refactor: Encrypt & Expire User Provided Keys, feat: Rate Limiting (#874)

* docs: make_your_own.md formatting fix for mkdocs

* feat: add express-mongo-sanitize
feat: add login/registration rate limiting

* chore: remove unnecessary console log

* wip: remove token handling from localStorage to encrypted DB solution

* refactor: minor change to UserService

* fix mongo query and add keys route to server

* fix backend controllers and simplify schema/crud

* refactor: rename token to key to separate from access/refresh tokens, setTokenDialog -> setKeyDialog

* refactor(schemas): TEndpointOption token -> key

* refactor(api): use new encrypted key retrieval system

* fix(SetKeyDialog): fix key prop error

* fix(abortMiddleware): pass random UUID if messageId is not generated yet for proper error display on frontend

* fix(getUserKey): wrong prop passed in arg, adds error handling

* fix: prevent message without conversationId from saving to DB, prevents branching on the frontend to a new top-level branch

* refactor: change wording of multiple display messages

* refactor(checkExpiry -> checkUserKeyExpiry): move to UserService file

* fix: type imports from common

* refactor(SubmitButton): convert to TS

* refactor(key.ts): change localStorage map key name

* refactor: add new custom tailwind classes to better match openAI colors

* chore: remove unnecessary warning and catch ScreenShot error

* refactor: move userKey frontend logic to hooks and remove use of localStorage and instead query the DB

* refactor: invalidate correct query key, memoize userKey hook, conditionally render SetKeyDialog to avoid unnecessary calls, refactor SubmitButton props and useEffect for showing 'provide key first'

* fix(SetKeyDialog): use enum-like object for expiry values
feat(Dropdown): add optionsClassName to dynamically change dropdown options container classes

* fix: handle edge case where user had provided a key but the server changes to env variable for keys

* refactor(OpenAI/titleConvo): move titling to client to retain authorized credentials in message lifecycle for titling

* fix(azure): handle user_provided keys correctly for azure

* feat: send user Id to OpenAI to differentiate users in completion requests

* refactor(OpenAI/titleConvo): adding tokens helps minimize LLM from using the language in title response

* feat: add delete endpoint for keys

* chore: remove throttling of title

* feat: add 'Data controls' to Settings, add 'Revoke' keys feature in Key Dialog and Data controls

* refactor: reorganize PluginsClient files in langchain format

* feat: use langchain for titling convos

* chore: cleanup titling convo, with fallback to original method, escape braces, use only snippet for language detection

* refactor: move helper functions to appropriate langchain folders for reusability

* fix: userProvidesKey handling for gptPlugins

* fix: frontend handling of plugins key

* chore: cleanup logging and ts-ignore SSE

* fix: forwardRef misuse in DangerButton

* fix(GoogleConfig/FileUpload): localize errors and simplify validation with zod

* fix: cleanup google logging and fix user provided key handling

* chore: remove titling from google

* chore: removing logging from browser endpoint

* wip: fix menu flicker

* feat: useLocalStorage hook

* feat: add Tooltip for UI

* refactor(EndpointMenu): utilize Tooltip and useLocalStorage, remove old 'New Chat' slide-over

* fix(e2e): use testId for endpoint menu trigger

* chore: final touches to EndpointMenu before future refactor to declutter component

* refactor(localization): change select endpoint to open menu and add translations

* chore: add final prop to error message response

* ci: minor edits to facilitate testing

* ci: new e2e test which tests for new key setting/revoking features

api/app/clients/OpenAIClient.js

@@ -5,6 +5,8 @@ const {
   get_encoding: getEncoding,
 } = require('@dqbd/tiktoken');
 const { maxTokensMap, genAzureChatCompletion } = require('../../utils');
+const { runTitleChain } = require('./chains');
+const { createLLM } = require('./llm');
 
 // Cache to store Tiktoken instances
 const tokenizersCache = {};
@@ -105,6 +107,7 @@ class OpenAIClient extends BaseClient {
 
     if (this.options.reverseProxyUrl) {
       this.completionsUrl = this.options.reverseProxyUrl;
+      this.langchainProxy = this.options.reverseProxyUrl.match(/.*v1/)[0];
     } else if (isChatGptModel) {
       this.completionsUrl = 'https://api.openai.com/v1/chat/completions';
     } else {
@@ -116,7 +119,7 @@ class OpenAIClient extends BaseClient {
     }
 
     if (this.azureEndpoint && this.options.debug) {
-      console.debug(`Using Azure endpoint: ${this.azureEndpoint}`, this.azure);
+      console.debug('Using Azure endpoint');
     }
 
     return this;
@@ -315,6 +318,7 @@ class OpenAIClient extends BaseClient {
     let reply = '';
     let result = null;
     let streamResult = null;
+    this.modelOptions.user = this.user;
     if (typeof opts.onProgress === 'function') {
       await this.getCompletion(
         payload,
@@ -373,6 +377,64 @@ class OpenAIClient extends BaseClient {
       content: response.text,
     });
   }
+
+  async titleConvo({ text, responseText = '' }) {
+    let title = 'New Chat';
+    const convo = `||>User:
+"${text}"
+||>Response:
+"${JSON.stringify(responseText)}"`;
+
+    const modelOptions = {
+      model: 'gpt-3.5-turbo-0613',
+      temperature: 0.2,
+      presence_penalty: 0,
+      frequency_penalty: 0,
+      max_tokens: 16,
+    };
+
+    const configOptions = {};
+
+    if (this.langchainProxy) {
+      configOptions.basePath = this.langchainProxy;
+    }
+
+    try {
+      const llm = createLLM({
+        modelOptions,
+        configOptions,
+        openAIApiKey: this.apiKey,
+        azure: this.azure,
+      });
+
+      title = await runTitleChain({ llm, text, convo });
+    } catch (e) {
+      console.error(e.message);
+      console.log('There was an issue generating title with LangChain, trying the old method...');
+      modelOptions.model = 'gpt-3.5-turbo';
+      const instructionsPayload = [
+        {
+          role: 'system',
+          content: `Detect user language and write in the same language an extremely concise title for this conversation, which you must accurately detect.
+Write in the detected language. Title in 5 Words or Less. No Punctuation or Quotation. Do not mention the language. All first letters of every word should be capitalized and write the title in User Language only.
+
+${convo}
+
+||>Title:`,
+        },
+      ];
+
+      try {
+        title = (await this.sendPayload(instructionsPayload, { modelOptions })).replaceAll('"', '');
+      } catch (e) {
+        console.error(e);
+        console.log('There was another issue generating the title, see error above.');
+      }
+    }
+
+    console.log('CONVERSATION TITLE', title);
+    return title;
+  }
 }
 
 module.exports = OpenAIClient;