mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-17 17:00:15 +01:00
refactor: Client Classes & Azure OpenAI as a separate Endpoint (#532)
* refactor: start new client classes, test localAi support * feat: create base class, extend chatgpt from base * refactor(BaseClient.js): change userId parameter to user refactor(BaseClient.js): change userId parameter to user feat(OpenAIClient.js): add sendMessage method refactor(OpenAIClient.js): change getConversation method to use user parameter instead of userId refactor(OpenAIClient.js): change saveMessageToDatabase method to use user parameter instead of userId refactor(OpenAIClient.js): change buildPrompt method to use messages parameter instead of orderedMessages feat(index.js): export client classes refactor(askGPTPlugins.js): use req.body.token or process.env.OPENAI_API_KEY as OpenAI API key refactor(index.js): comment out askOpenAI route feat(index.js): add openAI route feat(openAI.js): add new route for OpenAI API requests with support for progress updates and aborting requests. * refactor(BaseClient.js): use optional chaining operator to access messageId property refactor(OpenAIClient.js): use orderedMessages instead of messages to build prompt refactor(OpenAIClient.js): use optional chaining operator to access messageId property refactor(fetch-polyfill.js): remove fetch polyfill refactor(openAI.js): comment out debug option in clientOptions * refactor: update import statements and remove unused imports in several files feat: add getAzureCredentials function to azureUtils module docs: update comments in azureUtils module * refactor(utils): rename migrateConversations to migrateDataToFirstUser for clarity and consistency * feat(chatgpt-client.js): add getAzureCredentials function to retrieve Azure credentials feat(chatgpt-client.js): use getAzureCredentials function to generate reverseProxyUrl feat(OpenAIClient.js): add isChatCompletion property to determine if chat completion model is used feat(OpenAIClient.js): add saveOptions parameter to sendMessage and buildPrompt methods feat(OpenAIClient.js): modify buildPrompt method to handle chat completion model feat(openAI.js): modify endpointOption to include modelOptions instead of individual options refactor(OpenAIClient.js): modify getDelta property to use isChatCompletion property instead of isChatGptModel property refactor(OpenAIClient.js): modify sendMessage method to use saveOptions parameter instead of modelOptions parameter refactor(OpenAIClient.js): modify buildPrompt method to use saveOptions parameter instead of modelOptions parameter refactor(OpenAIClient.js): modify ask method to include endpointOption parameter * chore: delete draft file * refactor(OpenAIClient.js): extract sendCompletion method from sendMessage method for reusability * refactor(BaseClient.js): move sendMessage method to BaseClient class feat(OpenAIClient.js): inherit from BaseClient class and implement necessary methods and properties for OpenAIClient class. * refactor(BaseClient.js): rename getBuildPromptOptions to getBuildMessagesOptions feat(BaseClient.js): add buildMessages method to BaseClient class fix(ChatGPTClient.js): use message.text instead of message.message refactor(ChatGPTClient.js): rename buildPromptBody to buildMessagesBody refactor(ChatGPTClient.js): remove console.debug statement and add debug log for prompt variable refactor(OpenAIClient.js): move setOptions method to the bottom of the class feat(OpenAIClient.js): add support for cl100k_base encoding feat(OpenAIClient.js): add support for unofficial chat GPT models feat(OpenAIClient.js): add support for custom modelOptions feat(OpenAIClient.js): add caching for tokenizers feat(OpenAIClient.js): add freeAndInitializeEncoder method to free and reinitialize tokenizers refactor(OpenAIClient.js): rename getBuildPromptOptions to getBuildMessagesOptions refactor(OpenAIClient.js): rename buildPrompt to buildMessages refactor(OpenAIClient.js): remove endpointOption from ask function arguments in openAI.js * refactor(ChatGPTClient.js, OpenAIClient.js): improve code readability and consistency - In ChatGPTClient.js, update the roleLabel and messageString variables to handle cases where the message object does not have an isCreatedByUser property or a role property with a value of 'user'. - In OpenAIClient.js, rename the freeAndInitializeEncoder method to freeAndResetEncoder to better reflect its functionality. Also, update the method calls to reflect the new name. Additionally, update the getTokenCount method to handle errors by calling the freeAndResetEncoder method instead of the now-renamed freeAndInitializeEncoder method. * refactor(OpenAIClient.js): extract instructions object to a separate variable and add it to payload after formatted messages fix(OpenAIClient.js): handle cases where progressMessage.choices is undefined or empty * refactor(BaseClient.js): extract addInstructions method from sendMessage method feat(OpenAIClient.js): add maxTokensMap object to map maximum tokens for each model refactor(OpenAIClient.js): use addInstructions method in buildMessages method instead of manually building the payload list * refactor(OpenAIClient.js): remove unnecessary condition for modelOptions.model property in buildMessages method * feat(BaseClient.js): add support for token count tracking and context strategy feat(OpenAIClient.js): add support for token count tracking and context strategy feat(Message.js): add tokenCount field to Message schema and updateMessage function * refactor(BaseClient.js): add support for refining messages based on token limit feat(OpenAIClient.js): add support for context refinement strategy refactor(OpenAIClient.js): use context refinement strategy in message sending refactor(server/index.js): improve code readability by breaking long lines * refactor(BaseClient.js): change `remainingContext` to `remainingContextTokens` for clarity feat(BaseClient.js): add `refinePrompt` and `refinePromptTemplate` to handle message refinement feat(BaseClient.js): add `refineMessages` method to refine messages feat(BaseClient.js): add `handleContextStrategy` method to handle context strategy feat(OpenAIClient.js): add `abortController` to `buildPrompt` method options refactor(OpenAIClient.js): change `payload` and `tokenCountMap` to let variables in `handleContextStrategy` method refactor(BaseClient.js): change `remainingContext` to `remainingContextTokens` in `handleContextStrategy` method for consistency refactor(BaseClient.js): change `remainingContext` to `remainingContextTokens` in `getMessagesWithinTokenLimit` method for consistency refactor(BaseClient.js): change `remainingContext` to `remainingContext * chore(openAI.js): comment out contextStrategy option in clientOptions * chore(openAI.js): comment out debug option in clientOptions object * test: BaseClient tests in progress * test: Complete OpenAIClient & BaseClient tests * fix(OpenAIClient.js): remove unnecessary whitespace fix(OpenAIClient.js): remove unused variables and comments fix(OpenAIClient.test.js): combine getTokenCount and freeAndResetEncoder tests * chore(.eslintrc.js): add rule for maximum of 1 empty line feat(ask/openAI.js): add abortMessage utility function fix(ask/openAI.js): handle error and abort message if partial text is less than 2 characters feat(utils/index.js): export abortMessage utility function * test: complete additional tests * feat: Azure OpenAI as a separate endpoint * chore: remove extraneous console logs * fix(azureOpenAI): use chatCompletion endpoint * chore(initializeClient.js): delete initializeClient.js file chore(askOpenAI.js): delete old OpenAI route handler chore(handlers.js): remove trailing whitespace in thought variable assignment * chore(chatgpt-client.js): remove unused chatgpt-client.js file refactor(index.js): remove askClient import and export from index.js * chore(chatgpt-client.tokens.js): update test script for memory usage and encoding performance The test script in `chatgpt-client.tokens.js` has been updated to measure the memory usage and encoding performance of the client. The script now includes information about the initial memory usage, peak memory usage, final memory usage, and memory usage after a timeout. It also provides insights into the number of encoding requests that can be processed per second. The script has been modified to use the `OpenAIClient` class instead of the `ChatGPTClient` class. Additionally, the number of iterations for the encoding loop has been reduced to 10,000. A timeout function has been added to simulate a delay of 15 seconds. After the timeout, the memory usage is measured again. The script now handles uncaught exceptions and logs any errors that occur, except for errors related to failed fetch requests. Note: This is a test script and should not be used in production * feat(FakeClient.js): add a new class `FakeClient` that extends `BaseClient` and implements methods for a fake client feat(FakeClient.js): implement the `setOptions` method to handle options for the fake client feat(FakeClient.js): implement the `initializeFakeClient` function to initialize a fake client with options and fake messages fix(OpenAIClient.js): remove duplicate `maxTokensMap` import and use the one from utils feat(BaseClient): return promptTokens and completionTokens * refactor(gptPlugins): refactor ChatAgent to PluginsClient, which extends OpenAIClient * refactor: client paths * chore(jest.config.js): remove jest.config.js file * fix(PluginController.js): update file path to manifest.json feat(gptPlugins.js): add support for aborting messages refactor(ask/index.js): rename askGPTPlugins to gptPlugins for consistency * fix(BaseClient.js): fix spacing in generateTextStream function signature refactor(BaseClient.js): remove unnecessary push to currentMessages in generateUserMessage function refactor(BaseClient.js): remove unnecessary push to currentMessages in handleStartMethods function refactor(PluginsClient.js): remove unused variables and date formatting in constructor refactor(PluginsClient.js): simplify mapping of pastMessages in getCompletionPayload function * refactor(GoogleClient): GoogleClient now extends BaseClient * chore(.env.example): add AZURE_OPENAI_MODELS variable fix(api/routes/ask/gptPlugins.js): enable Azure integration if PLUGINS_USE_AZURE is true fix(api/routes/endpoints.js): getOpenAIModels function now accepts options, use AZURE_OPENAI_MODELS if PLUGINS_USE_AZURE is true fix(client/components/Endpoints/OpenAI/Settings.jsx): remove console.log statement docs(features/azure.md): add documentation for Azure OpenAI integration and environment variables * fix(e2e:popup): includes the icon + endpoint names in role, name property
This commit is contained in:
Danny Avila
GitHub
parent
10c772c9f2
commit
8819e83d2c
88 changed files with 4257 additions and 10198 deletions
|
|
@ -1,89 +0,0 @@
|
|||
require('dotenv').config();
|
||||
|
||||
const run = async () => {
|
||||
const { ChatGPTClient } = await import('@waylaidwanderer/chatgpt-api');
|
||||
const text = `
|
||||
The standard Lorem Ipsum passage, used since the 1500s
|
||||
|
||||
"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum."
|
||||
Section 1.10.32 of "de Finibus Bonorum et Malorum", written by Cicero in 45 BC
|
||||
|
||||
"Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos qui ratione voluptatem sequi nesciunt. Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam, quis nostrum exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit qui in ea voluptate velit esse quam nihil molestiae consequatur, vel illum qui dolorem eum fugiat quo voluptas nulla pariatur?"
|
||||
1914 translation by H. Rackham
|
||||
|
||||
"But I must explain to you how all this mistaken idea of denouncing pleasure and praising pain was born and I will give you a complete account of the system, and expound the actual teachings of the great explorer of the truth, the master-builder of human happiness. No one rejects, dislikes, or avoids pleasure itself, because it is pleasure, but because those who do not know how to pursue pleasure rationally encounter consequences that are extremely painful. Nor again is there anyone who loves or pursues or desires to obtain pain of itself, because it is pain, but because occasionally circumstances occur in which toil and pain can procure him some great pleasure. To take a trivial example, which of us ever undertakes laborious physical exercise, except to obtain some advantage from it? But who has any right to find fault with a man who chooses to enjoy a pleasure that has no annoying consequences, or one who avoids a pain that produces no resultant pleasure?"
|
||||
Section 1.10.33 of "de Finibus Bonorum et Malorum", written by Cicero in 45 BC
|
||||
|
||||
"At vero eos et accusamus et iusto odio dignissimos ducimus qui blanditiis praesentium voluptatum deleniti atque corrupti quos dolores et quas molestias excepturi sint occaecati cupiditate non provident, similique sunt in culpa qui officia deserunt mollitia animi, id est laborum et dolorum fuga. Et harum quidem rerum facilis est et expedita distinctio. Nam libero tempore, cum soluta nobis est eligendi optio cumque nihil impedit quo minus id quod maxime placeat facere possimus, omnis voluptas assumenda est, omnis dolor repellendus. Temporibus autem quibusdam et aut officiis debitis aut rerum necessitatibus saepe eveniet ut et voluptates repudiandae sint et molestiae non recusandae. Itaque earum rerum hic tenetur a sapiente delectus, ut aut reiciendis voluptatibus maiores alias consequatur aut perferendis doloribus asperiores repellat."
|
||||
1914 translation by H. Rackham
|
||||
|
||||
"On the other hand, we denounce with righteous indignation and dislike men who are so beguiled and demoralized by the charms of pleasure of the moment, so blinded by desire, that they cannot foresee the pain and trouble that are bound to ensue; and equal blame belongs to those who fail in their duty through weakness of will, which is the same as saying through shrinking from toil and pain. These cases are perfectly simple and easy to distinguish. In a free hour, when our power of choice is untrammelled and when nothing prevents our being able to do what we like best, every pleasure is to be welcomed and every pain avoided. But in certain circumstances and owing to the claims of duty or the obligations of business it will frequently occur that pleasures have to be repudiated and annoyances accepted. The wise man therefore always holds in these matters to this principle of selection: he rejects pleasures to secure other greater pleasures, or else he endures pains to avoid worse pains."
|
||||
`;
|
||||
const model = 'gpt-3.5-turbo';
|
||||
const maxContextTokens = model === 'gpt-4' ? 8191 : model === 'gpt-4-32k' ? 32767 : 4095; // 1 less than maximum
|
||||
const clientOptions = {
|
||||
reverseProxyUrl: process.env.OPENAI_REVERSE_PROXY || null,
|
||||
maxContextTokens,
|
||||
modelOptions: {
|
||||
model,
|
||||
},
|
||||
proxy: process.env.PROXY || null,
|
||||
debug: true
|
||||
};
|
||||
|
||||
let apiKey = process.env.OPENAI_API_KEY;
|
||||
|
||||
const maxMemory = 0.05 * 1024 * 1024 * 1024;
|
||||
|
||||
// Calculate initial percentage of memory used
|
||||
const initialMemoryUsage = process.memoryUsage().heapUsed;
|
||||
|
||||
|
||||
function printProgressBar(percentageUsed) {
|
||||
const filledBlocks = Math.round(percentageUsed / 2); // Each block represents 2%
|
||||
const emptyBlocks = 50 - filledBlocks; // Total blocks is 50 (each represents 2%), so the rest are empty
|
||||
const progressBar = '[' + '█'.repeat(filledBlocks) + ' '.repeat(emptyBlocks) + '] ' + percentageUsed.toFixed(2) + '%';
|
||||
console.log(progressBar);
|
||||
}
|
||||
|
||||
const iterations = 16000;
|
||||
console.time('loopTime');
|
||||
// Trying to catch the error doesn't help; all future calls will immediately crash
|
||||
for (let i = 0; i < iterations; i++) {
|
||||
try {
|
||||
console.log(`Iteration ${i}`);
|
||||
const client = new ChatGPTClient(apiKey, clientOptions);
|
||||
|
||||
client.getTokenCount(text);
|
||||
// const encoder = client.constructor.getTokenizer('cl100k_base');
|
||||
// console.log(`Iteration ${i}: call encode()...`);
|
||||
// encoder.encode(text, 'all');
|
||||
// encoder.free();
|
||||
|
||||
const memoryUsageDuringLoop = process.memoryUsage().heapUsed;
|
||||
const percentageUsed = memoryUsageDuringLoop / maxMemory * 100;
|
||||
printProgressBar(percentageUsed);
|
||||
|
||||
if (i === (iterations - 1)) {
|
||||
console.log(' done');
|
||||
// encoder.free();
|
||||
}
|
||||
} catch (e) {
|
||||
console.log(`caught error! in Iteration ${i}`);
|
||||
console.log(e);
|
||||
}
|
||||
}
|
||||
|
||||
console.timeEnd('loopTime');
|
||||
// Calculate final percentage of memory used
|
||||
const finalMemoryUsage = process.memoryUsage().heapUsed;
|
||||
// const finalPercentageUsed = finalMemoryUsage / maxMemory * 100;
|
||||
console.log(`Initial memory usage: ${initialMemoryUsage / 1024 / 1024} megabytes`);
|
||||
console.log(`Final memory usage: ${finalMemoryUsage / 1024 / 1024} megabytes`);
|
||||
setTimeout(() => {
|
||||
const memoryUsageAfterTimeout = process.memoryUsage().heapUsed;
|
||||
console.log(`Post timeout: ${memoryUsageAfterTimeout / 1024 / 1024} megabytes`);
|
||||
} , 10000);
|
||||
}
|
||||
|
||||
run();
|
||||
Loading…
Add table
Add a link
Reference in a new issue