries to enforce limits and provide usage statistics.
- Updated memory retrieval and update routes to include total token usage and limit.
- Enhanced MemoryEditDialog and MemoryViewer components to display memory usage and token information.
- Refactored memory processing functions to handle token limits and provide feedback on memory capacity.

feat: implement memory artifact handling in attachment handler

- Enhanced useAttachmentHandler to process memory artifacts when receiving updates.
- Introduced handleMemoryArtifact utility to manage memory updates and deletions.
- Updated query client to reflect changes in memory state based on incoming data.

refactor: restructure web search key extraction logic

- Moved the logic for extracting API keys from the webSearchAuth configuration into a dedicated function, getWebSearchKeys.
- Updated webSearchKeys to utilize the new function for improved clarity and maintainability.
- Prevents build time errors

feat: add personalization settings and memory preferences management

- Introduced a new Personalization tab in settings to manage user memory preferences.
- Implemented API endpoints and client-side logic for updating memory preferences.
- Enhanced user interface components to reflect personalization options and memory usage.
- Updated permissions to allow users to opt out of memory features.
- Added localization support for new settings and messages related to personalization.

style: personalization switch class

feat: add PersonalizationIcon and align Side Panel UI

feat: implement memory creation functionality

- Added a new API endpoint for creating memory entries, including validation for key and value.
- Introduced MemoryCreateDialog component for user interface to facilitate memory creation.
- Integrated token limit checks to prevent exceeding user memory capacity.
- Updated MemoryViewer to include a button for opening the memory creation dialog.
- Enhanced localization support for new messages related to memory creation.

feat: enhance message processing with configurable window size

- Updated AgentClient to use a configurable message window size for processing messages.
- Introduced messageWindowSize option in memory configuration schema with a default value of 5.
- Improved logic for selecting messages to process based on the configured window size.

chore: update librechat-data-provider version to 0.7.87 in package.json and package-lock.json

chore: remove OpenAPIPlugin and its associated tests

chore: remove MIGRATION_README.md as migration tasks are completed

ci: fix backend tests

chore: remove unused translation keys from localization file

chore: remove problematic test file and unused var in AgentClient

chore: remove unused import and import directly for JSDoc

* feat: add api package build stage in Dockerfile for improved modularity

* docs: reorder build steps in contributing guide for clarity
2025-06-07 18:52:22 -04:00

166 lines
4.9 KiB
JavaScript

const {
ErrorTypes,
EModelEndpoint,
resolveHeaders,
mapModelToAzureConfig,
} = require('librechat-data-provider');
const {
isEnabled,
isUserProvided,
getOpenAIConfig,
getAzureCredentials,
createHandleLLMNewToken,
} = require('@librechat/api');
const { getUserKeyValues, checkUserKeyExpiry } = require('~/server/services/UserService');
const OpenAIClient = require('~/app/clients/OpenAIClient');
const initializeClient = async ({
req,
res,
endpointOption,
optionsOnly,
overrideEndpoint,
overrideModel,
}) => {
const {
PROXY,
OPENAI_API_KEY,
AZURE_API_KEY,
OPENAI_REVERSE_PROXY,
AZURE_OPENAI_BASEURL,
OPENAI_SUMMARIZE,
DEBUG_OPENAI,
} = process.env;
const { key: expiresAt } = req.body;
const modelName = overrideModel ?? req.body.model;
const endpoint = overrideEndpoint ?? req.body.endpoint;
const contextStrategy = isEnabled(OPENAI_SUMMARIZE) ? 'summarize' : null;
const credentials = {
[EModelEndpoint.openAI]: OPENAI_API_KEY,
[EModelEndpoint.azureOpenAI]: AZURE_API_KEY,
};
const baseURLOptions = {
[EModelEndpoint.openAI]: OPENAI_REVERSE_PROXY,
[EModelEndpoint.azureOpenAI]: AZURE_OPENAI_BASEURL,
};
const userProvidesKey = isUserProvided(credentials[endpoint]);
const userProvidesURL = isUserProvided(baseURLOptions[endpoint]);
let userValues = null;
if (expiresAt && (userProvidesKey || userProvidesURL)) {
checkUserKeyExpiry(expiresAt, endpoint);
userValues = await getUserKeyValues({ userId: req.user.id, name: endpoint });
}
let apiKey = userProvidesKey ? userValues?.apiKey : credentials[endpoint];
let baseURL = userProvidesURL ? userValues?.baseURL : baseURLOptions[endpoint];
let clientOptions = {
contextStrategy,
proxy: PROXY ?? null,
debug: isEnabled(DEBUG_OPENAI),
reverseProxyUrl: baseURL ? baseURL : null,
...endpointOption,
};
const isAzureOpenAI = endpoint === EModelEndpoint.azureOpenAI;
/** @type {false | TAzureConfig} */
const azureConfig = isAzureOpenAI && req.app.locals[EModelEndpoint.azureOpenAI];
if (isAzureOpenAI && azureConfig) {
const { modelGroupMap, groupMap } = azureConfig;
const {
azureOptions,
baseURL,
headers = {},
serverless,
} = mapModelToAzureConfig({
modelName,
modelGroupMap,
groupMap,
});
clientOptions.reverseProxyUrl = baseURL ?? clientOptions.reverseProxyUrl;
clientOptions.headers = resolveHeaders({ ...headers, ...(clientOptions.headers ?? {}) });
clientOptions.titleConvo = azureConfig.titleConvo;
clientOptions.titleModel = azureConfig.titleModel;
const azureRate = modelName.includes('gpt-4') ? 30 : 17;
clientOptions.streamRate = azureConfig.streamRate ?? azureRate;
clientOptions.titleMethod = azureConfig.titleMethod ?? 'completion';
const groupName = modelGroupMap[modelName].group;
clientOptions.addParams = azureConfig.groupMap[groupName].addParams;
clientOptions.dropParams = azureConfig.groupMap[groupName].dropParams;
clientOptions.forcePrompt = azureConfig.groupMap[groupName].forcePrompt;
apiKey = azureOptions.azureOpenAIApiKey;
clientOptions.azure = !serverless && azureOptions;
if (serverless === true) {
clientOptions.defaultQuery = azureOptions.azureOpenAIApiVersion
? { 'api-version': azureOptions.azureOpenAIApiVersion }
: undefined;
clientOptions.headers['api-key'] = apiKey;
}
} else if (isAzureOpenAI) {
clientOptions.azure = userProvidesKey ? JSON.parse(userValues.apiKey) : getAzureCredentials();
apiKey = clientOptions.azure.azureOpenAIApiKey;
}
/** @type {undefined | TBaseEndpoint} */
const openAIConfig = req.app.locals[EModelEndpoint.openAI];
if (!isAzureOpenAI && openAIConfig) {
clientOptions.streamRate = openAIConfig.streamRate;
clientOptions.titleModel = openAIConfig.titleModel;
}
/** @type {undefined | TBaseEndpoint} */
const allConfig = req.app.locals.all;
if (allConfig) {
clientOptions.streamRate = allConfig.streamRate;
}
if (userProvidesKey & !apiKey) {
throw new Error(
JSON.stringify({
type: ErrorTypes.NO_USER_KEY,
}),
);
}
if (!apiKey) {
throw new Error(`${endpoint} API Key not provided.`);
}
if (optionsOnly) {
const modelOptions = endpointOption.model_parameters;
modelOptions.model = modelName;
clientOptions = Object.assign({ modelOptions }, clientOptions);
clientOptions.modelOptions.user = req.user.id;
const options = getOpenAIConfig(apiKey, clientOptions);
const streamRate = clientOptions.streamRate;
if (!streamRate) {
return options;
}
options.llmConfig.callbacks = [
{
handleLLMNewToken: createHandleLLMNewToken(streamRate),
},
];
return options;
}
const client = new OpenAIClient(apiKey, Object.assign({ req, res }, clientOptions));
return {
client,
openAIApiKey: apiKey,
};
};
module.exports = initializeClient;