mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-27 21:58:51 +01:00
feat: Plugins endpoint - Reverse Engineering of official Plugins features (#197)
* components for plugins in progress * WIP: add langchain client implementation for tools/plugins feat(langchain): add loadHistory function for loading chat history from database feat(langchain): add saveMessageToDatabase function for saving chat messages to database * chore(Memory.js): remove Memory.js file from the project directory. * WIP: adding plugin functionality —————————————————— fix(eslintrc.js): change arrow-parens rule to always require parentheses refactor(agent.js): reorganize imports and add new imports feat(agent.js): add support for saving and loading chat history feat(agent.js): add support for saving messages to database feat(agent.js): add ChatAgent class with initialize and sendMessage methods fix(langchain): use getConvo and saveMessage functions from models.js instead of Conversation and Message models feat(langchain): add user parameter to loadHistory and saveMessageToDatabase functions chore(package.json): update langchain package version to 0.0.59 and add langchain script to run test2.js file —————————————————— * WIP: testing agent initialization * WIP: testing various agent methods feat(agent.js): add CustomChatAgent class and initializeAgentExecutorWithOptions method feat(customChatAgent.js): add CustomPromptTemplate and CustomOutputParser classes refactor(langchain): uncomment code for input2 and options feat(langchain): add input1 to read comments on a youtube video docs(langchain): remove commented code and add whitespace to package.json * WIP: feat: plugin endpoint, backend class working * feat(agent.js): add support for Zapier NLA API key feat(agent.js): add ZapierToolKit to tools if zapierApiKey is provided feat(customAgent.js): change prompt prefix and suffix to reflect new task-based prompt feat(test4.js): add test for new task-based prompt * style(langchain): improve readability and add comments to code feat(langchain): update prompt message for custom agent fix(langchain): update message format in test4.js * style(customAgent.js): remove unnecessary capitalization and rephrase some sentences test(langchain): add test2 and test3 scripts to package.json * chore(customAgent.js): fix typo in comment, change "an" to "identical" * WIP: gpt-4 testing * feat(langchain): add AIPluginTool and HumanTool classes fix(langchain): remove zapierApiKey option from ChatAgent constructor refactor(langchain): update langchain package to v0.0.64 misc(langchain): update test2, test3, and test4 scripts to use --inspect flag * feat(langchain): add GoogleSearchAPI tool for searching the web using Google Custom Search API * feat(askGPTPlugins.js): add support for progress callback in ask function fix(agent.js): pass progress callback to sendApiMessage function * refactor(agent.js): load tools from options and initialize them in constructor feat(agent.js): add support for environment variable SERPAPI_API_KEY feat(agent.js): add support for environment variable ZAPIER_NLA_API_KEY docs(agent.js): remove commented out code and add comments to clarify code * chore(langchain): remove unused files loadHistory.js and saveMessage.js * feat(validateTools.js): add function to validate API keys for supported tools * feat(langchain): update langchain package to version 0.0.66 feat(langchain): add support for GPT-4 model fix(server/index.js): fix uncaughtException handler to ignore 'fetch failed' errors * refactor(agent.js): remove FORMAT_INSTRUCTIONS and replace with a more concise message refactor(agent.js): remove unused variable 'errorMessage' refactor(agent.js): change 'result' variable initialization to an empty object instead of null refactor(agent.js): change error message when response generation fails refactor(agent.js): change output message when response generation fails refactor(agent.js): change output message when response generation succeeds * chore(langchain): comment out unused model in ChatAgent constructor feat(langchain): add test5 script to package.json for running test5.js script * refactor(agent.js): change response to answer and update message refactor(test3.js, test5.js): remove commented out code and add comments The changes in agent.js are to improve the message that is returned to the user. The word "response" has been changed to "answer" to better reflect the output of the chatbot. The message has also been updated to provide clearer instructions to the user. The changes in test3.js and test5.js are to remove commented out code and add comments to improve readability. * docs: update links to LOCAL_INSTALL.md and defaultSystemMessage.md fix: fix typo in BingAI/Settings.jsx feat: add Dockerfile for app containerization docs(google_search.md): add guide for setting up Google Custom Search API key and ID * docs: update link to system message guidelines in Bing AI Settings component docs: update link to system message guidelines in GOOGLE_SEARCH.md feat: add JAILBREAK_INFO.md guide for Bing AI jailbreak mode system message guidelines * style(api): remove unnecessary quotes and empty values from .env.example style(agent.js): refactor getActions method to accept an input parameter feat(agent.js): add handleChainEnd method to CustomChatAgent class style(customAgent.js): add a new line to the end of the file style(test5.js): comment out unused variable and update input1 variable style(googleSearch.js): change tool name to kebab-case * chore(langchain): comment out handleChainEnd method in agent.js feat(langchain): add browser tool to ChatAgent in test2.js feat(langchain): add modelOptions to ChatAgent in test2.js feat(langchain): change question in input1 and request article review summary in test5.js * fix(askGPTPlugins.js): fix syntax error by removing extra comma in parentMessageId field feat(askGPTPlugins.js): add default value of null to parentMessageId parameter in ask function * fix(askGPTPlugins.js): change endpoint string from 'GPTPlugins' to 'gptPlugins' feat(endpoints.js): add support for gptPlugins endpoint feat(PresetItem.jsx): add support for gptPlugins endpoint feat(HoverButtons.jsx): add support for gptPlugins endpoint feat(createPayload.ts): add support for gptPlugins endpoint feat(types.ts): add gptPlugins endpoint to EModelEndpoint enum feat(endpoints.js): add gptPlugins endpoint to availableEndpoints selector feat(cleanupPreset.js): add support for gptPlugins endpoint feat(getDefaultConversation.js): add support for gptPlugins endpoint feat(getIcon.jsx): add support for gptPlugins endpoint feat(handleSubmit.js): add support for gptPlugins endpoint * refactor(agent.js): remove debug option from options object refactor(agent.js): change tool name from 'google-search' to 'google' refactor(agent.js): update description for 'google' tool feat(agent.js): add support for citing sources when using web links in response message fix(agent.js): update error message to not mention error to user feat(agent.js): add unique message ids for user message and response message feat(agent.js): limit number of search results to 5 in 'google' tool refactor(validateTools.js): add console log to show valid tools * feat(askGPTPlugins.js): add support for GPT-3.5-turbo model and validate model option refactor(askGPTPlugins.js): remove unused imports and variables refactor(askGPTPlugins.js): remove commented code refactor(askGPTPlugins.js): remove unused parameters in ask function feat(ask/index.js): add askGPTPlugins route to router * feat(NewConversationMenu): add alpha tag to gptPlugins endpoint and rename it to Plugins * refactor(askGPTPlugins.js): remove commented code and unused imports feat(askGPTPlugins.js): add support for debug option in endpointOption feat(askGPTPlugins.js): add support for chatGptLabel, promptPrefix, temperature, top_p, presence_penalty, and frequency_penalty in endpointOption feat(askGPTPlugins.js): add support for sending plugin and pluginend events feat(askGPTPlugins.js): add onAgentAction and onChainEnd callbacks to ChatAgent.sendMessage refactor(titleConvo.js): comment out unused imports refactor(validateTools.js): comment out console.log statement refactor(agent.js): change saveMessage to include unfinished property feat(agent.js): add endpoint property to saveConvo call in saveMessageToDatabase feat(askGPTPlugins.js): add validateTools import and use it to validate endpointOption.tools before passing to ChatAgent constructor feat(askGPTPlugins.js * refactor(MessageHeader.jsx): extract plugins section into a separate variable and add support for gptPlugins endpoint fix(MessageHeader.jsx): disable clicking on non-clickable endpoints * components for plugins in progress * feat(Plugin.jsx): add plugin prop to Plugin component and display plugin name feat(Plugin.jsx): add loading state and display loading spinner feat(Plugin.jsx): add Disclosure component to Plugin component feat(Plugin.jsx): add Disclosure.Panel to Plugin component to display team pricing information feat(Spinner.jsx): add classProp prop to Spinner component to allow for custom styling feat(Landing.jsx): add Plugin component to Landing page for testing testing gpt plugins feat(plugins): Milestone commit - Add formatAction function to format plugin actions. - Add prefix.js file to store the prefix message for ChatAgent. - Update ask function to include plugin object to store plugin data. - Update onAgentAction and onChainEnd functions to format plugin data and send intermediate messages. - Update response object to include plugin data. The `handlers.js` file now includes a `formatAction` function that formats the action object for display in the UI. The `createOnProgress` function now returns a `sendIntermediateMessage` function that sends intermediate messages to the client. feat (client): add support for plugins in messages This commit adds support for plugins in messages. It includes changes to the `handlers.js`, `index.jsx`, `CodeBlock.jsx`, `Message.jsx`, `MessageHeader.jsx`, and `Plugin.jsx` files. The `index.jsx` file now includes a `plugin` property in the `messageHandler` function. The `CodeBlock.jsx` file now includes a `plugin` property that determines the language of the code block. The `Message.jsx` file now includes a `Plugin` component that displays the plugin used in the message. The `MessageHeader.jsx` file now includes a `Plugins` component that displays the enabled plugins. feat(langchain): add OpenAICreateImage tool for generating images based on user prompts fix(langchain): update validateTools to include create-image tool fix(langchain): save plugin data to messageSchema fix(server/routes/askGPTPlugins.js): save userMessage and response to messageSchema feat(langchain): add SelfReflectionTool Add a new tool to the LangChain agent, SelfReflectionTool, which enhances the agent's self-awareness by reflecting on its thoughts before taking action. The tool provides a space for the agent to explore and organize its ideas in response to the user's message. Also, update the prefix message to reflect the changes in the agent's behavior and the way it should engage with the user. The prefix message now emphasizes the use of tools when necessary, and relying on the agent's knowledge for creative requests. It also provides clear instructions on how to use the 'Action' input and how to carry out tasks in the sequence written by the human. Finally, update the OpenAICreateImage tool to return the image URL in markdown format. The tool replaces newlines and spaces in the input text with hyphens to create a valid markdown link. Milestone commit: better error handling with custom output parser, dir and file re-org style(langchain): fix formatting and add comments to prefix.js fix(langchain): remove commented out code in test6.js feat(langchain): reduce maxAttempts from 3 to 2 in CustomChatAgent's buildPromptPrefix method feat(langchain): add null check for result.output in CustomChatAgent's buildPromptPrefix method style(langchain): improve consistency and readability of code This commit improves the consistency and readability of the code in the langchain directory. Specifically, it: - Changes the case of the "Thought" output in the CustomChatAgent class to match the "Thought" output in the SelfReflectionTool class. - Adds a currentDateString property to the CustomChatAgent class to avoid repeating the same code in multiple places. - Updates the prefix in the prefix.js file to match the current objectives of the ChatGPT model. - Changes the description of the OpenAICreateImage tool to request a description of the image to be generated. - Updates the tools used by the ChatAgent in the askGPTPlugins.js file to include the Google and Browser tools instead of the Calculator and Create-Image tools. feat: add wolfram, improve image creation, rename to dall-e * refactor(langchain): update language and formatting in various files - Update tool-based instructions to use proper Markdown syntax for image URLs - Adjust temperature for modelOptions in CustomChatAgent class - Comment out console.debug statement in CustomChatAgent class - Update prefix in initializeCustomAgent function to use proper line breaks - Update prefix in instructions.js to use proper line breaks and change "user" to "human" - Update input in test6.js to use Ezra Pound instead of Hemingway - Update return statement in OpenAICreateImage class to use "generated-image" as alt-text - Update description in SelfReflectionTool class to provide clearer instructions - Update tools in ask function in askGPTPlugins.js to use only the DALL-E tool and enable debug mode feat(ask): add support for DALL-E tool in formatAction function feat(ask): add support for self-reflection tool in formatAction function feat(Plugin.jsx): add support for self-reflection tool in Plugin component fix(Plugin.jsx): fix Plugin component to not display 'None' when latest is not available * docs(openaiCreateImage.js): update tool description to clarify usage * feat(agent.js): add message parameter to initialize function feat(agent.js): pass message parameter to SelfReflectionTool constructor feat(customAgent.js): add longestToolName variable to CustomOutputParser feat(openaiCreateImage.js): replace new lines with spaces in prompt parameter feat(selfReflection.js): add message parameter to SelfReflectionTool constructor feat(selfReflection.js): add placeholder response to selfReflect function * feat: frontend plugin selection * fix: agent updates, available tools via endpoint config * fix: improve frontend plugin selection * feat: further customize agent and bypass executor when no tools are provided * fix: key issue in multiselect and allow setting changes during convo in plugins endpoint * fix: convo will save modelOptions, fix persistent errors with agent * fix: add looser final answer parsing and edit action formatting * fix: handle edge case where stop token is not hit and causes long parsing error * feat: trying new prompt for image creation * fix: improvements based on gpt-3.5 * feat: allow setting model options throughout plugin conversation * fix: agent adjustments * improve final reply for gpt-4, gpt-3.5 needs a more stable approach * fix: better context output for gpt-3.5 * fix: added clarification for better context output for gpt-3.5 * feat(PluginsOptions): add advanced mode to show/hide options style(PluginsOptions): add styles for advanced mode and show/hide options * minor changes to styling * refactor(langchain): add support for custom GPT-4 agent This commit adds support for a custom GPT-4 agent in the langchain module. The `CustomGpt4Agent` class extends the `ZeroShotAgent` class and includes a new `createPrompt` method that generates a prompt template for the agent. The `initializeCustomAgent` function has been updated to use the `CustomGpt4Agent` class when the model is not GPT-3. The `instructions.js` file has also been updated to include new instructions for the GPT-4 agent. The `formatInstructions` method has been removed and replaced with `gpt4Instructions` and `prefix2` and `suffix2` have been added to include the new instructions. feat(langchain): add custom output parser for langchain agents This commit adds a custom output parser for langchain agents. The new parser is called CustomOutputParser and it extends ZeroShotAgentOutputParser. It takes a fields object as a parameter and sets the tools and longestToolName properties. It also sets the finishToolNameRegex property to match the final answer. The parse method of the CustomOutputParser class takes a text parameter and returns an object with returnValues, log, and toolInput properties. This commit also adds a Gpt4OutputParser class that extends ZeroShotAgentOutputParser. It takes a fields object as a parameter and sets the tools and longestToolName properties. It also sets the finishToolNameRegex property to match the final answer. The parse method of the Gpt4OutputParser class takes a text parameter and returns an object with returnValues, log, and toolInput properties. feat(langchain): add isGpt3 parameter to * Stable Diffusion Plugin (#204) * Added stable diffusion plugin * Added example prompt * Fixed naming * Removed brackets in the prompt * fix: improved agent for gpt-3.5 * fix: outparser, gpt3 instructions, and wolfram error handling * chore: update langchain to 0.0.71 * fix: long parsing action input fix * fix: make plugin select close on clicking label/button * fix: make plugin select close on clicking label/button * fix: wolfram input formatting and gpt-3 payload without plugins * chore(api): update axios package version to 1.3.4 feat(api): add requireJwtAuth middleware to askGPTPlugins endpoint fix(api): replace session user with user id in askGPTPlugins endpoint docs(LOCAL_INSTALL.md): update guide for local installation and testing This commit updates the guide for local installation and testing of the ChatGPT-Clone app. It includes instructions for locally running the app, updating the app version, and running tests. It also includes a new option for running the app using Docker. The commit also fixes some typos and formatting issues. * add reverseProxy to plugins client * chore(Dockerfile-app): add Dockerfile for building and running the app in a container docs: remove outdated guides on Google search and Bing jailbreak mode docs(LOCAL_INSTALL.md): remove outdated Windows installation instructions and update MeiliSearch configuration file * fix: handle n/a parsing error better, reduce token waste if no agentic behavior is needed * style: fix formatting and add parentheses around arrow function parameter style: change hover background color to white and dark hover background color to gray-700 * chore: re-organize agent dir and files * feat(ChatAgent.js): add support for PlanAndExecuteAgentExecutor feat(PlanAndExecuteAgentExecutor.js): add PlanAndExecuteAgentExecutor class feat(planExecutor.js): add demo for PlanAndExecuteAgentExecutor * feat: add azure support to plugins * refactor(utils): add basePath endpoint for genAzureEndpoint feat(api): add support for Azure OpenAI API in various modules and tools * feat: add plugin api for fetching available tools * feat: add data service for getting available plugins * feat: first iteration plugin store UI * refactor: rename files to follow proper naming convention * feat: Plugin store UI components * feat: create separate user routes, service, controller, and add plugins to user model * feat: create data service for adding and removing plugins per user * feat: UI for adding and removing plugins, displaying plugins in dropdown based on what user has installed * fix: merge conflicts from main * fix: fix plugin items titles * fix: tool.value -> tool.pluginKey * fix: testing returnDirect for self-reflection * fix: add browser tool to manifest * refactor(outputParser.js): remove commented out code feat(outputParser.js): add support for thought input when there is no action input * handling 'use tool' edge case * merge main to langchain * fix(User.js, auth.service.js, localStrategy.js): change deprecated Joi.validate() to schema.validate() method (#322) * fix(auth.service.js): fixes deprecated error callback in mongoose save method (#323) * chore: run formatting script with new rules * refactor: add requiresAuth to manifest, fix uninstall button * version with plugin auth as dialog modal * feat: Complete frontend for plugin auth * frontend styling updates * feat: api for plugin auth * feat: Add tooltip with field description to plugin auth form * fix: issue with plugin that has no auth * feat(tools): add support for user-specific API keys This commit adds support for user-specific API keys for the following tools: - Google Search API - Web Browser - SerpAPI - Zapier - DALL-E - Wolfram Alpha API It also adds support for OpenAI API key for the Web Browser tool. The `validateTools` function now takes a `user` parameter and checks for user-specific API keys before falling back to environment variables. The `loadTools` function now takes a `user` parameter and initializes the tools with user-specific API keys if available. The `manifest.json` file has been updated to include the new `authConfig` fields for the tools that support user-specific API keys. The `askGPTPlugins.js` file has been updated to use the `validateTools` function with the `user` parameter. refactor(ChatAgent.js): add user parameter to initialize function and pass it to loadTools function refactor(tools/index.js): set default value for tools parameter in validateTools function refactor(askGPTPlugins.js): remove duplicate user variable declaration and use the one from req object * refactor(ChatAgent.js): await validTool() before pushing to this.tools array refactor(tools/index.js): use Map instead of Set to store valid tools refactor(tools/index.js): filter availableTools to only validate tools passed in refactor(PluginController.js): filter out duplicate plugins by pluginKey refactor(crypto.js): use environment variables for encryption key and initialization vector feat(PluginService.js): add null check for pluginAuth in getUserPluginAuthValue() * feat(api): add credentials key and IV to .env.example for securely storing credentials * Adds testing for handling tools, introducing a test env to the backend Fixes bugs & optimizes code as revealed through testing, including: - wolfram.js: fixes bug where wolfram was not handling authentication - ChatAgent.js: ChatAgent modified to reflect 'handleTools' changes - handleTools.js: Moves logic out of index file - handleTools.js: loadTools: returns only requested tools - handleTools.js: validTools: correctly returns tools based on authentication * test(index.test.js): add test to validate a tool from an environment variable * test(tools): add test for initializing an authenticated tool through Environment Variables * refactor(ChatAgent.js): remove commented out code and unused imports * refactor(ChatAgent.js): move instructions to a separate file and import them fix(ChatAgent.js): replace hardcoded instructions with imported ones * refactor(ChatAgent.js): change import path for TextStream refactor(stream.js): remove unused TextStream class * chore(.gitignore): add .env.test to gitignore refactor(ChatAgent.js): rename CustomChatAgent to ChatAgent test(ChatAgent.test.js): add tests for ChatAgent class refactor(outputParser.js): remove OldOutputParser class refactor(outputParser.js): rename CustomOutputParser to OutputParser docs(.env.test.example): add comment explaining how to use OPENAI_API_KEY refactor(jestSetup.js): use dotenv to load environment variables from .env.test file * Various optimizations and config, add tests for PluginStoreDialog * test(ChatAgent.test.js): add test to check if chat history is returned correctly * test: unit tests for plugin store * test: add frontend-test script to root package.json * feat(ChatAgent.js, askGPTPlugins.js): add support for aborting chat requests (in progress) * test: add more client tests * feat(ChatAgent): allow plugin requests to be cancelled * feat(ChatAgent): allow message regeneration * feat(ChatAgent): remember last selected tools * Remove plugins we don't yet have from manifest.json * fix(ChatAgent.js): increase maxAttempts from 1 to 2 fix(ChatAgent.js): change error message to 'Cancelled.' if message was aborted mid-generation fix(openaiCreateImage.js): replace unwanted characters in input string fix(handlers.js): compare action.tool in lowercase to 'self-reflection' * fix(ChatAgent): Fix up plugin I/O formatting for n/a actions * refactor(Plugin.jsx): remove unused import statement feat(Plugin.jsx): add Plugin component with svg paths and styles * refactor: simplify credential encryption/decryption by using a single key and IV for all environments. Update crypto.js and .env.example files accordingly. * fix(ChatAgent.js): reduce maxAttempts from 2 to 1 feat(ChatAgent.js): add model information to responseMessage object feat(Message.js): add model field to messageSchema feat(Message.js): add model field to message object feat(Message.jsx): pass model information to getIcon function feat(getIcon.jsx): add Plugin component and handle plugin messages differently * feat(askGPTPlugins.js): add model property to the ask function response object feat(EndpointItem.jsx): add message property to the EndpointItem component feat(MessageHeader.jsx): add Plugin icon to the plugins section feat(MessageHeader.jsx): change alpha to beta in the plugins section feat(svg): add Plugin, GPTIcon, and BingIcon components to the svg folder refactor(EndpointItems.jsx): remove unused import statement * refactor(googleSearch.js, wolfram.js): change error handling to return a message instead of throwing an error * refactor(CustomAgent): remove commented code and change return object to include returnValues property * feat(CustomAgent.js): add currentDateString to createPrompt method options deps(api/package.json): update langchain to v0.0.81 * fix: do not show pagination if the maxPage is 1 * Add Zapier back to manifest (accidentally removed) * chore(api): update langchain dependency to version 0.0.84 * feat(DALL-E.js): add DALL-E tool for generating images using OpenAI's DALL-E API refactor(handleTools.js): update import for DALL-E tool refactor(index.test.js): update import for DALL-E tool refactor(stablediffusion.js): add check for image directory existence before saving image * refactor(CustomAgent): rename instructions prefix variable to gpt3 and add gpt4 instructions feat(CustomAgent): add support for gpt-4 model fix(initializeCustomAgent.js): pass model name to createPrompt method fix(outputParser.js): set selectedTool to 'self-reflection' when tool parsing fails * style(langchain/tools): update guidelines for image creation in DALL-E and StableDiffusion - Update guidelines for image creation in DALL-E and StableDiffusion tools - Emphasize the importance of "showing" and not "telling" the imagery in crafting input - Update formatting for the example prompt for generating a realistic portrait photo of a man - Generate images only once per human query unless explicitly requested by the user * docs(tools): update tool descriptions for DALL-E and Stable Diffusion - Update the description for DALL-E tool to indicate that it is exclusively for visual content and provide guidelines for generating images with a focus on visual attributes. - Update the description for Stable Diffusion tool to indicate that it is exclusively for visual content and provide guidelines for generating images with a focus on visual attributes. * chore(api): update "@waylaidwanderer/chatgpt-api" dependency to version "^1.36.3" * refactor(ChatAgent.js): use environment variable for reverse proxy url refactor(ChatAgent.js): use environment variable for openai base path refactor(instructions.js): update gpt3 and gpt3-v2 instructions refactor(outputParser.js): update finishToolNameRegex in CustomOutputParser class * refactor(DALL-E.js): change apiKey and azureKey fields to uppercase refactor(googleSearch.js): change cx and apiKey fields to uppercase feat(manifest.json): add authConfig field for Stable Diffusion WebUI API URL refactor(stablediffusion.js): add url field to constructor and change getServerURL() to this.url refactor(wolfram.js): change apiKey field to uppercase WOLFRAM_APP_ID * refactor(handleTools.js): simplify tool loading and add support for custom tool constructors and options * refactor(handleTools.js): remove commented out code and unused imports * refactor(handleTools.js, index.js): change file name from wolfram.js to Wolfram.js and selfReflection.js to SelfReflection.js to follow PascalCase convention * refactor(outputParser.js, askGPTPlugins.js): improve code readability and remove unnecessary comments * feat(GoogleSearch.js): add GoogleSearchAPI tool to allow agents to use the Google Custom Search API feat(SelfReflection.js): add SelfReflectionTool to allow agents to reflect on their thoughts and actions feat(StableDiffusion.js): add StableDiffusionAPI tool to allow agents to generate images using stable diffusion webui's api feat(Wolfram.js): add WolframAlphaAPI tool for computation, math, curated knowledge & real-time data through WolframAlpha. * testing openai specs * doc: fix link in .env.example * package-update * fix(MultiSelectDropDown.jsx): handle null or undefined values in availableValues array * refactor(DALL-E.js, StableDiffusion.js): remove 'dist/' from image path feat(docker-compose.yml): add comments for reverse proxy configuration * chore(.gitignore): ignore client/public/images/ fix(DALL-E.js, StableDiffusion.js): change image path from dist/ to public/ feat(index.js): add support for serving static files from client/public/ directory * fix: remove selected tool when uninstalled * plugin options in progress * fix: fix issue with uninstalling a plugin that is in use and typescript errors * feat(gptPlugins): add Preset support for GPT Plugins endpoint feat(ChatAgent.js): add support for agentOptions object feat(convoSchema.js): add agentOptions field to conversation schema feat(defaults.js): add agentOptions object to defaults feat(presetSchema.js): add agentOptions field to preset schema feat(askGPTPlugins.js): add support for agentOptions object in request body feat(EditPresetDialog.jsx): add support for showing/hiding GPT Plugins agent settings feat(EditPresetDialog.jsx): add support for setting GPT Plugins agent options fix(EndpointOptionsDialog.jsx): change endpoint name from 'gptPlugins' to 'Plugins' feat(AgentSettings.jsx): add AgentSettings component for GPT plugins configuration feat(client): add GPT Plugins settings component and endpoint to Settings component fix(client): remove unused imports in GoogleOptions component feat(PluginsOptions): add support for agent settings and refactor code feat(PluginsOptions): add GPTIcon to show/hide agent settings button feat(index.ts): export SVG components feat(GPTIcon.jsx): add className prop to GPTIcon component feat(GPTIcon.jsx): import cn function from utils feat(BingIcon.tsx): export BingIcon component feat(index.ts): export BingIcon component feat(index.ts): export MessagesSquared component refactor(cleanupPreset.js): add default values for agentOptions in gptPlugins endpoint feat(getDefaultConversation.js, handleSubmit.js): add agentOptions object to conversation object for GPT plugins endpoint. Update default temperature value to 0.8. Add chatGptLabel and promptPrefix properties to conversation object. * fix: set default convo back to null * refactor(ChatAgent.js, askGPTPlugins.js, AgentSettings.jsx): change variable names for better readability and remove redundant code * test: add RecoilRoot to layout-test-utils * refactor(askGPTPlugins.js): remove redundant code and use endpointOption directly feat(askGPTPlugins.js): add validation for tools in endpointOption before using it * chore(ChatAgent.js, Settings.jsx): add agentOptions to saveConvo function and adjust Settings component height The ChatAgent.js file was modified to include the agentOptions object in the saveConvo function. The Settings.jsx file was modified to adjust the height of the component to ensure that all content is visible. * refactor(ChatAgent.js): extract reverseProxyUrl option to a class property and add support for it feat(ChatAgent.js): add support for completionMode option in sendApiMessage method feat(ChatAgent.js): add support for user-provided promptPrefix in buildPrompt method * feat(plugins): allow preset change mid conversation * chore: update OPENAI_KEY to OPENAI_API_KEY in .github/playwright.yml and api/.env.example refactor(chatgpt-client.js): update OPENAI_KEY to OPENAI_API_KEY feat(langchain): add demo-aiplugin.js and demo-yaml.js, remove test2.js, test3.js, and test4.js chore: remove unused test files fix(titleConvo.js): fix typo in environment variable name fix(askGPTPlugins.js): fix typo in environment variable name fix(endpoints.js): fix typo in environment variable name docs: update installation guide to use OPENAI_API_KEY instead of OPENAI_KEY in .env file * fix(index.test.js): change import of GoogleSearchAPI to use uppercase G in GoogleSearch * chore(api): bump langchain version * feat(PluginController.js): authenticate plugins from environment variables if they are set feat(PluginStoreDialog.tsx): show plugin auth form only if plugin is not authenticated by env var and require authentication feat(types.ts): add authenticated field to TPlugin type definition * docs: update google_search.md and add stable_diffusion.md * Update stable_diffusion.md * refactor(Wolfram.js): remove newline characters from query before encoding docs(wolfram.md): add instructions for setting WOLFRAM_APP_ID in api.env to bypass prompt for AppID in plugin * refactor(Wolfram.js): replace deprecated replaceAll method with replace method * Update wolfram.md * fix(askGPTPlugins): error message will reference correct Parent Message * refactor(chatgpt-client.js, ChatAgent.js): simplify maxContextTokens calculation and add promptPrefix parameter to buildPrompt method * docs: initial draft of intro to plugins * Update introduction.md * Update introduction.md * Feature: User/Reg cleanup + Install / Upgrade script for langchain (#427) * test: login tests * test: finish login tests * test: initial tests for registration * test: registration specs * feature: Init a app config file - Simplifies the ENV vars too - Legacy fallbacks for older builds * refactor(auth): Refactor log in/out controllers - Moves both login and logout controllers to their own file * chore(jwt): Throw warning if secret is default * feature(frontend): Ability to disable registration * feature(env): Env in the root + version support ie .env.prod, .env.dev, .env.test * feature: Upgrade .env script for users * chore(config): Refactor and remove legacy env refs * feature(upgrade): Upgrade script for .env changes * feature: Install script and upgrade script * bugfix: Uncomment line to remove old .env file * chore: rename OPENAI_KEY to OPENAI_API_KEY * chore: Cleanup config changes/bugs * bugfix: Fix config and node env issues * bugfix: Config validation logic * bugfix: Handle unusual env configs gracefully * bugfix: Revert route changes and fix registration disable calling * bugfix: Fix env issues in frontend * bugfix: Fix login * bugfix: Fix frontend envs * bugfix: Fix frontend jest tests * bugfix: Fix upgrade scripts * bugfix: Allow install in non-tty envs * bugfix(windows): Use cross-env to set for windows * bugfix(env): Handle .env being incorrect to begin with for client domain * chore(merge-conflict): Update to LibreChat * chore(merge-conflict): Update to package-lock --------- Co-authored-by: Daniel D Orlando <dan@danorlando.com> * chore: comment out unused agent options * Update langchain plugins docs (#461) * Update: install docs (LibreChat) (#458) * Release: rename project from ChatGPT Clone to LibreChat Release: rename project from ChatGPT Clone to LibreChat * Release: rename project from ChatGPT Clone to LibreChat Release: rename project from ChatGPT Clone to LibreChat * Release: rename project from ChatGPT Clone to LibreChat Release: rename project from ChatGPT Clone to LibreChat * Release: rename project from ChatGPT Clone to LibreChat Release: rename project from ChatGPT Clone to LibreChat * Update documentation_guidelines.md * Update introduction.md add link to readme * Update stable_diffusion.md add link back to readme * Update wolfram.md add link back to readme * Update README.md add Plugins to ToC * feat(ChatAgent.js): add support for langchainProxy configuration option Add a new configuration option `langchainProxy` to the ChatAgent class. If the option is set, the `basePath` configuration option of the `ChatOpenAI` instance is set to the base path of `langchainProxy`. * bugfix(errors): Possible workaround for error flashing (#463) * Test/user auth system client tests (#462) * test: login tests * test: finish login tests * test: initial tests for registration * test: registration specs * chore(api): update langchain dependency to version 0.0.91 * Update introduction.md * Update introduction.md * Update introduction.md * fix: no longer renders html in markdown content fix: patch XSS vulnerability completely by handling cursor on the frontend without css/html * fix(Content.jsx): fix cursor logic so it never shows for static messages * bugfix(langchain): Upgrade script, docker, env and docs (#465) * bugfix(errors): Remove incorrect manual fix from misunderstanding * chore(env): Lets not make a .env.prod and use the prod values in the default root .env - .env.dev will still be created * chore(upgrade.js): Lets tell the user about .env.dev if we create it * bugfix(env): Move to full name environments for vite - .env.prod => .env.production - .env.dev => .env.development * chore(env-example): Explain how to get google login working in production * bugfix(oauth): Minor fix to point isProduction to a correct value * bugfix: Typo in public * chore(docs): Update docs to note the changes to .env * chore(docs): Include note on how to get google auth working in dev and how to disable registration * bugfix: Fix missing env changes * bugfix: Fix up docker to work with new env / npm changes * Update .env.example Cleanup the env of the palm2 instruction and fix to formating * chore(docker): Simplify Docker deployments - Needs work to support dev env/hotreload * bugfix: Remove volume map for client dir * chore(env-example): Change instructions to be more user centric --------- Co-authored-by: Fuegovic <32828263+fuegovic@users.noreply.github.com> * update: install docs (#466) * Add files via upload * Update apis-and-tokens.md * Update apis-and-tokens.md * Update docker_install.md * Update linux_install.md * Rename apis-and-tokens.md to apis_and_tokens.md * Update docker_install.md * Update linux_install.md * Update mac_install.md * Update linux_install.md * Update docker_install.md * Update windows_install.md * Update apis_and_tokens.md * Update mac_install.md * Update linux_install.md * Update docker_install.md * Update README.md * Update README.md : Breaking Changes --------- Co-authored-by: Danny Avila <110412045+danny-avila@users.noreply.github.com> * Update README.md (#468) add new API/Token docs to Toc * docs: guide on how to create your own plugin * Update make_your_own.md * Update make_your_own.md * feat(docker): add build args for frontend variables in Dockerfile feat(docker-compose): add build args for frontend variables in docker-compose.yml * Update docker_install.md * Update docker_install.md * Update docker_install.md * Update docker_install.md * docs: update (#469) * Update: make_your_own.md * Update README.md add `make_your_own.md` to ToC * Update linux_install.md * Update mac_install.md * Update windows_install.md * Update apis_and_tokens.md * Update docker_install.md * Update docker_install.md * Update linux_install.md * Update mac_install.md * Update windows_install.md * Update apis_and_tokens.md * Update user_auth_system.md * Update docker_install.md clean up of repeated information * Update docker_install.md * Update docker_install.md typo * fix: fix issue with pluginstore next and prev buttons going out of bounds * fix: add icon for web browser plugin * docs(GoogleSearch.js): update description of GoogleSearchAPI class to be more descriptive of its functionality * feat(ask/handlers.js): add cursor to indicate ongoing progress of a long-running task fix(Content.jsx): handle null content in the message stream by replacing it with an empty string (with a space so a text space is rendered) * Update README.md * Update README.md * fix: plugin option stacking order * update: web browser icon (#470) * Delete web-browser.png * update: web browser icon * Update readme (#472) * Update README.md Discord badge now displays the number of online users Project description has been updated to reflect current status Feature section has been updated to reflect current capabilities Sponsors section is now located just above the contributors section Roadmap has been removed as it was outdated. * Delete roadmap.md Roadmap has been removed to streamline document maintenance. * Update README.md * Update README.md * Delete CHANGELOG.md * fix: pluginstore in mobile view getting clipped and not scrolling * docs(linux_install.md): remove duplicate git clone command * chore(Dockerfile): comment out nginx-client build stage docs(README.md): update installation instructions and mention docker-compose changes docs(features/plugins/introduction.md): bold plugin names and add emphasis to notes * feat: add superscript and subscript support to markdown rendering refactor: support markdown citations for BingAI * refactor: support markdown citations for BingAI --------- Co-authored-by: David Shin <42793498+dncc89@users.noreply.github.com> Co-authored-by: Daniel D Orlando <dan@danorlando.com> Co-authored-by: LaraClara <2524209+ClaraLeigh@users.noreply.github.com> Co-authored-by: Fuegovic <32828263+fuegovic@users.noreply.github.com>
This commit is contained in:
Danny Avila
GitHub
parent
aaa20309a0
commit
e4c91dfbea
194 changed files with 19251 additions and 5744 deletions
|
|
@ -1,5 +1,5 @@
|
|||
# AI-Assisted Google Search
|
||||
This bot supports searching google for answers to your questions with assistance from GPT! To get started, you need to get a Google Custom Search API key, and a Google Custom Search Engine ID. You can then define these as follows in your `.env` file:
|
||||
# Google Search Plugin
|
||||
Through the plugins endpoint, you can use google search for answers to your questions with assistance from GPT! To get started, you need to get a Google Custom Search API key, and a Google Custom Search Engine ID. You can then define these as follows in your `.env` file:
|
||||
```env
|
||||
GOOGLE_API_KEY="...."
|
||||
GOOGLE_CSE_ID="...."
|
||||
|
|
|
|||
77
docs/features/plugins/introduction.md
Normal file
77
docs/features/plugins/introduction.md
Normal file
|
|
@ -0,0 +1,77 @@
|
|||
# Plugins Endpoint
|
||||
|
||||
|
||||
|
||||
The plugins endpoint opens the door to prompting LLMs in new ways other than traditional input/output prompting.
|
||||
|
||||
The first step is using chain-of-thought prompting for using plugins/tools in a fashion mimicing the official ChatGPT Plugins feature.
|
||||
|
||||
More than this, you can use this endpoint for changing your conversation settings mid-conversation. Unlike the official ChatGPT site and all other endpoints, you can switch models, presets, and settings mid-convo, even when you have no plugins selected. This is useful if you first want a creative response from GPT-4, and then a deterministic, lower cost response from GPT-3. Soon, you will be able to use PaLM2 and HuggingFace models, all in this endpoint in the same modular manner.
|
||||
|
||||
### Roadmap:
|
||||
- More plugins and advanced plugin usage
|
||||
- More LLMs to choose from for both Thinking and Completion Phases
|
||||
- Alternative prompting methods such as Tree-of-Thought
|
||||
|
||||
## Using Plugins
|
||||
|
||||
The LLM process when using Plugins is illustrated below.
|
||||
|
||||
|
||||
|
||||
**When you open the settings with the Plugins endpoint selected, you will view the default settings for the Completion Phase.**
|
||||
|
||||
Clicking on **"Show Agent Settings"** will allow you to modify parameters for the thinking phase
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
- You can specify which plugins you would like to select from by installing/uninstalling them in the Plugin store
|
||||
- See this guide on how to create your own plugins (WIP)
|
||||
- ChatGPT Plugins, both community-made and official versions, will be available for use in a future update
|
||||
|
||||
### Notes
|
||||
- Every additional plugin selected will increase your token usage as there are detailed instructions the LLM needs for each one
|
||||
- For best use, be selective with plugins per message and narrow your requests as much as possible
|
||||
- If you need help coming up with a good plugin prompt, ask the LLM for suggestions before using one!
|
||||
- Chain-of-thought prompting (plugin use) will always be more expensive than regular input/output prompting, so be sure it meets your need.
|
||||
- Currently, the cheapest use will be to use gpt-3.5 for both phases
|
||||
- From my testing, the best "bang for your buck" will be to use gpt-3.5 for the thinking phase, and gpt-4 for completion.
|
||||
- Adding to above, if you ask for a poem and an image at the same time, it may work, but both may suffer in quality
|
||||
- Instead, ask for a poem first with creative settings
|
||||
- Then, ask for a good prompt for Stable Diffusion based on the poem
|
||||
- Finally, use the Stable Diffusion plugin by referencing the pre-generated prompt
|
||||
- Presets are only available when no Plugins are selected as the final review of the thinking phase has a specific system message.
|
||||
- ⚠️ The **Browser/Scraper, Serpapi, and Zapier NLA plugins** are official langchain integrations and don't work the best. Improvements to them will be made
|
||||
|
||||
### Plugins Setup Instructions
|
||||
- **[Google Search](./google_search.md)**
|
||||
- **[Stable Diffusion](./stable_diffusion.md)**
|
||||
- **[Wolfram](./wolfram.md)**
|
||||
- **DALL-E** - same setup as above, you just need an OpenAI key, and it's made distinct from your main API key to make Chats but it can be the same one
|
||||
- **Zapier** - You need a Zapier account. Get your [API key from here](https://nla.zapier.com/credentials/) after you've made an account
|
||||
- Create allowed actions - Follow step 3 in this [getting start guide](https://nla.zapier.com/start/) from Zapier
|
||||
- ⚠️ NOTE: zapier is known to be finicky with certain actions. I found that writing email drafts is probably the best use of it
|
||||
- there are improvements that can be made to override the official NLA integration and that is TBD
|
||||
- **Browser/Scraper** - This is not to be confused with 'browsing' on chat.openai.com (which is technically a plugin suite or multiple plugins)
|
||||
- This plugin uses OpenAI embeddings so an OpenAI key is necessary, similar to DALL-E, and it's made distinct from your main API key to make Chats but it can be the same one
|
||||
- This plugin will simply scrape html, and will not work with dynamic Javascript pages as that would require a more involved solution
|
||||
- A better solution for 'browsing' is planned but can't guarantuee when
|
||||
- This plugin is best used in combination with google so it doesn't hallucinate webpages to visit
|
||||
- **Serpapi** - an alternative to Google search but not as performant in my opinion
|
||||
- You can get an API key here: https://serpapi.com/dashboard
|
||||
- For free tier, you are limited to 100 queries/month
|
||||
- With google, you are limited to 100/day for free, which is a better deal, and any after may cost you a few pennies
|
||||
|
||||
### Showcase
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../../README.md)
|
||||
289
docs/features/plugins/make_your_own.md
Normal file
289
docs/features/plugins/make_your_own.md
Normal file
|
|
@ -0,0 +1,289 @@
|
|||
## Making your own Plugin
|
||||
|
||||
Creating custom plugins for this project involves extending the `Tool` class from the `langchain/tools` module.
|
||||
|
||||
**Note:** I will use the word plugin interchangeably with tool, as the latter is specific to langchain, and we are mainly conforming to the library in this implementation.
|
||||
|
||||
You are essentially creating DynamicTools in Langchain speak. See the [langchainjs docs](https://js.langchain.com/docs/modules/agents/tools/dynamic) for more info.
|
||||
|
||||
This guide will walk you through the process of creating your own custom plugins, using the `StableDiffusionAPI` and `WolframAlphaAPI` tools as examples.
|
||||
|
||||
The most common implementation is to make an API call based on the natural language input from the AI.
|
||||
|
||||
---
|
||||
|
||||
|
||||
## Key Takeaways
|
||||
|
||||
Here are the key takeaways for creating your own plugin:
|
||||
|
||||
1. [**Import Required Modules:**](make_your_own.md#step-1-import-required-modules) Import the necessary modules for your plugin, including the `Tool` class from `langchain/tools` and any other modules your plugin might need.
|
||||
|
||||
2. [**Define Your Plugin Class:**](make_your_own.md#step-2-define-your-tool-class) Define a class for your plugin that extends the `Tool` class. Set the `name` and `description` properties in the constructor. If your plugin requires credentials or other variables, set them from the fields parameter or from a method that retrieves them from your process environment.
|
||||
|
||||
3. [**Define Helper Methods:**](make_your_own.md#step-3-define-helper-methods) Define helper methods within your class to handle specific tasks if needed.
|
||||
|
||||
4. [**Implement the `_call` Method:**](make_your_own.md#step-4-implement-the-_call-method) Implement the `_call` method where the main functionality of your plugin is defined. This method is called when the language model decides to use your plugin. It should take an `input` parameter and return a result. If an error occurs, the function should return a string representing an error, rather than throwing an error.
|
||||
|
||||
5. [**Export Your Plugin and Import into handleTools.js:**](make_your_own.md#step-5-export-your-plugin-and-import-into-handletoolsjs) Export your plugin and import it into `handleTools.js`. Add your plugin to the `toolConstructors` object in the `loadTools` function. If your plugin requires more advanced initialization, add it to the `customConstructors` object.
|
||||
|
||||
6. [**Add Your Plugin to manifest.json:**](make_your_own.md#step-6-add-your-plugin-to-manifestjson) Add your plugin to `manifest.json`. Follow the strict format for each of the fields of the "plugin" object. If your plugin requires authentication, add those details under `authConfig` as an array. The `pluginKey` should match the class `name` of the Tool class you made, and the `authField` prop must match the process.env variable name.
|
||||
|
||||
Remember, the key to creating a custom plugin is to extend the `Tool` class and implement the `_call` method. The `_call` method is where you define what your plugin does. You can also define helper methods and properties in your class to support the functionality of your plugin.
|
||||
|
||||
**Note: You can find all the files mentioned in this guide in the `.\api\app\langchain\tools` folder.**
|
||||
|
||||
---
|
||||
|
||||
## Step 1: Import Required Modules
|
||||
|
||||
Start by importing the necessary modules. This will include the `Tool` class from `langchain/tools` and any other modules your tool might need. For example:
|
||||
|
||||
```javascript
|
||||
const { Tool } = require('langchain/tools');
|
||||
// ... whatever else you need
|
||||
```
|
||||
|
||||
## Step 2: Define Your Tool Class
|
||||
|
||||
Next, define a class for your plugin that extends the `Tool` class. The class should have a constructor that calls the `super()` method and sets the `name` and `description` properties. These properties will be used by the language model to determine when to call your tool and with what parameters.
|
||||
|
||||
**Important:** you should set credentials/necessary variables from the fields parameter, or alternatively from a method that gets it from your process environment
|
||||
```javascript
|
||||
class StableDiffusionAPI extends Tool {
|
||||
constructor(fields) {
|
||||
super();
|
||||
this.name = 'stable-diffusion';
|
||||
this.url = fields.SD_WEBUI_URL || this.getServerURL(); // <--- important!
|
||||
this.description = `You can generate images with 'stable-diffusion'. This tool is exclusively for visual content...`;
|
||||
}
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
Note that we're getting the necessary variable from the process env with this method if it isn't passed in the fields object.
|
||||
|
||||
A distinction has to be made. The credentials are passed through `fields` when the user provides it from the frontend; otherwise, the admin can "authorize" the plugin through environment variables.
|
||||
|
||||
```js
|
||||
getServerURL() {
|
||||
const url = process.env.SD_WEBUI_URL || '';
|
||||
if (!url) {
|
||||
throw new Error('Missing SD_WEBUI_URL environment variable.');
|
||||
}
|
||||
return url;
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
## Step 3: Define Helper Methods
|
||||
|
||||
You can define helper methods within your class to handle specific tasks if needed. For example, the `StableDiffusionAPI` class includes methods like `replaceNewLinesWithSpaces`, `getMarkdownImageUrl`, and `getServerURL` to handle various tasks.
|
||||
|
||||
```javascript
|
||||
class StableDiffusionAPI extends Tool {
|
||||
...
|
||||
replaceNewLinesWithSpaces(inputString) {
|
||||
return inputString.replace(/\r\n|\r|\n/g, ' ');
|
||||
}
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
## Step 4: Implement the `_call` Method
|
||||
|
||||
The `_call` method is where the main functionality of your plugin is implemented. This method is called when the language model decides to use your plugin. It should take an `input` parameter and return a result.
|
||||
|
||||
```javascript
|
||||
class StableDiffusionAPI extends Tool {
|
||||
...
|
||||
async _call(input) {
|
||||
// Your tool's functionality goes here
|
||||
...
|
||||
return this.result;
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Important:** The _call function is what will the agent will actually call. When an error occurs, the function should, when possible, return a string representing an error, rather than throwing an error. This allows the error to be passed to the LLM and the LLM can decide how to handle it. If an error is thrown, then execution of the agent will stop.
|
||||
|
||||
## Step 5: Export Your Plugin and import into handleTools.js
|
||||
|
||||
|
||||
**This process will be somewhat automated in the future, as long as you have your plugin/tool in api\app\langchain\tools**
|
||||
|
||||
```javascript
|
||||
// Export
|
||||
module.exports = StableDiffusionAPI;
|
||||
```
|
||||
|
||||
```js
|
||||
/* api\app\langchain\tools\handleTools.js */
|
||||
const StableDiffusionAPI = require('./StableDiffusion');
|
||||
...
|
||||
```
|
||||
|
||||
In handleTools.js, find the beginning of the `loadTools` function and add your plugin/tool to the toolConstructors object.
|
||||
```js
|
||||
const loadTools = async ({ user, model, tools = [], options = {} }) => {
|
||||
const toolConstructors = {
|
||||
calculator: Calculator,
|
||||
google: GoogleSearchAPI,
|
||||
wolfram: WolframAlphaAPI,
|
||||
'dall-e': OpenAICreateImage,
|
||||
'stable-diffusion': StableDiffusionAPI // <----- Newly Added. Note: the key is the 'name' provided in the class.
|
||||
// We will now refer to this name as the `pluginKey`
|
||||
};
|
||||
```
|
||||
|
||||
If your Tool class requires more advanced initialization, you would add it to the customConstructors object.
|
||||
|
||||
The default initialization can be seen in the `loadToolWithAuth` function, and most custom plugins should be initialized this way.
|
||||
|
||||
Here are a few customConstructors, which have varying initializations
|
||||
```javascript
|
||||
const customConstructors = {
|
||||
browser: async () => {
|
||||
let openAIApiKey = process.env.OPENAI_API_KEY;
|
||||
if (!openAIApiKey) {
|
||||
openAIApiKey = await getUserPluginAuthValue(user, 'OPENAI_API_KEY');
|
||||
}
|
||||
return new WebBrowser({ model, embeddings: new OpenAIEmbeddings({ openAIApiKey }) });
|
||||
},
|
||||
// ...
|
||||
plugins: async () => {
|
||||
return [
|
||||
new HttpRequestTool(),
|
||||
await AIPluginTool.fromPluginUrl(
|
||||
"https://www.klarna.com/.well-known/ai-plugin.json", new ChatOpenAI({ openAIApiKey: options.openAIApiKey, temperature: 0 })
|
||||
),
|
||||
]
|
||||
}
|
||||
};
|
||||
```
|
||||
|
||||
## Step 6: Add your Plugin to manifest.json
|
||||
|
||||
**This process will be somehwat automated in the future along with step 5, as long as you have your plugin/tool in api\app\langchain\tools, and your plugin can be initialized with the default method**
|
||||
|
||||
```json
|
||||
{
|
||||
"name": "Calculator",
|
||||
"pluginKey": "calculator",
|
||||
"description": "Perform simple and complex mathematical calculations.",
|
||||
"icon": "https://i.imgur.com/RHsSG5h.png",
|
||||
"isAuthRequired": "false",
|
||||
"authConfig": []
|
||||
},
|
||||
{
|
||||
"name": "Stable Diffusion",
|
||||
"pluginKey": "stable-diffusion",
|
||||
"description": "Generate photo-realistic images given any text input.",
|
||||
"icon": "https://i.imgur.com/Yr466dp.png",
|
||||
"authConfig": [
|
||||
{
|
||||
"authField": "SD_WEBUI_URL",
|
||||
"label": "Your Stable Diffusion WebUI API URL",
|
||||
"description": "You need to provide the URL of your Stable Diffusion WebUI API. For instructions on how to obtain this, see <a href='url'>Our Docs</a>."
|
||||
}
|
||||
]
|
||||
},
|
||||
```
|
||||
|
||||
Each of the fields of the "plugin" object are important. Follow this format strictly. If your plugin requires authentication, you will add those details under `authConfig` as an array since there could be multiple authentication variables. See the Calculator plugin for an example of one that doesn't require authentication, where the authConfig is an empty array (an array is always required).
|
||||
|
||||
**Note:** as mentioned earlier, the `pluginKey` matches the class `name` of the Tool class you made.
|
||||
**Note:** the `authField` prop must match the process.env variable name
|
||||
|
||||
Here is an example of a plugin with more than one credential variable
|
||||
```json
|
||||
[
|
||||
{
|
||||
"name": "Google",
|
||||
"pluginKey": "google",
|
||||
"description": "Use Google Search to find information about the weather, news, sports, and more.",
|
||||
"icon": "https://i.imgur.com/SMmVkNB.png",
|
||||
"authConfig": [
|
||||
{
|
||||
"authField": "GOOGLE_CSE_ID",
|
||||
"label": "Google CSE ID",
|
||||
"description": "This is your Google Custom Search Engine ID. For instructions on how to obtain this, see <a href='https://github.com/danny-avila/chatgpt-clone/blob/main/guides/GOOGLE_SEARCH.md'>Our Docs</a>."
|
||||
},
|
||||
{
|
||||
"authField": "GOOGLE_API_KEY",
|
||||
"label": "Google API Key",
|
||||
"description": "This is your Google Custom Search API Key. For instructions on how to obtain this, see <a href='https://github.com/danny-avila/chatgpt-clone/blob/main/guides/GOOGLE_SEARCH.md'>Our Docs</a>."
|
||||
}
|
||||
]
|
||||
},
|
||||
```
|
||||
|
||||
## Example: WolframAlphaAPI Tool
|
||||
|
||||
Here's another example of a custom tool, the `WolframAlphaAPI` tool. This tool uses the `axios` module to make HTTP requests to the Wolfram Alpha API.
|
||||
|
||||
```javascript
|
||||
const axios = require('axios');
|
||||
const { Tool } = require('langchain/tools');
|
||||
|
||||
class WolframAlphaAPI extends Tool {
|
||||
constructor(fields) {
|
||||
super();
|
||||
this.name = 'wolfram';
|
||||
this.apiKey = fields.WOLFRAM_APP_ID || this.getAppId();
|
||||
this.description = `Access computation, math, curated knowledge & real-time data through wolframAlpha...`;
|
||||
}
|
||||
|
||||
async fetchRawText(url) {
|
||||
try {
|
||||
const response = await axios.get(url, { responseType: 'text' });
|
||||
return response.data;
|
||||
} catch (error) {
|
||||
console.error(`Error fetching raw text: ${error}`);
|
||||
throw error
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
getAppId() {
|
||||
const appId = process.env.WOLFRAM_APP_ID || '';
|
||||
if (!appId) {
|
||||
throw new Error('Missing WOLFRAM_APP_ID environment variable.');
|
||||
}
|
||||
return appId;
|
||||
}
|
||||
|
||||
createWolframAlphaURL(query) {
|
||||
const formattedQuery = query.replaceAll(/`/g, '').replaceAll(/\n/g, ' ');
|
||||
const baseURL = 'https://www.wolframalpha.com/api/v1/llm-api';
|
||||
const encodedQuery = encodeURIComponent(formattedQuery);
|
||||
const appId = this.apiKey || this.getAppId();
|
||||
const url = `${baseURL}?input=${encodedQuery}&appid=${appId}`;
|
||||
return url;
|
||||
}
|
||||
|
||||
async _call(input) {
|
||||
try {
|
||||
const url = this.createWolframAlphaURL(input);
|
||||
const response = await this.fetchRawText(url);
|
||||
return response;
|
||||
} catch (error) {
|
||||
if (error.response && error.response.data) {
|
||||
console.log('Error data:', error.response.data);
|
||||
return error.response.data;
|
||||
} else {
|
||||
console.log(`Error querying Wolfram Alpha`, error.message);
|
||||
return 'There was an error querying Wolfram Alpha.';
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
module.exports = WolframAlphaAPI;
|
||||
```
|
||||
|
||||
In this example, the `WolframAlphaAPI` class has helper methods like `fetchRawText`, `getAppId`, and `createWolframAlphaURL` to handle specific tasks. The `_call` method makes an HTTP request to the Wolfram Alpha API and returns the response.
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../../README.md)
|
||||
61
docs/features/plugins/stable_diffusion.md
Normal file
61
docs/features/plugins/stable_diffusion.md
Normal file
|
|
@ -0,0 +1,61 @@
|
|||
# Stable Diffusion Plugin
|
||||
|
||||
To use Stable Diffusion with this project, you will need to download and install [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
|
||||
|
||||
- Note: you need a compatible GPU. Nvidia is recommended, but there is no clear resource on incompatible GPUs. Any decent GPU should work.
|
||||
|
||||
1. Follow download and installation instructions from [stable-diffusion-webui readme](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
|
||||
|
||||
2. Edit your run script settings
|
||||
|
||||
### Windows
|
||||
|
||||
- Edit your **webui-user.bat** file by adding the following line before the call command:
|
||||
- `set COMMANDLINE_ARGS=--api`
|
||||
|
||||
- Your .bat file should like this with all other settings default
|
||||
```shell
|
||||
@echo off
|
||||
|
||||
set PYTHON=
|
||||
set GIT=
|
||||
set VENV_DIR=
|
||||
set COMMANDLINE_ARGS=--api
|
||||
|
||||
call webui.bat
|
||||
```
|
||||
### Others (not tested but should work)
|
||||
|
||||
- Edit your **webui-user.sh** file by adding the following line:
|
||||
- `export COMMANDLINE_ARGS="--api"`
|
||||
|
||||
- Your .sh file should like this with all other settings default
|
||||
```bash
|
||||
|
||||
export COMMANDLINE_ARGS="--api"
|
||||
|
||||
#!/bin/bash
|
||||
#########################################################
|
||||
# Uncomment and change the variables below to your need:#
|
||||
#########################################################
|
||||
|
||||
# ...rest
|
||||
```
|
||||
|
||||
3. Run Stable Diffusion (either .sh or .bat file according to your operating system)
|
||||
|
||||
4. In the app, select the plugins endpoint, open the plugins store, and install Stable Diffusion
|
||||
- You will need the stable diffusion webui API URL, which should be `http://127.0.0.1:7860`
|
||||
- Alternatively: you (the admin) can set the value in `\.env` to bypass the prompt
|
||||
- `SD_WEBUI_URL=http://127.0.0.1:7860`
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
5. Select the plugin and enjoy!
|
||||
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../../README.md)
|
||||
24
docs/features/plugins/wolfram.md
Normal file
24
docs/features/plugins/wolfram.md
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
# Wolfram Alpha Plugin
|
||||
|
||||
An AppID must be supplied in all calls to the Wolfram|Alpha API.
|
||||
|
||||
- Note: Wolfram API calls are limited to 100 calls/day and 2000/month for regular users.
|
||||
|
||||
1. Make an account at <a href='http://products.wolframalpha.com/api/'>Wolfram|Alpha</a>
|
||||
2. Go to the <a href='https://developer.wolframalpha.com/portal/myapps/'>Developer Portal</a> click on "Get an AppID".
|
||||
3. In the app, select the plugins endpoint, open the plugins store, and install Wolfram
|
||||
- You will be prompted for your AppID
|
||||
- Alternatively: you (the admin) can set the value in `\.env` to bypass the prompt
|
||||
- `WOLFRAM_APP_ID=your_app_id`
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
5. Select the plugin and enjoy!
|
||||
|
||||
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../../README.md)
|
||||
|
|
@ -1,47 +1,37 @@
|
|||
# User/Auth System
|
||||
|
||||
**First Time Setup**
|
||||
## **First Time Setup**
|
||||
|
||||
In order for the auth system to function properly, there are some environment variables that are needed. Note that this information is also included in the [/api/.env.example](https://github.com/danny-avila/chatgpt-clone/blob/main/api/.env.example) and [/client/.env.example](https://github.com/danny-avila/chatgpt-clone/blob/main/client/.env.example) files.
|
||||
In order for the auth system to function properly, there are some environment variables that are needed. Note that this information is also included in the [/.env.example](https://github.com/danny-avila/chatgpt-clone/blob/main/.env.example) file.
|
||||
|
||||
In /api/.env, you will need to set the following variables:
|
||||
In /.env, you will need to set the following variables:
|
||||
```bash
|
||||
JWT_SECRET_DEV=secret
|
||||
# Add a secure secret for production if deploying to live domain.
|
||||
JWT_SECRET_PROD=secret
|
||||
# Change this to a secure string
|
||||
JWT_SECRET=secret
|
||||
# Set the expiration delay for the secure cookie with the JWT token
|
||||
# Delay is in millisecond e.g. 7 days is 1000*60*60*24*7
|
||||
SESSION_EXPIRY=1000 * 60 * 60 * 24 * 7
|
||||
# Note: NODE_ENV should be set to 'development' in the Server configuration section if you want to run in dev mode
|
||||
CLIENT_URL_DEV=http://localhost:3090
|
||||
SERVER_URL_DEV=http://localhost:3080
|
||||
# Change these values to domain if deploying:
|
||||
CLIENT_URL_PROD=http://localhost:3080
|
||||
SERVER_URL_PROD=http://localhost:3080
|
||||
DOMAIN_SERVER=http://localhost:3080
|
||||
DOMAIN_CLIENT=http://localhost:3080
|
||||
```
|
||||
|
||||
In /client/.env, you will need to set the following variables:
|
||||
```bash
|
||||
VITE_SERVER_URL_DEV=http://localhost:3080
|
||||
# Change this to domain if deploying:
|
||||
VITE_SERVER_URL_PROD=http://localhost:3080
|
||||
```
|
||||
*Please Note: If you are wanting this to work in development mode, you will need to create a file called `.env.development` in the root directory and set `DOMAIN_CLIENT` to `http://localhost:3090` or whatever port is provided by vite when runnning `npm run frontend-dev`*
|
||||
|
||||
The first time you run the application, you should register a new account by clicking the "Sign up" link on the login page. The first account registered will be recieve an admin role. The admin account does not currently have extended functionality, but is valuable should you choose to create an admin dashboard for user management.
|
||||
The first time you run the application, you should register a new account by clicking the "Sign up" link on the login page. The first account registered will receive an admin role. The admin account does not currently have extended functionality, but is valuable should you choose to create an admin dashboard for user management.
|
||||
|
||||
**Migrating Previous Conversations and Presets to new User Account**
|
||||
## **Migrating Previous Conversations and Presets to new User Account**
|
||||
|
||||
When the first account is registered, the application will automatically migrate any conversations and presets that you created before the user system was implemented to that account.
|
||||
|
||||
⚠️**IMPORTANT**: if you use login for the first time with a social login account (eg. Google, facebook, etc.), the conversations and presets that you created before the user system was implemented will NOT be migrated to that account. You should register and login with a local account (email and password) for the first time.
|
||||
|
||||
**OAuth2/Social Login**
|
||||
## **OAuth2/Social Login**
|
||||
|
||||
The application is setup to support OAuth2/Social Login with Google. All of the code is in place for Facebook login as well, but this has not been tested because the setup process with Facebook was honestly just too painful for me to deal with. I plan to add support for other OAuth2 providers including Github and Discord at a later time.
|
||||
|
||||
To enable Google login, you must create an application in the [Google Cloud Console](https://cloud.google.com) and provide the client ID and client secret in the [/api/.env](https://github.com/danny-avila/chatgpt-clone/blob/main/api/.env.example) file, then set `VITE_SHOW_GOOGLE_LOGIN_OPTION=true` in the [/client/.env](https://github.com/danny-avila/chatgpt-clone/blob/main/client/.env.example) file.
|
||||
To enable Google login, you must create an application in the [Google Cloud Console](https://cloud.google.com) and provide the client ID and client secret in the [/.env](https://github.com/danny-avila/chatgpt-clone/blob/main/.env.example) file, then set `VITE_SHOW_GOOGLE_LOGIN_OPTION=true`.
|
||||
|
||||
*Instructions for setting up Google login are provided below.*
|
||||
### *Instructions for setting up Google login are provided below.*
|
||||
```
|
||||
1. Go to "APIs and Services" in your Google Cloud account and click on "Credentials".
|
||||
2. Click on "Configure consent screen" and select "External" as the user type.
|
||||
|
|
@ -52,15 +42,19 @@ To enable Google login, you must create an application in the [Google Cloud Cons
|
|||
7. Add "http://localhost" "http://localhost:3080" and "http://localhost:3090" to the authorized JavaScript origins.
|
||||
8. Add "http://localhost:3080/oauth/google/callback" to the authorized redirect URIs.
|
||||
9. Click on "Create" and copy your client ID and client secret.
|
||||
10. Paste them into your api/.env file.
|
||||
11. Enable the feature in the client/.env file
|
||||
10. Paste them into your /.env file.
|
||||
11. Enable the feature in the /.env file
|
||||
```
|
||||
|
||||
**Email and Password Reset**
|
||||
## **Email and Password Reset**
|
||||
|
||||
Most of the code is in place for sending password reset emails, but is not yet feature-complete as I have not setup an email server to test it. Currently, submitting a password reset request will then display a link with the one-time reset token that can then be used to reset the password. Understanding that this is a considerable security hazard, email integration will be included in the next release.
|
||||
|
||||
***Warning***
|
||||
## **Disable User Registration**
|
||||
|
||||
To disable or re-enable registration, open up the root `.env` file and set `ALLOW_REGISTRATION=true` or `ALLOW_REGISTRATION=false` depending on if you want registration open or closed.
|
||||
|
||||
### ***Warning***
|
||||
|
||||
If you previously implemented your own user system using the original scaffolding that was provided, you will no longer see conversations and presets by switching to the new user system. This is because of a design flaw in the scaffolding implementation that was problematic for the inclusion of social login.
|
||||
|
||||
|
|
|
|||
|
|
@ -1,34 +0,0 @@
|
|||
# Roadmap
|
||||
|
||||
## For the most up to date information: [LibreChat | Trello](https://trello.com/b/17z094kq/chatgpt-clone)
|
||||
|
||||
<summary><strong>Here are my recently completed and planned features:</strong></summary>
|
||||
|
||||
- [x] Persistent conversation
|
||||
- [x] Rename, delete conversations
|
||||
- [x] UI Error handling
|
||||
- [x] Bing AI integration
|
||||
- [x] AI model change handling (start new convos within existing, remembers last selected)
|
||||
- [x] Code block handling (highlighting, markdown, clipboard, language detection)
|
||||
- [x] Markdown handling
|
||||
- [x] Customize prompt prefix/label (custom ChatGPT using official API)
|
||||
- [x] Server convo pagination (limit fetch and load more with 'show more' button)
|
||||
- [x] Config file for easy startup (docker compose)
|
||||
- [x] Mobile styling (thanks to [wtlyu](https://github.com/wtlyu))
|
||||
- [x] Resubmit/edit sent messages (thanks to [wtlyu](https://github.com/wtlyu))
|
||||
- [x] Message Search
|
||||
- [x] Custom params for ChatGPT API (temp, top_p, presence_penalty)
|
||||
- [x] Bing AI Styling (params, suggested responses, convo end, etc.)
|
||||
- [x] Add warning before clearing convos
|
||||
- [x] Optional use of local storage for credentials (for bing and browser)
|
||||
- [ ] Build test suite for CI/CD
|
||||
- [ ] Prompt Templates/Search
|
||||
- [ ] Refactor/clean up code (tech debt)
|
||||
- [ ] ChatGPT Plugins (reverse engineered)
|
||||
- [ ] Deploy demo
|
||||
|
||||
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../README.md)
|
||||
81
docs/install/apis_and_tokens.md
Normal file
81
docs/install/apis_and_tokens.md
Normal file
|
|
@ -0,0 +1,81 @@
|
|||
# How to setup various tokens and APIs for the project
|
||||
|
||||
This doc explains how to setup various tokens and APIs for the project. You will need some of these tokens and APIs to run the app and use its features. You must set up at least one of these tokens or APIs to run the app.
|
||||
|
||||
## OpenAI API key
|
||||
|
||||
To get your OpenAI API key, you need to:
|
||||
|
||||
- Go to https://platform.openai.com/account/api-keys
|
||||
- Create an account or log in with your existing one
|
||||
- Add a payment method to your account (this is not free, sorry 😬)
|
||||
- Copy your secret key (sk-...) and save it in ./.env as OPENAI_API_KEY
|
||||
|
||||
## ChatGPT Free Access token
|
||||
|
||||
To get your Access token for ChatGPT 'Free Version', you need to:
|
||||
|
||||
- Go to https://chat.openai.com
|
||||
- Create an account or log in with your existing one
|
||||
- Visit https://chat.openai.com/api/auth/session
|
||||
- Copy the value of the "access_token" field and save it in ./.env as CHATGPT_ACCESS_TOKEN
|
||||
|
||||
Warning: There may be a chance of your account being banned if you deploy the app to multiple users with this method. Use at your own risk. 😱
|
||||
|
||||
## Bing Access Token
|
||||
|
||||
To get your Bing Access Token, you have a few options:
|
||||
|
||||
- You can try leaving it blank and see if it works (fingers crossed 🤞)
|
||||
|
||||
- You can follow these [new instructions](https://github.com/danny-avila/LibreChat/issues/370#issuecomment-1560382302) (thanks @danny-avila for sharing 🙌)
|
||||
|
||||
- You can use MS Edge, navigate to bing.com, and do the following:
|
||||
- Make sure you are logged in
|
||||
- Open the DevTools by pressing F12 on your keyboard
|
||||
- Click on the tab "Application" (On the left of the DevTools)
|
||||
- Expand the "Cookies" (Under "Storage")
|
||||
- Copy the value of the "\_U" cookie and save it in ./.env as BING_ACCESS_TOKEN
|
||||
|
||||
## Google's PaLM 2
|
||||
|
||||
To setup PaLM 2 (via Google Cloud Vertex AI API), you need to:
|
||||
|
||||
- Enable the Vertex AI API on Google Cloud:
|
||||
- Go to https://console.cloud.google.com/vertex-ai
|
||||
- Click on "Enable API" if prompted
|
||||
- Create a Service Account:
|
||||
- Go to https://console.cloud.google.com/projectselector/iam-admin/serviceaccounts/create?walkthrough_id=iam--create-service-account#step_index=1
|
||||
- Select or create a project
|
||||
- Enter a service account name and description
|
||||
- Click on "Create and Continue" to give at least the "Vertex AI User" role
|
||||
- Click on "Done"
|
||||
- Create a JSON key, rename as 'auth.json' and save it in /api/data/:
|
||||
- Go back to https://console.cloud.google.com/projectselector/iam-admin/serviceaccounts
|
||||
- Select your service account
|
||||
- Click on "Keys"
|
||||
- Click on "Add Key" and then "Create new key"
|
||||
- Choose JSON as the key type and click on "Create"
|
||||
- Download the key file and rename it as 'auth.json'
|
||||
- Save it in /api/data/
|
||||
|
||||
##
|
||||
|
||||
That's it! You're all set. 🎉
|
||||
|
||||
##
|
||||
|
||||
## Go Back to Your Install Documentation:
|
||||
- [Docker Install](docker_install.md)
|
||||
- [Linux Install](linux_install.md)
|
||||
- [Mac Install](mac_install.md)
|
||||
- [Windows Install](windows_install.md)
|
||||
|
||||
##
|
||||
|
||||
### Note: If you're still having trouble, before creating a new issue, please search for similar ones on our [#issues thread on our discord](https://discord.gg/weqZFtD9C4) or our [troubleshooting discussion](https://github.com/danny-avila/LibreChat/discussions/new?category=troubleshooting) on our Discussions page. If you don't find a relevant issue, feel free to create a new one and provide as much detail as possible.
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../README.md)
|
||||
|
||||
|
|
@ -1,41 +1,110 @@
|
|||
# Docker
|
||||
# Docker
|
||||
|
||||
|
||||
|
||||
- **Edit** the credentials you see in [docker-compose.yml](https://stackedit.io/docker-compose.yml) under api service as needed
|
||||
- **Provide** all necessary credentials in the ./api/.env and client/.env files before the next step
|
||||
- Docker will read those env files. See their respective `.env.example` files for reference
|
||||
- **Run** `docker-compose up` to start the app
|
||||
- Note: MongoDB does not support older ARM CPUs like those found in Raspberry Pis. However, you can make it work by setting MongoDB’s version to mongo:4.4.18 in docker-compose.yml, the most recent version compatible with
|
||||
|
||||
##
|
||||
|
||||
**[chatgptclone/app Tags | Docker Hub](https://hub.docker.com/r/chatgptclone/app/tags)**
|
||||
|
||||
##
|
||||
|
||||
### Prerequisites
|
||||
- Node.js >= 19.0.0 : https://nodejs.org/en/download
|
||||
- MongoDB installed or [MongoDB Atlas](https://account.mongodb.com/account/login) (required if not using Docker)
|
||||
- MongoDB does not support older ARM CPUs like those found in Raspberry Pis. However, you can make it work by setting MongoDB's version to mongo:4.4.18 in docker-compose.yml, the most recent version compatible with.
|
||||
- If using MongoDB Atlas, remove `&w=majority` from default connection string.
|
||||
- [OpenAI API key](https://platform.openai.com/account/api-keys)
|
||||
- BingAI, ChatGPT access tokens (optional, free AIs)
|
||||
|
||||
### Usage
|
||||
Docker installation is recommended for most use cases. It's the easiest, simplest, and most reliable method to get started.
|
||||
|
||||
- **Clone/download** the repo down where desired
|
||||
```bash
|
||||
git clone https://github.com/danny-avila/LibreChat.git
|
||||
```
|
||||
- Install **Docker:** [Docker Desktop](https://www.docker.com/products/docker-desktop/) is recommended for managing your docker container
|
||||
- **Edit** the credentials you see in [docker-compose.yml](https://stackedit.io/docker-compose.yml) under api service as needed
|
||||
- **Provide** all necessary credentials in the /.env file before the next step
|
||||
- See my notes below for specific instructions on some of the configuration
|
||||
- Docker will read those env files. See their respective `.env.example` files for reference
|
||||
- **Run** `docker-compose up` to start the app
|
||||
- Note: MongoDB does not support older ARM CPUs like those found in Raspberry Pis. However, you can make it work by setting MongoDB’s version to mongo:4.4.18 in docker-compose.yml, the most recent version compatible with
|
||||
- **That's it!** If you need more detailed information on configuring your compose file, see my notes below.
|
||||
|
||||
- **If you're still having trouble, before creating a new issue, please search for similar ones on our [#issues thread on our discord](https://discord.gg/weqZFtD9C4) or our [troubleshooting discussion](https://github.com/danny-avila/LibreChat/discussions/new?category=troubleshooting) on our Discussions page. If you don't find a relevant issue, feel free to create a new one and provide as much detail as possible.**
|
||||
|
||||
## [Get Your API keys and Tokens](apis_and_tokens.md) (Required)
|
||||
- You must set up at least one of these tokens or APIs to run the app.
|
||||
|
||||
## [User/Auth System](../features/user_auth_system.md) (Optional)
|
||||
- How to set up the user/auth system and Google login.
|
||||
|
||||
## Update
|
||||
To update LibreChat. enter these commands one after the other from the root dir:
|
||||
- git pull
|
||||
- docker-compose build
|
||||
- docker-compose up
|
||||
|
||||
##
|
||||
|
||||
**Create a MongoDB database**
|
||||
|
||||
## Config notes for docker-compose.yml file
|
||||
|
||||
- Any environment variables set in your compose file will override variables with the same name in your .env file. Note that the following variables are necessary to include in the compose file so they work in the docker environment, so they are included for you.
|
||||
```yaml
|
||||
env_file:
|
||||
- .env
|
||||
environment:
|
||||
- HOST=0.0.0.0
|
||||
- MONGO_URI=mongodb://mongodb:27017/LibreChat
|
||||
# ...
|
||||
- MEILI_HOST=http://meilisearch:7700
|
||||
- MEILI_HTTP_ADDR=meilisearch:7700
|
||||
# ...
|
||||
env_file:
|
||||
- .env
|
||||
environment:
|
||||
- MEILI_HOST=http://meilisearch:7700
|
||||
- MEILI_HTTP_ADDR=meilisearch:7700
|
||||
```
|
||||
- If you'd like to change the app title or disable/enable google login, edit the following lines (the ones in your .env file are not read during building)
|
||||
```yaml
|
||||
args:
|
||||
VITE_APP_TITLE: LibreChat # default, change to your desired app name
|
||||
VITE_SHOW_GOOGLE_LOGIN_OPTION: false # default, change to true if you have google auth setup
|
||||
```
|
||||
|
||||
- If for some reason you're not able to build the app image, you can pull the latest image from **Dockerhub**.
|
||||
- Comment out the following lines (CTRL+/ on most IDEs, or put a `#` in front each line)
|
||||
|
||||
|
||||
```yaml
|
||||
image: node # Comment this & uncomment below to build from docker hub image
|
||||
build:
|
||||
context: .
|
||||
target: node
|
||||
args:
|
||||
VITE_APP_TITLE: LibreChat # default, change to your desired app name
|
||||
VITE_SHOW_GOOGLE_LOGIN_OPTION: false # default, change to true if you have google auth setup
|
||||
```
|
||||
|
||||
- Comment this line in (remove the `#` key)
|
||||
|
||||
|
||||
```yaml
|
||||
# image: chatgptclone/app:latest # Uncomment this & comment above to build from docker hub image
|
||||
```
|
||||
- **Note:** The latest Dockerhub image is only updated with new release tags, so it may not have the latest changes to the main branch
|
||||
- You also can't edit the title or toggle google login off as shown above, as these variables are set during build time.
|
||||
- If you are running APIs in other docker containers that you need access to, you will need to uncomment the following lines
|
||||
|
||||
```yaml
|
||||
# extra_hosts: # if you are running APIs on docker you need access to, you will need to uncomment this line and next
|
||||
# - "host.docker.internal:host-gateway"
|
||||
```
|
||||
|
||||
- Usually, these are reverse proxies, which you can set as shown below under `environment:`
|
||||
|
||||
|
||||
```yaml
|
||||
environment:
|
||||
- HOST=0.0.0.0
|
||||
- MONGO_URI=mongodb://mongodb:27017/LibreChat
|
||||
- CHATGPT_REVERSE_PROXY=http://host.docker.internal:8080/api/conversation # if you are hosting your own chatgpt reverse proxy with docker
|
||||
- OPENAI_REVERSE_PROXY=http://host.docker.internal:8070/v1/chat/completions # if you are hosting your own chatgpt reverse proxy with docker
|
||||
```
|
||||
|
||||
### **[LibreChat on Docker Hub](https://hub.docker.com/r/chatgptclone/app/tags)**
|
||||
|
||||
## **Create a MongoDB database** (Not required if you'd like to use the local database installed by Docker)
|
||||
|
||||
Navigate to https://www.mongodb.com/ and Sign In or Create an account
|
||||
|
||||
- Create a new project
|
||||
- Build a Database using the free plan and name the cluster (example: chatgpt-clone)
|
||||
- Build a Database using the free plan and name the cluster (example: LibreChat)
|
||||
- Use the "Username and Password" method for authentication
|
||||
- Add your current IP to the access list
|
||||
- In the Database Deployment tab, click on Connect
|
||||
|
|
@ -43,25 +112,6 @@ Navigate to https://www.mongodb.com/ and Sign In or Create an account
|
|||
- Driver = Node.js / Version = 4.1 or later
|
||||
- Copy the connection string, fill in your password and remove `&w=majority` from default connection string.
|
||||
|
||||
|
||||
##
|
||||
**ChatGPT Free Instructions:**
|
||||
- To get your Access token for ChatGPT 'Free Version', log in to chat.openai.com, then visit https://chat.openai.com/api/auth/session.
|
||||
- Warning: There may be a high chance of your account being banned with this method. Continue doing so at your own risk.
|
||||
|
||||
### **Get your Bing Access Token**
|
||||
|
||||
⚠️**For better results, please follow these [new instructions](https://github.com/danny-avila/LibreChat/issues/370#issuecomment-1560382302)**
|
||||
|
||||
or
|
||||
|
||||
Using MS Edge, navigate to bing.com
|
||||
- Make sure you are logged in
|
||||
- Open the DevTools by pressing F12 on your keyboard
|
||||
- Click on the tab "Application" (On the left of the DevTools)
|
||||
- Expand the "Cookies" (Under "Storage")
|
||||
- Copy the value of the "\_U" cookie
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../README.md)
|
||||
|
|
|
|||
|
|
@ -7,35 +7,33 @@
|
|||
|
||||
## Prerequisites
|
||||
|
||||
Before installing ChatGPT-Clone, make sure your machine has the following prerequisites installed:
|
||||
Before installing LibreChat, make sure your machine has the following prerequisites installed:
|
||||
|
||||
- Git: To clone the repository.
|
||||
- Node.js: To run the application.
|
||||
- MongoDB: To store the chat history.
|
||||
|
||||
## Installation Steps
|
||||
|
||||
## 1. Clone the repository:
|
||||
## Clone the repository:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/danny-avila/LibreChat.git
|
||||
```
|
||||
|
||||
## 2. Extract the content in your desired location:
|
||||
## Extract the content in your desired location:
|
||||
|
||||
```bash
|
||||
cd chatgpt-clone
|
||||
unzip chatgpt-clone.zip -d /usr/local/
|
||||
cd LibreChat
|
||||
unzip LibreChat.zip -d /usr/local/
|
||||
```
|
||||
|
||||
Note: The above command extracts the files to "/usr/local/chatgpt-clone". If you want to install the files to a different location, modify the instructions accordingly.
|
||||
Note: The above command extracts the files to "/usr/local/LibreChat". If you want to install the files to a different location, modify the instructions accordingly.
|
||||
|
||||
## 3. Enable the Conversation search feature: (optional)
|
||||
## Enable the Conversation search feature: (optional)
|
||||
|
||||
- Download MeiliSearch latest release from: https://github.com/meilisearch/meilisearch/releases
|
||||
- Copy it to "/usr/local/chatgpt-clone/"
|
||||
- Copy it to "/usr/local/LibreChat/"
|
||||
- Rename the file to "meilisearch"
|
||||
- Open a terminal and navigate to "/usr/local/chatgpt-clone/"
|
||||
- Open a terminal and navigate to "/usr/local/LibreChat/"
|
||||
- Run the following command:
|
||||
|
||||
```bash
|
||||
|
|
@ -44,7 +42,7 @@ Note: The above command extracts the files to "/usr/local/chatgpt-clone". If you
|
|||
|
||||
Note: Replace "YOUR_MASTER_KEY" with the generated master key, which you saved earlier.
|
||||
|
||||
## 4. Install Node.js:
|
||||
## Install Node.js:
|
||||
|
||||
Open a terminal and run the following commands:
|
||||
|
||||
|
|
@ -53,11 +51,11 @@ curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo -E bash -
|
|||
sudo apt-get install -y nodejs
|
||||
```
|
||||
|
||||
## 5. Create a MongoDB database:
|
||||
## Create a MongoDB database:
|
||||
|
||||
- Navigate to https://www.mongodb.com/ and sign in or create an account.
|
||||
- Create a new project.
|
||||
- Build a Database using the free plan and name the cluster (example: chatgpt-clone).
|
||||
- Build a Database using the free plan and name the cluster (example: LibreChat).
|
||||
- Use the "Username and Password" method for authentication.
|
||||
- Add your current IP to the access list.
|
||||
- Then in the Database Deployment tab click on Connect.
|
||||
|
|
@ -65,34 +63,11 @@ sudo apt-get install -y nodejs
|
|||
- Driver = Node.js / Version = 4.1 or later.
|
||||
- Copy the connection string and save it somewhere (you will need it later).
|
||||
|
||||
## 6. Get your OpenAI API key
|
||||
- Visit https://platform.openai.com/account/api-keys and save your API key somewhere safe (you will need it later)
|
||||
## [Get Your API keys and Tokens](apis_and_tokens.md) (Required)
|
||||
- You must set up at least one of these tokens or APIs to run the app.
|
||||
|
||||
## 7. Get your Bing Access Token
|
||||
|
||||
⚠️**For better results, please follow these [new instructions](https://github.com/danny-avila/LibreChat/issues/370#issuecomment-1560382302)**
|
||||
|
||||
or
|
||||
|
||||
Using MS Edge, navigate to bing.com
|
||||
- Make sure you are logged in
|
||||
- Open the DevTools by pressing F12 on your keyboard
|
||||
- Click on the tab "Application" (On the left of the DevTools)
|
||||
- Expand the "Cookies" (Under "Storage")
|
||||
- Copy the value of the "\_U" cookiee
|
||||
|
||||
## 8. Create the ".env" File
|
||||
|
||||
You will need all your credentials, (API keys, access tokens, and MongoDB Connection String, MeiliSearch Master Key)
|
||||
|
||||
- Open "~/chatgpt-clone/api/.env.example" in a text editor
|
||||
- At this line MONGO_URI="mongodb://127.0.0.1:27017/chatgpt-clone", replace mongodb://127.0.0.1:27017/chatgpt-clone with the MongoDB connection string you saved earlier, remove "&w=majority" at the end
|
||||
- It should look something like this: "MONGO_URI="mongodb+srv://username:password@chatgpt-clone.lfbcwz3.mongodb.net/?retryWrites=true"
|
||||
- At this line OPENAI_KEY= you need to add your OpenAI API key
|
||||
- Add your Bing token to this line BINGAI_TOKEN= (needed for BingChat & Sydney)
|
||||
- If you want to enable Search, SEARCH=TRUE if you do not want to enable search SEARCH=FALSE
|
||||
- Add your previously saved MeiliSearch Master key to this line MEILI_MASTER_KEY= (the key is needed if search is enabled even on local install or you may encounter errors)
|
||||
- Save the file as "~/chatgpt-clone/api/.env"
|
||||
## [User/Auth System](../features/user_auth_system.md) (Optional)
|
||||
- How to set up the user/auth system and Google login.
|
||||
|
||||
## Run the project
|
||||
|
||||
|
|
@ -132,5 +107,8 @@ If you update the chatgpt-clone project files, manually redo the npm ci and npm
|
|||
|
||||
##
|
||||
|
||||
### Note: If you're still having trouble, before creating a new issue, please search for similar ones on our [#issues thread on our discord](https://discord.gg/weqZFtD9C4) or our [troubleshooting discussion](https://github.com/danny-avila/LibreChat/discussions/new?category=troubleshooting) on our Discussions page. If you don't find a relevant issue, feel free to create a new one and provide as much detail as possible.
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../README.md)
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
# Mac Install
|
||||
# Mac Install
|
||||
## **Recommended : [Docker Install](docker_install.md)**
|
||||
|
||||
##
|
||||
|
|
@ -14,7 +14,7 @@
|
|||
|
||||
- Navigate to https://www.mongodb.com/ and Sign In or Create an account
|
||||
- Create a new project
|
||||
- Build a Database using the free plan and name the cluster (example: chatgpt-clone)
|
||||
- Build a Database using the free plan and name the cluster (example: LibreChat)
|
||||
- Use the "Username and Password" method for authentication
|
||||
- Add your current IP to the access list
|
||||
- Then in the Database Deployment tab click on Connect
|
||||
|
|
@ -30,33 +30,14 @@
|
|||
- If using MongoDB Atlas, remove &w=majority from the default connection string
|
||||
Follow the instructions for setting up proxies, access tokens, and user system:
|
||||
|
||||
## Access Tokens:
|
||||
|
||||
### **Get your OpenAI API key**
|
||||
|
||||
- here: https://platform.openai.com/account/api-keys and save it somewhere safe (you will need it later)
|
||||
|
||||
### **ChatGPT Free Instructions:**
|
||||
|
||||
- To get your Access token for ChatGPT 'Free Version', log in to chat.openai.com, then visit https://chat.openai.com/api/auth/session.
|
||||
- Warning: There may be a high chance of your account being banned with this method. Continue doing so at your own risk.
|
||||
|
||||
### **Get your Bing Access Token**
|
||||
|
||||
⚠️**For better results, please follow these [new instructions](https://github.com/danny-avila/LibreChat/issues/370#issuecomment-1560382302)**
|
||||
|
||||
or
|
||||
|
||||
Using MS Edge, navigate to bing.com
|
||||
- Make sure you are logged in
|
||||
- Open the DevTools by pressing F12 on your keyboard
|
||||
- Click on the tab "Application" (On the left of the DevTools)
|
||||
- Expand the "Cookies" (Under "Storage")
|
||||
- Copy the value of the "\_U" cookie
|
||||
## [Get Your API keys and Tokens](apis_and_tokens.md) (Required)
|
||||
- You must set up at least one of these tokens or APIs to run the app.
|
||||
|
||||
## [User/Auth System](../features/user_auth_system.md) (Optional)
|
||||
- How to set up the user/auth system and Google login.
|
||||
|
||||
## Setup Instruction
|
||||
- Create a .env file in the api directory by running cp api/.env.example api/.env and edit the file with your preferred text editor, adding the required API keys, access tokens, and MongoDB connection string
|
||||
- Create a .env file in the api directory by running `cp .env.example .env` and edit the file with your preferred text editor, adding the required API keys, access tokens, and MongoDB connection string
|
||||
- Run npm ci from root directory `npm ci`
|
||||
- Build the client by running `npm run frontend`
|
||||
|
||||
|
|
@ -77,7 +58,7 @@ chmod +x meilisearch-macos-amd64
|
|||
./meilisearch-macos-amd64 --master-key your_master_key_goes_here
|
||||
```
|
||||
|
||||
- MeiliSearch will start running on the default port, which is 7700. You can now use MeiliSearch in your ChatGPT-Clone project.
|
||||
- MeiliSearch will start running on the default port, which is 7700. You can now use MeiliSearch in your LibreChat project.
|
||||
|
||||
- Remember to include the MeiliSearch URL and Master Key in your .env file in the api directory. Your .env file should include the following lines:
|
||||
|
||||
|
|
@ -86,14 +67,14 @@ MEILISEARCH_URL=http://127.0.0.1:7700
|
|||
MEILISEARCH_KEY=your_master_key_goes_here
|
||||
```
|
||||
|
||||
- With MeiliSearch running and configured, the ChatGPT-Clone project should now have the Conversation search feature enabled.
|
||||
- With MeiliSearch running and configured, the LibreChat project should now have the Conversation search feature enabled.
|
||||
|
||||
- In the chatgpt-clone directory, start the application by running `npm run backend`
|
||||
- In the LibreChat directory, start the application by running `npm run backend`
|
||||
Visit http://localhost:3080 (default port) & enjoy
|
||||
|
||||
## Optional but recommended:
|
||||
|
||||
- Create a script to automate the starting process by creating a new file named start_chatgpt.sh in the chatgpt-clone directory and pasting the following code:
|
||||
- Create a script to automate the starting process by creating a new file named start_chatgpt.sh in the LibreChat directory and pasting the following code:
|
||||
|
||||
```
|
||||
#!/bin/bash
|
||||
|
|
@ -110,7 +91,7 @@ npm run backend
|
|||
chmod +x start_chatgpt.sh
|
||||
```
|
||||
|
||||
### **Start ChatGPT-Clone by running**
|
||||
### **Start LibreChat by running**
|
||||
```
|
||||
./start_chatgpt.sh
|
||||
```
|
||||
|
|
@ -123,4 +104,8 @@ npm run backend
|
|||
|
||||
##
|
||||
|
||||
### Note: If you're still having trouble, before creating a new issue, please search for similar ones on our [#issues thread on our discord](https://discord.gg/weqZFtD9C4) or our [troubleshooting discussion](https://github.com/danny-avila/LibreChat/discussions/new?category=troubleshooting) on our Discussions page. If you don't find a relevant issue, feel free to create a new one and provide as much detail as possible.
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../README.md)
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
# Windows Install
|
||||
# Windows Install
|
||||
|
||||
### Recommended: **[Docker](docker_install.md)**
|
||||
or
|
||||
|
|
@ -9,18 +9,18 @@ or
|
|||
## Manual Installation
|
||||
### Install the prerequisites on your machine
|
||||
|
||||
### **Download chatgpt-clone**
|
||||
### **Download LibreChat**
|
||||
|
||||
- Download the latest release here: https://github.com/danny-avila/LibreChat/releases/
|
||||
- Or by clicking on the green code button in the top of the page and selecting "Download ZIP"
|
||||
- Open Terminal (command prompt) and clone the repository by running `git clone https://github.com/danny-avila/LibreChat.git`
|
||||
- If you downloaded a zip file, extract the content in "C:/chatgpt-clone/"
|
||||
- If you downloaded a zip file, extract the content in "C:/LibreChat/"
|
||||
- **IMPORTANT : If you install the files somewhere else modify the instructions accordingly**
|
||||
|
||||
### **Enable the Conversation search feature:** (optional)
|
||||
|
||||
- Download MeiliSearch latest release from : https://github.com/meilisearch/meilisearch/releases
|
||||
- Copy it to "C:/chatgpt-clone/"
|
||||
- Copy it to "C:/LibreChat/"
|
||||
- Rename the file to "meilisearch.exe"
|
||||
- Open it by double clicking on it
|
||||
- Copy the generated Master Key and save it somewhere (You will need it later)
|
||||
|
|
@ -33,7 +33,7 @@ or
|
|||
|
||||
- Navigate to https://www.mongodb.com/ and Sign In or Create an account
|
||||
- Create a new project
|
||||
- Build a Database using the free plan and name the cluster (example: chatgpt-clone)
|
||||
- Build a Database using the free plan and name the cluster (example: LibreChat)
|
||||
- Use the "Username and Password" method for authentication
|
||||
- Add your current IP to the access list
|
||||
- Then in the Database Deployment tab click on Connect
|
||||
|
|
@ -41,36 +41,26 @@ or
|
|||
- Driver = Node.js / Version = 4.1 or later
|
||||
- Copy the connection string and save it somewhere(you will need it later)
|
||||
|
||||
|
||||
### **Get your OpenAI API key**
|
||||
- here: https://platform.openai.com/account/api-keys and save it somewhere safe (you will need it later)
|
||||
### [Get Your API keys and Tokens](apis_and_tokens.md) (Required)
|
||||
- You must set up at least one of these tokens or APIs to run the app.
|
||||
|
||||
### **Get your Bing Access Token**
|
||||
### [User/Auth System](../features/user_auth_system.md) (Optional)
|
||||
- How to set up the user/auth system and Google login.
|
||||
|
||||
⚠️**For better results, please follow these [new instructions](https://github.com/danny-avila/LibreChat/issues/370#issuecomment-1560382302)**
|
||||
|
||||
or
|
||||
|
||||
Using MS Edge, navigate to bing.com
|
||||
- Make sure you are logged in
|
||||
- Open the DevTools by pressing F12 on your keyboard
|
||||
- Click on the tab "Application" (On the left of the DevTools)
|
||||
- Expand the "Cookies" (Under "Storage")
|
||||
- Copy the value of the "\_U" cookie
|
||||
|
||||
### **Create the ".env" File**
|
||||
You will need all your credentials, (API keys, access tokens, and Mongo Connection String, MeileSearch Master Key)
|
||||
- Open "C:/chatgpt-clone/api/.env.example" in a text editor
|
||||
- At this line **MONGO_URI="mongodb://127.0.0.1:27017/chatgpt-clone"**
|
||||
Replace mongodb://127.0.0.1:27017/chatgpt-clone with the MondoDB connection string you saved earlier, **remove "&w=majority" at the end**
|
||||
- It should look something like this: "MONGO_URI="mongodb+srv://username:password@chatgpt-clone.lfbcwz3.mongodb.net/?retryWrites=true"
|
||||
- At this line **OPENAI_KEY=** you need to add your openai API key
|
||||
- Open the .env.example file in your install folder e.g. "C:/LibreChat/.env.example" in a text editor
|
||||
- At this line **MONGO_URI="mongodb://127.0.0.1:27017/LibreChat"**
|
||||
Replace mongodb://127.0.0.1:27017/LibreChat with the MondoDB connection string you saved earlier, **remove "&w=majority" at the end**
|
||||
- It should look something like this: "MONGO_URI="mongodb+srv://username:password@LibreChat.lfbcwz3.mongodb.net/?retryWrites=true"
|
||||
- At this line **OPENAI_API_KEY=** you need to add your openai API key
|
||||
- Add your Bing token to this line **BINGAI_TOKEN=** (needed for BingChat & Sydney)
|
||||
- If you want to enable Search, **SEARCH=TRUE** if you do not want to enable search **SEARCH=FALSE**
|
||||
- Add your previously saved MeiliSearch Master key to this line **MEILI_MASTER_KEY=** (the key is needed if search is enabled even on local install or you may encounter errors)
|
||||
- Save the file as **"C:/chatgpt-clone/api/.env"**
|
||||
- Save the file as .env at the root of your install dir e.g. **"C:/LibreChat/.env"**
|
||||
|
||||
### Run the app
|
||||
## Run the app
|
||||
|
||||
### Using the command line (in the root directory)
|
||||
To setup the app:
|
||||
|
|
@ -87,25 +77,30 @@ To use the app:
|
|||
- **Make a batch file to automate the starting process**
|
||||
- Open a text editor
|
||||
- Paste the following code in a new document
|
||||
- The meilisearch executable needs to be at the root of the chatgpt-clone directory
|
||||
- The meilisearch executable needs to be at the root of the LibreChat directory
|
||||
- Put your MeiliSearch master key instead of "your_master_key_goes_here"
|
||||
- Save the file as "C:/chatgpt-clone/chatgpt-clone.bat"
|
||||
- Save the file as "C:/LibreChat/LibreChat.bat"
|
||||
- you can make a shortcut of this batch file and put it anywhere
|
||||
|
||||
```
|
||||
start "MeiliSearch" cmd /k "meilisearch --master-key your_master_key_goes_here
|
||||
|
||||
start "ChatGPT-Clone" cmd /k "npm run backend"
|
||||
start "LibreChat" cmd /k "npm run backend"
|
||||
|
||||
REM this batch file goes at the root of the chatgpt-clone directory (C:/chatgpt-clone/)
|
||||
REM this batch file goes at the root of the LibreChat directory (C:/LibreChat/)
|
||||
```
|
||||
##
|
||||
|
||||
### **Update**
|
||||
## **Update**
|
||||
- run `git pull` from the root dir
|
||||
- Run npm ci from root directory `npm ci`
|
||||
- Build the client by running `npm run frontend`
|
||||
|
||||
|
||||
##
|
||||
|
||||
### Note: If you're still having trouble, before creating a new issue, please search for similar ones on our [#issues thread on our discord](https://discord.gg/weqZFtD9C4) or our [troubleshooting discussion](https://github.com/danny-avila/LibreChat/discussions/new?category=troubleshooting) on our Discussions page. If you don't find a relevant issue, feel free to create a new one and provide as much detail as possible.
|
||||
|
||||
##
|
||||
|
||||
## [Go Back to ReadMe](../../README.md)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue